Agentic Index

The best agent infrastructure platforms in 2026, ranked

The best agent infrastructure platforms of 2026 are Mastra, Perplexity, and Agno, ranked by verified capability coverage on the Agentic Index. All 199 researched vendors in the category are scored against the same 14 capabilities, and Mastra documents the broadest coverage at 14.0 out of 14.

Agentic Index ranks 199 of the 200 agent infrastructure platforms in its index by verified capability coverage. These are platforms that provide deployment, orchestration, and runtime tooling for production agents. Each vendor is scored across the same 14 point taxonomy used throughout the index, most recently verified on 2026-10-28, and this ranking recomputes automatically as new research is verified. Vendors awaiting capability research are listed separately and are not ranked.

Buyers also search this category as agent runtimes, agent orchestration infrastructure, and AI agent deployment platforms.

Scored on 14 buyer facing capabilities researched from public sources. No vendor pays for placement. How this ranking works

Best agent infrastructure platforms by buyer need

Best for production reliability

Mastra

Documents 2.0 of 2 on testing and observability, and 14.0 of 14 overall.

Best for developer extensibility

Perplexity

Documents 2.0 of 2 on APIs, MCP support, and tool calling, and 13.5 of 14 overall.

Best for self hosted and sovereign deployment

Agno

Documents 2.0 of 2 on deployment control and model flexibility, and 13.0 of 14 overall.

Best for complex multi step work

AutoGPT

Documents 3.0 of 3 on orchestration, memory, and knowledge grounding, and 13.0 of 14 overall.

Each segment names the vendor with the most documented coverage on the criteria that segment depends on, computed from the same research as the ranking below. A vendor appears once, in its strongest segment.

1. 1

   M

   Mastra14.0 / 14

   Open source TypeScript framework for agents and workflows, with the Mastra Platform for hosted Studio, observability, evals and deployment.

   Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 12 more.

2. 2

   P

   Perplexity13.5 / 14

   Perplexity pairs its cited answer engine with Computer, an agent that turns a goal into a plan, hands the pieces to subagents in an isolated cloud sandbox, and acts across more than 400 apps, from Gmail and Slack to Salesforce and Snowflake. Computer runs on schedules or app events, keeps a per user memory called Brain, and lets people or admins pick models from Anthropic, OpenAI, Google and xAI. Enterprise plans add SSO, SCIM, custom roles and audit logs, and the Agent API opens the same runtime to developers.

   Full coverage on Browser / Computer-use and APIs / SDKs / MCP Extensibility and 11 more.

3. 3

   A

   Agno13.0 / 14

   Python agent framework and AgentOS runtime (formerly Phidata) for building, running and managing agents, teams and workflows in your own cloud.

   Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 11 more. No documented coverage on Browser & Computer Use.

4. 4

   A

   AutoGPT13.0 / 14

   Open-source AI agent platform with a visual block-based builder, agent marketplace, and continuous agent runtime, available as free self-hosted software or a hosted cloud with subscription plus pay as you go credits.

   Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 10 more.

5. 5

   T

   Tray.ai13.0 / 14

   Enterprise integration and automation platform with an agent layer, offering more than 700 connectors, visual workflows, agents built without code and grounded in a synced knowledge base, and an MCP gateway that governs which tools agents may call.

   Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 11 more. No documented coverage on Browser & Computer Use.

6. 6

   W

   Writer13.0 / 14

   Enterprise agent platform with automation that keeps output on brand, Knowledge Graph RAG, and configurable agent skills and playbooks, built for teams of knowledge workers with strict governance requirements.

7. 7

   A

   Akka12.5 / 14

   Enterprise agentic AI platform that builds and runs multi agent systems on a durable distributed runtime, unifying orchestration, agents, memory, and streaming in one SDK.

   Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 10 more. No documented coverage on Browser / Computer-use.

8. 8

   K

   Kestra12.5 / 14

   Open source declarative orchestration platform whose AI agents call its 2,000+ plugins as tools, remember across runs and pause for approval, self hosted under Apache 2.0 or run on the Enterprise Edition or Kestra Cloud.

9. 9

   L

   Latenode12.5 / 14

   Low code agent and automation platform billing by execution seconds rather than per task, with a built in headless browser and database, bundled access to GPT, Claude and Gemini, and self hosted or on premise deployment.

10. 10

    S

    SimplAI12.5 / 14

    Datafuse Technology Inc builds SimplAI, an enterprise agentic AI operating system for building, orchestrating and governing multi agent systems across cloud, on premises and air gapped environments.

11. 11

    E

    Edge Delta12.0 / 14

    Agentic observability platform whose AI Teammates, coordinated by the OnCall AI super agent, autonomously triage alerts, run root cause analysis, review code and PRs, and file tickets across SRE, security, and DevOps work, grounded in real time telemetry.

12. 12

    H

    Haystack12.0 / 14

    Open source Python framework by deepset for agents, RAG and search pipelines, with the Haystack Enterprise Platform for managed or self-hosted deployment and governance.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 9 more. No documented coverage on Browser & Computer Use.

13. 13

    I

    Infobip12.0 / 14

    Global CPaaS provider whose AgentOS platform runs autonomous AI agents across more than fifteen channels, with customer selected LLMs, a Quality center for agent testing, and a fully public developer surface.

14. 14

    L

    LlamaIndex12.0 / 14

    Document agents and parsing platform (LlamaParse, LlamaAgents) plus the open source LlamaIndex framework for building agents and RAG over your data.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 9 more. No documented coverage on Browser & Computer Use.

15. 15

    P

    Pydantic AI12.0 / 14

    Open source Python agent framework from the Pydantic team, with typed tools, durable execution, the Pydantic AI Harness capability library and Pydantic Evals.

16. 16

    S

    Shakudo12.0 / 14

    Shakudo is a sovereign AI and data platform that deploys inside a company's own Kubernetes environment, on any major cloud, on premises or air gapped. Its Kaji agent plans and carries out work from plain language, runs code, uses a real browser, remembers facts in a knowledge graph, runs on schedules and delegates to parallel sub agents, with model calls routed through Shakudo's AI gateway.

    Full coverage on Browser / Computer-use and Model Flexibility & Routing and 9 more. No documented coverage on APIs / SDKs / MCP Extensibility.

17. 17

    S

    Sinch12.0 / 14

    The global communications platform behind SMS, RCS, WhatsApp, voice and email for more than 190,000 businesses, selling Chatlayer, a flow based builder for multilingual chat and voice bots that call outside systems, answer from a knowledge base and hand off to live agents, plus Voice Relay, Functions and an MCP server for agents customers build themselves.

    Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 9 more. No documented coverage on Browser / Computer-use.

18. 18

    S

    SmythOS12.0 / 14

    Open-source agent operating system pairing a visual builder and SDK with a runtime for deploying and governing agents across cloud, on-premises and edge.

19. 19

    S

    SnapLogic12.0 / 14

    Enterprise iPaaS repositioned as the Agentic Integration Company, letting teams build and run low-code LLM agents on top of more than a thousand prebuilt connectors, with MCP support and hybrid deployment.

20. 20

    S

    SuperAGI12.0 / 14

    Open-source MIT-licensed framework for building and running autonomous agents, with a graphical builder, toolkit marketplace, layered memory and self-hosting.

21. 21

    T

    Tembo12.0 / 14

    Cloud execution platform for coding agents you already use, running Claude Code, Codex, Cursor, OpenCode, Amp and Pi across repositories on signals from GitHub, Linear, Jira, Sentry and Slack, self hostable in your own cloud.

22. 22

    W

    Windmill12.0 / 14

    Open source workflow engine and developer platform: scripts in 20+ languages become flows, apps and endpoints, with AI agent steps and evals, approval steps, broad triggers and full self-hosting.

23. 23

    x

    xpander.ai12.0 / 14

    Governed runtime for enterprise AI agents: runs the agents teams already use, with approvals, audit, memory, knowledge and cloud, hybrid or air-gapped deployment.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 9 more. No documented coverage on Browser & Computer Use.

24. 24

    Datafold11.5 / 14

    Data engineering automation platform whose AI Migration Agent translates and validates data pipelines to full parity, with a Data Knowledge Graph and MCP tools that give coding agents the lineage and business logic of the customer's data.

    Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 8 more. No documented coverage on Browser / Computer-use.

25. 25

    Delight.ai11.5 / 14

    Enterprise AI agent platform from Sendbird, running omnichannel agents with a dedicated memory platform and the Trust OS governance layer for observability, control, and staged release.

26. 26

    Gnani.ai11.5 / 14

    Voice AI platform with foundational speech models and agents that run production workflows for enterprises.

27. 27

    Itential11.5 / 14

    Agentic orchestration platform for network and infrastructure operations where AI reasons and proposes but never touches infrastructure directly. Every human, workflow or agent action executes through one governed engine with RBAC, approval gates, blast radius limits, validation, rollback and immutable audit trails.

28. 28

    LangChain11.5 / 14

    Three open source agent frameworks, with LangChain for tool calling agents on any model provider, LangGraph for durable, stateful orchestration, and Deep Agents for long running agents.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 8 more. No documented coverage on Browser & Computer Use.

29. 29

    LangSmith11.5 / 14

    LangChain's commercial agent engineering platform, with tracing and evaluation, managed deployment of long running agents, no code Fleet agents, an issues agent, an LLM gateway and sandboxes, sold per seat with usage metered on top.

30. 30

    Letta11.5 / 14

    Memory-first agent harness from the MemGPT team: Letta Agent and Letta Code, plus an Agent SDK and self-hosted App Server for embedding stateful agents that learn over time.

31. 31

    nexos.ai11.5 / 14

    Governed AI platform that gives companies an employee Workspace with 200+ models, Projects, scheduled no code agents and approval gates, plus a Gateway API, under one set of admin controls.

32. 32

    Sourcegraph11.5 / 14

    Code intelligence platform whose code graph indexes entire organizations for exhaustive search, Deep Search answers with citations, and Batch Changes across many repositories. An MCP server feeds that code graph to third party coding agents as context.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 8 more. No documented coverage on Browser & Computer Use.

33. 33

    Anchor Browser11.0 / 14

    Cloud hosted browser infrastructure that lets AI agents operate real web interfaces, navigating, authenticating, filling forms, and extracting data on sites that have no API.

    Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 8 more. No documented coverage on Memory & State Persistence and Knowledge Grounding & RAG.

34. 34

    Pipedream11.0 / 14

    Integration platform for AI agents and automations, offering 10,000+ prebuilt tools across 3,000+ APIs with managed OAuth through SDKs, an API and MCP, plus code first workflows with triggers, approvals and event history.

35. 35

    Redwood Software11.0 / 14

    Workload and service orchestration company whose RunMyJobs SaaS platform runs enterprise job chains across SAP, cloud and on premises systems and now gives AI agents governed access to them through Agent Studio, agentic workflows and an MCP server.

    Full coverage on APIs / SDKs / MCP Extensibility and Prebuilt Agents / Templates / Packs and 7 more. No documented coverage on Browser / Computer-use.

36. 36

    Smallest AI11.0 / 14

    Voice AI platform covering the full stack, pairing Atoms, a no code voice and chat agent builder handling conversations in more than twenty languages, with its own co optimized models, Lightning text to speech at roughly one hundred millisecond latency and Pulse speech to text with a sixty four millisecond first transcript.

37. 37

    Telnyx11.0 / 14

    Telnyx is a communications carrier that runs AI Assistants on its own network and GPUs. Teams configure voice and chat agents in a portal with their choice of model, speech providers, tools, MCP servers and knowledge bases, guide them with conversation workflows, check them with AI tests and release them through versioned canary traffic splits, at $0.05 a minute for the voice engine.

    Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 7 more. No documented coverage on Browser / Computer-use.

38. 38

    Thread AI11.0 / 14

    Lemma is AI orchestration infrastructure for durable, governed agent workflows, with human handoff states, a function registry, scheduled and streaming triggers, identity provider access control, and VPC or on-premises deployment.

39. 39

    Trigger.dev11.0 / 14

    Open source TypeScript platform for long-running background tasks and AI agents with no timeouts, a chat agent runtime with stored conversations and tool approvals, on managed cloud or self-hosted under Apache 2.0.

40. 40

    Vellum11.0 / 14

    Agent builder and evaluation platform with workflow orchestration, observability environments, model flexibility, and a free-tier entry, for product teams and AI developers building and managing production agents.

41. 41

    Apify10.5 / 14

    Cloud platform and marketplace of more than 73,000 ready-to-run Actors for web data and automation, with proxies, schedules and an MCP server that exposes them as tools for AI agents.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 6 more. No documented coverage on Knowledge Grounding & RAG.

42. 42

    Bernstein10.5 / 14

    Open source deterministic orchestrator that runs 40 plus CLI coding agents such as Claude Code, Codex, and Gemini CLI in parallel git worktrees with no model in the coordination loop, so runs replay byte identically behind an HMAC signed audit chain.

43. 43

    Bluebricks10.5 / 14

    Context and control layer that lets AI agents operate cloud infrastructure, grounding them in a live cloud graph and routing every change through governed plan, approve, and apply orchestration.

    Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 7 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing.

44. 44

    Cartesia10.5 / 14

    Real time voice models (Sonic text to speech, Ink speech to text) and Managed Agents, a hosted voice agent platform with tools, a knowledge base, batch calling and call evaluations.

45. 45

    Forest10.5 / 14

    Operational infrastructure for regulated fintech ops where human teams and AI agents run KYC, AML, payments and case workflows on the customer's own data, with the backend self hosted, bring your own model, an MCP server exposing Forest to outside agents, and a record level audit trail on every action.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 7 more. No documented coverage on Browser / Computer-use and Memory & State Persistence.

46. 46

    Moderne10.5 / 14

    Moderne is an enterprise platform on the open source OpenRewrite engine. It builds type aware Lossless Semantic Trees of an entire estate and runs deterministic refactoring recipes across thousands of repositories at once, and local and remote MCP servers expose those recipes as tool calls to any coding agent.

47. 47

    Netlify10.5 / 14

    Web platform whose Agent Runners run Claude Code, Codex, Gemini and OpenCode on live projects with previews and approval before publishing, plus an AI Gateway, durable workflows and an MCP server for agents.

48. 48

    OpenRouter10.5 / 14

    Unified API and marketplace routing agents to 500+ models from 80+ providers through one OpenAI compatible endpoint, with failover, spend controls, in-region routing and the Ori agent CLI.

49. 49

    Pipecat10.5 / 14

    Open-source framework for building real-time voice and multimodal AI agents.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more.

50. 50

    SentinelOne10.5 / 14

    Purple AI runs zero-click investigations to a verdict with an auditable evidence chain, then either triggers policy-driven response or prompts an analyst. Hyperautomation adds 130+ templates and approval gates. Plans start at $179.99 per endpoint per year, and the agentic analyst is in Enterprise.

51. 51

    Twilio10.5 / 14

    Twilio, the communications platform behind SMS, voice and WhatsApp for hundreds of thousands of businesses, now sells the layer around an AI agent the customer builds. Agent Connect wires any LLM agent into its channels, Conversation Memory keeps customer profiles that build up across calls and chats, Orchestrator threads every channel into one conversation, and Conversation Relay puts the agent on a phone call.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 6 more. No documented coverage on Browser / Computer-use.

52. 52

    Braintrust10.0 / 14

    AI observability and evaluation platform: traces, datasets, experiments, online scoring and human review, with hosted prompts and tools, a model gateway, the Loop agent and an MCP server.

53. 53

    Browserbase10.0 / 14

    Hosted browsers for AI agents, plus Browserbase Agents, Functions, Fetch and Search on one API key.

    Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 6 more. No documented coverage on Prebuilt Agents, Templates & Packs and Knowledge Grounding & RAG.

54. 54

    Inngest10.0 / 14

    Durable workflow engine for AI applications that runs step-based functions on your own hosts, with model calls offloaded through step.ai, the AgentKit agent framework, agent evals and a self-hostable server under the SSPL.

55. 55

    LangWatch10.0 / 14

    Open source platform for agent tracing, simulation-based agent testing and evaluation, with an AI gateway for routing and governance and Langy, an automated AI engineer that opens pull requests.

56. 56

    Paragon10.0 / 14

    Integration infrastructure for AI products: managed ingestion with RAG permissions, one API and MCP server for hundreds of agent actions, event forwarding and an embedded workflow builder.

57. 57

    QA Wolf10.0 / 14

    End-to-end testing platform whose agent maps an app and writes Playwright and Appium tests from prompts, run in parallel on deploy, schedule or pull request, sold self-serve by usage or as a managed service with guaranteed coverage.

58. 58

    Waniwani10.0 / 14

    AI distribution platform: an open source SDK and hosted platform for MCP apps that quote, book and capture leads inside ChatGPT, Claude and Gemini, with synthetic buyer testing, analytics and compliance monitoring.

59. 59

    Zaro10.0 / 14

    Shared context layer for enterprise AI: company knowledge held as versioned, permissioned files that people and agents read from and write back to, with approval gates and a full action trail.

    Full coverage on Browser & Computer Use and Memory & State Persistence and 5 more. No documented coverage on Triggers & Channel Coverage.

60. 60

    AlphaBitCore9.5 / 14

    AI control plane for regulated financial firms: one gateway enforces policy on every model, tool, workflow and agent call before it runs, and a sealed, replayable record proves what happened.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 6 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 1 more.

61. 61

    Avesha9.5 / 14

    Obliq, Avesha's autonomous AI SRE for Kubernetes and agentic workloads: agents watch CI and telemetry, synthesize root cause and execute rollbacks, replica bursts or config patches under risk scores and policy as code.

    Full coverage on Model Flexibility & Routing and Triggers & Channel Coverage and 4 more. No documented coverage on Browser / Computer-use.

62. 62

    Chamber9.5 / 14

    AIOps agent for ML teams: Chambie runs in the customer's own GPU cluster, diagnoses failed training jobs, applies typed fixes under risk tiered Slack approvals, and reclaims idle GPUs.

    Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 5 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing.

63. 63

    Composio9.5 / 14

    Action layer for AI agents, with more than 1,500 toolkits behind managed OAuth for each user, approvals before chosen tools run, a Firewall against prompt injection, triggers, a code sandbox and a cloud browser, and a log of every tool call.

64. 64

    Corti9.5 / 14

    AI infrastructure for healthcare developers: clinical speech to text, medical coding, text generation, EU-hosted Corti Models and an Agentic Framework with connectors, traces and a 20+ agent library, through one API with published usage pricing.

65. 65

    Instantly9.5 / 14

    Cold email platform with named agents: the AI Sales Agent finds leads in a 450M+ database, writes and sends sequences with manual approval or on autopilot, and the AI Reply Agent answers replies.

66. 66

    lemlist9.5 / 14

    French multichannel outbound platform with named agents (lemAgent plus signal, enrichment and messaging agents), a 650M+ lead database, an MCP server whose tools build and launch sequences, and a library of Claude skill files.

67. 67

    LiteLLM9.5 / 14

    Open source AI gateway and Python SDK: one OpenAI compatible API to 140+ model providers, plus MCP and agent gateways, keys, budgets, routing and self-hosting.

68. 68

    Personal AI9.5 / 14

    AI persona and memory platform: personas trained on an organization's own content, each with segregated memory, working in messages, channels, SMS and voice on Autopilot or Copilot, with a documented API, now positioned as a telco-optimized stack for agents on the carrier network.

69. 69

    Plivo9.5 / 14

    A voice and messaging API company whose AI Agent studio builds agents for calls, web chat, SMS and WhatsApp as visual flows, drafted from a plain English description by its Vibe Agent, with app actions, HTTP requests, a synced knowledge base and handover to human teams, at $0.03 a minute excluding telephony, alongside SIP trunking and audio streaming for agents built on LiveKit, Pipecat or Vapi.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser / Computer-use.

70. 70

    Pointee9.5 / 14

    Orchestration and governance platform that maps processes with an AI interviewer, runs people, AI agents and RPA robots in governed workflows, and uses Guardian Agents to catch and roll back failing automations.

    Full coverage on Testing, Debugging & Optimization and Prebuilt Agents / Templates / Packs and 7 more. No documented coverage on Browser / Computer-use and APIs / SDKs / MCP Extensibility and 2 more.

71. 71

    SageOx9.5 / 14

    Shared team memory for human and AI coworkers: captures discussions and coding sessions into a git-based Team Context and Ledger that primes every agent session, with an MCP server, REST API, CLI and an open-source AI coworker for Slack.

72. 72

    TrueFoundry9.5 / 14

    Enterprise AI gateway for LLMs, MCP servers and agents, with a hosted agent harness, deployable as SaaS, VPC, on-prem or air-gapped.

73. 73

    Airtop9.0 / 14

    Cloud browsers for AI agents that compile plain English workflows into deterministic agents: runs on schedules or triggers, self-heals broken runs, persists authenticated profiles, and supports Live View human takeover. SDKs, REST APIs, and a builder agent named Mark.

74. 74

    Arize AI9.0 / 14

    AI observability and evaluation platform that traces, evaluates, and monitors LLM applications and agents, with an open source core in Phoenix.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 6 more. No documented coverage on Browser & Computer Use and Memory & State Persistence and 2 more.

75. 75

    Capsule Security9.0 / 14

    Runtime security layer for AI agents that discovers agents across builders, coding tools and enterprise platforms, maps them in an agent security graph and blocks unsafe tool calls inline, with a consent gated Guardian Agent assistant and a GraphQL API.

76. 76

    Celonis9.0 / 14

    Process intelligence platform whose AgentC suite and Celonis Context Model give AI agents the business context to analyze, design, and operate autonomous enterprise processes.

    Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 6 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

77. 77

    Extend9.0 / 14

    Document processing infrastructure for AI agents: five composable APIs for parsing, extraction, splitting, classification and form editing, wrapped in versioned workflows with conditional routing, a confidence-threshold human review gate, and an evaluation framework with labeled evaluation sets and a publish gate.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Prebuilt Agents, Templates & Packs and 1 more.

78. 78

    F5 AI Guardrails9.0 / 14

    F5's AI security platform, formerly CalypsoAI, that runs inline guardrails on prompts, responses and agent tool calls across any model and, as F5 AI Red Team, red teams the customer's models and agents with scheduled attack campaigns, as SaaS or self-hosted.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 6 more. No documented coverage on Browser & Computer Use and Memory & State Persistence and 2 more.

79. 79

    Galileo9.0 / 14

    AI reliability platform that evaluates, observes, and guardrails GenAI apps and agents using its own low latency Luna evaluation models.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 6 more. No documented coverage on Browser & Computer Use and Memory & State Persistence and 2 more.

80. 80

    HiddenLayer9.0 / 14

    AI security platform for the customer's own models and agents: AI discovery, model supply chain scanning, red team evaluations against the customer's AI applications, and runtime policies with turn-by-turn agent session replay; SaaS or self-hosted.

81. 81

    Island9.0 / 14

    The enterprise browser as a control plane for AI: governed agents that act in the browser and through Island hosted MCP, per agent permissions and human approval rules, audit logs of every prompt, tool call and agent action, and model agnostic provider choice.

82. 82

    Langbase9.0 / 14

    Serverless developer platform of composable AI primitives: pipe agents, managed RAG memory, threads, workflows and tools, with 100+ models on your own keys, an API, SDK and remote MCP server.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser & Computer Use and Triggers & Channel Coverage.

83. 83

    MakinaRocks9.0 / 14

    Industrial AI company selling two halves: Runway, an AI operating system that handles identity, permissions, GPU allocation and audit logging once at the platform level so teams can deploy pre-installed, catalog or bring-your-own AI applications on top, built to install in air-gapped networks; and Specialized AI, four agent lines for expert augmentation, control, predictive operations and machine vision, plus DrawX for engineering drawings.

    Full coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 4 more. No documented coverage on Browser & Computer Use and Memory & State Persistence.

84. 84

    Opik9.0 / 14

    Open source LLM and agent observability and evaluation platform from Comet, with tracing, LLM as a judge metrics, guardrails, and an agent optimizer.

85. 85

    Phonic9.0 / 14

    Speech to speech voice agent platform on Phonic's own audio models: developers build agents with webhook, WebSocket and MCP tools, run them on phone numbers, SIP trunks, LiveKit or apps, hand off between agents, and score calls with eval prompts and replays. SOC 2 Type II, SSO, self host on Enterprise; usage pricing from $0.14 a minute.

86. 86

    Turbotic9.0 / 14

    Swedish AI automation company whose Automation AI builds, runs and repairs workflows from plain English, and whose Automation Orchestration gives one control plane over RPA robots and AI agents from UiPath, Blue Prism, Automation Anywhere and others.

    Full coverage on Deployment & Data Residency and Observability & Auditability and 3 more. No documented coverage on Memory & State Persistence.

87. 87

    W&B Weave9.0 / 14

    Agent and LLM observability, evaluation, and guardrails from Weights and Biases, with session aware tracing, LLM as a judge scoring, and safety scorers.

88. 88

    Zenity9.0 / 14

    Security and governance platform for enterprise AI agents: inventory and execution analysis across SaaS, cloud, endpoint and coding agents, posture checks before go-live, runtime Boundaries that allow, block or shut down agent actions, an Evaluate API and OpenTelemetry for custom agents, and Blue Agent for finding triage with human approval. SOC 2 Type II and ISO 27001.

89. 89

    Browserless8.5 / 14

    Headless browser infrastructure for automation and AI agents: managed Chrome, Firefox and WebKit over WebSocket, BrowserQL, REST APIs and an MCP server with a 136-skill catalog, with self-hosting into a VPC or air-gapped network.

90. 90

    C TWO8.5 / 14

    Vendor neutral control layer above RPA robots, AI agents, APIs and people, routing each work item to the best worker against its service level, recovering failed work and governing credentials, approvals and audit across the estate.

    Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 6 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 3 more.

91. 91

    Confident AI8.5 / 14

    LLM evaluation and observability platform from the creators of DeepEval, with 50+ open source metrics for testing agents, RAG, and chatbots.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Memory & State Persistence and 2 more.

92. 92

    DBOS8.5 / 14

    Open source durable execution library on Postgres that makes workflows, queues and AI agents fault tolerant with a few annotations, managed through the Conductor console.

93. 93

    DeepKeep8.5 / 14

    AI security platform: red teaming of the customer's models, apps and agents (with the Reddy agent pausing for human steering), an inline AI Firewall that logs every interaction, an Agent Scanner for n8n, CrewAI, Make and Dify agents, and SaaS to air-gapped deployment.

94. 94

    E2B8.5 / 14

    E2B is an open source sandbox platform that gives AI agents isolated Firecracker microVMs to run code, use tools and operate desktops, in E2B's cloud, the customer's own VPC, or self-hosted.

95. 95

    Fiddler AI8.5 / 14

    Fiddler AI is an AI control plane for enterprise agents: hierarchical agent tracing, evaluations, and real-time guardrails powered by in-environment Centor Models, with SaaS, VPC, on-premises and air-gapped deployment.

96. 96

    Firecrawl8.5 / 14

    Web data API for AI agents that searches, scrapes, crawls and acts on web pages through hosted browsers, with an open source core.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Testing, Debugging & Optimization and Memory & State Persistence and 2 more.

97. 97

    Hatchet8.5 / 14

    Open source, MIT-licensed task queue and durable workflow engine on Postgres for AI agents and background tasks, with DAGs, durable waits, broad triggers and observability, self-hosted or on Hatchet Cloud.

    Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 4 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 1 more.

98. 98

    HoneyHive8.5 / 14

    OpenTelemetry native platform to trace, evaluate, and monitor AI agents across development and production, combining automated and human evaluation with a versioned system of record.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Memory & State Persistence and 2 more.

99. 99

    Inworld AI8.5 / 14

    Realtime voice AI platform: expressive text to speech and speech to text, a speech to speech Realtime API with function calling, and an LLM Router across 220+ models. Infrastructure for developers, not an end user assistant.

100. 100

     Jetty8.5 / 14

     Automation platform for AI agent runs: markdown runbooks executed in managed sandboxes with a chosen agent and model, scored by code checks, checklists and LLM judges, with every step recorded.

     Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 5 more. No documented coverage on Browser / Computer-use and Memory & State Persistence and 2 more.

101. 101

     Kernel8.5 / 14

     Cloud browsers for AI agents: isolated Chromium sessions agents drive by computer controls, Playwright or CDP, with managed auth, vaults and agent payments, live view, replays and telemetry, regional browsers, an OpenAPI API, SDKs, CLI and hosted MCP server.

102. 102

     Kong8.5 / 14

     API gateway extended to agent traffic: Kong AI Gateway governs model, MCP and agent-to-agent calls from one control plane, with RAG injection, LLM-as-judge scoring, guardrails and regional hosting.

103. 103

     Langfuse8.5 / 14

     Open-source AI engineering platform for tracing, observability, prompt management, and evaluation, self-hostable or SaaS, with an OSS community, free plan, and model-agnostic coverage.

104. 104

     Maxim AI8.5 / 14

     Platform to simulate, evaluate and observe AI agents across the lifecycle, with offline and online evaluations, multi turn simulation, tracing, human review and a no code agent builder.

     Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Prebuilt Agents, Templates & Packs and 2 more.

105. 105

     Okta8.5 / 14

     Identity platform extended to AI agents: agents registered as first-class identities with owners, an Agent Gateway that authorizes and logs every tool call, step-up human approval for high-risk actions, time-bound access requests and a kill switch; add-on to Workforce Identity plans.

106. 106

     Restate8.5 / 14

     Durable runtime for workflows, services and AI agents that journals every step, keeps per-session agent state in Virtual Objects, and self-hosts as a single binary under the BSL or runs on Restate Cloud and BYOC.

107. 107

     Sales Layer8.5 / 14

     Product information platform with no-code AI agents that enrich, translate, validate and categorize catalog data on triggers or schedules, with simulation and review before publishing and a read/write MCP server.

     Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 5 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

108. 108

     Shopify8.5 / 14

     Commerce platform whose UCP-compliant MCP servers let any identified agent search products across Shopify, build carts, hand checkout to the buyer and follow orders, with trust tiers deciding what each agent may do.

109. 109

     Straiker8.5 / 14

     Agent security in three products: discovery that maps each agent's tools and permissions, attack agents that red-team the customer's agents on every change, and runtime tracing and blocking; SaaS or on premises.

110. 110

     Temporal8.5 / 14

     Open source durable execution platform whose Workflows as code survive crashes and run long-lived AI agents, self-hosted under MIT or on multi-region Temporal Cloud.

111. 111

     WitnessAI8.5 / 14

     AI security and governance platform running inline at the network layer: intent-based policies route, block or redact AI prompts and responses, agents are governed at the tool call and MCP server level, agent state and execution commands are captured at runtime and tied to a human identity, and Witness Attack red-teams the customer's models before production. Single-tenant SaaS, also sold on AWS Marketplace.

112. 112

     Autobound8.0 / 14

     B2B signal intelligence sold as infrastructure, with 700+ signal types from 35+ sources reachable by REST API, MCP server or bulk file, and an AI Studio layer that turns those signals into personalized outreach pushed to Outreach and Salesloft.

113. 113

     Bright Data8.0 / 14

     Web data infrastructure for agents, with an MCP server of 60-plus tools, unblocking and SERP APIs, managed cloud browsers, 1,300-plus pre-built scrapers and a 400-million-IP proxy network.

114. 114

     CorpusIQ8.0 / 14

     A read only business data layer for AI assistants: CorpusIQ connects 40+ business tools to ChatGPT, Claude, Perplexity and agent clients over one MCP connection and returns answers with the source record behind every number.

     Full coverage on APIs / SDKs / MCP Extensibility and Prebuilt Agents / Templates / Packs and 2 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization.

115. 115

     Daytona8.0 / 14

     Infrastructure that gives AI agents isolated, persistent sandboxes in under 90 milliseconds, with container, VM, Windows and GPU options, desktop computer use and OpenTelemetry tracing.

     Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 4 more. No documented coverage on Testing, Debugging & Optimization and Human Oversight & Guardrails and 2 more.

116. 116

     Force Equals8.0 / 14

     Agent governance control plane that sits above a customer's whole agent estate, routing guardrail breaches and anomalies to the right human and executing each decision back into the platform where the agent runs.

     Full coverage on Triggers & Channel Coverage and Observability & Auditability and 4 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

117. 117

     Freeplay8.0 / 14

     Ops platform for AI engineering teams that combines LLM observability, prompt management, evaluations, test runs and human review for AI products and agents.

     Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Prebuilt Agents, Templates & Packs and 3 more.

118. 118

     Gentoro8.0 / 14

     MCP platform that uses LLMs to turn OpenAPI specs into MCP tools ready for agents, with testing, deployment in the customer's environment and governance based on identity.

     Full coverage on Model Flexibility & Routing and Deployment & Data Residency and 2 more. No documented coverage on Browser & Computer Use and Memory & State Persistence.

119. 119

     Helicone8.0 / 14

     Open source LLM observability platform and AI gateway that logs, routes, caches, and costs every request through one OpenAI compatible endpoint.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 5 more. No documented coverage on Browser & Computer Use and Prebuilt Agents, Templates & Packs and 3 more.

120. 120

     Hyperbrowser8.0 / 14

     Cloud browser infrastructure for AI agents: stealth browser sessions in five regions, web scraping and extraction APIs, hosted computer-use agents, and sandboxes.

121. 121

     Idira8.0 / 14

     Identity security platform (now Idira by Palo Alto Networks) extended to AI agents, with agent discovery and inventory, an AI Agent Gateway and identity broker with just in time access, identity audit on every tool call, admin approval of MCP servers and a kill switch.

122. 122

     Kerno8.0 / 14

     AI backend QA engineer that coding agents drive over MCP to test every code change against the running app and dependencies, with baseline diffs, security checks, MCP server testing and plan approval gates.

     Full coverage on Testing, Debugging & Optimization and Deployment & Data Residency and 3 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 1 more.

123. 123

     Metorial8.0 / 14

     Integration and governance platform connecting agents and MCP clients to 1,000+ tools, with per-user auth, triggers, portals, skills, Protoguard screening and full tool-call logs.

     Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 5 more. No documented coverage on Browser / Computer-use and Prebuilt Agents / Templates / Packs and 3 more.

124. 124

     Mindgard8.0 / 14

     Automated AI red teaming of the customer's agents and AI systems, from reconnaissance through multi-step attacks, run continuously or in CI/CD, with a Python SDK, CLI and API and runtime protection.

125. 125

     Modal8.0 / 14

     Serverless cloud for AI workloads, with per second GPU billing, isolated sandboxes for untrusted agent code, scheduled functions and model endpoints.

126. 126

     Monte Carlo8.0 / 14

     Agent trust platform that traces and evaluates AI agents alongside the data they depend on, with a fleet of read-only observability agents, telemetry kept in the customer's own warehouse, and an MCP server.

127. 127

     Repello AI8.0 / 14

     Autonomous red teaming of the customer's AI apps and agents (ARTEMIS), runtime guardrails that log every call (ARGUS), endpoint agent discovery (Workstation Lens) and an AI inventory, with a Python SDK and GitHub Action.

128. 128

     Senso8.0 / 14

     Verified context infrastructure for AI agents, with a compiled, permissioned knowledge base, monitoring of what AI models say about an organization, and a verify and publish loop, reachable by API, MCP server, CLI and agent skills.

     Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 4 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

129. 129

     Snowplow8.0 / 14

     Real-time customer context layer that collects, validates and delivers behavioral event data to the customer's own warehouse, and through Signals gives AI agents per-user context, agentic session contexts and real-time intervention triggers.

130. 130

     Stacklok8.0 / 14

     Self-hosted platform for running and governing what agents reach: MCP servers in isolated containers, an identity-aware tool gateway and an AI gateway for model routing, budgets, screening and audit, on Kubernetes.

131. 131

     Temporal Cortex8.0 / 14

     Open scheduling infrastructure giving AI agents 18 calendar tools over MCP, A2A and REST, with deterministic time logic, cross-calendar availability and atomic booking.

     Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 2 more.

132. 132

     Traceloop8.0 / 14

     Maintainer of OpenLLMetry, the Apache 2.0 OpenTelemetry standard for LLM observability, plus a managed platform adding dashboards, evals, production monitors and experiments over managed datasets, deployable air gapped.

133. 133

     Trent AI8.0 / 14

     AI security engineer whose four specialist agents scan code, cloud and AI agents, prioritize exploitable risk, open fix pull requests and verify them, reaching developers inside their coding tools through a hosted MCP server and plugin.

134. 134

     Arcade7.5 / 14

     Actions runtime for AI agents, with delegated user authorization, more than 8,000 permission aware tools and MCP servers, inline policy hooks and a record of every action an agent takes.

     Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Browser & Computer Use and Triggers & Channel Coverage and 4 more.

135. 135

     Beam7.5 / 14

     Serverless cloud for AI workloads with GPU inference, sandboxes, task queues and an agent framework, running on Beam's cloud, your own AWS or GCP account, or self hosted from the open source Beta9 engine.

136. 136

     Bird7.5 / 14

     Bird, the messaging and email platform founded as MessageBird, is now built for AI agents the customer already runs. A hosted MCP server and CLI let coding and managed agents send SMS, WhatsApp and email and set up numbers and domains, webhooks deliver inbound messages to Claude Managed Agents or Grok, and agent mailboxes give an agent its own inbox.

     Full coverage on APIs / SDKs / MCP Extensibility and Deployment & Data Residency and 3 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

137. 137

     BotGauge7.5 / 14

     AI agent testing with red teaming, tracing, evaluations and policies, alongside autonomous QA as a service where AI agents generate, run and self heal software tests reviewed by a BotGauge expert pod.

     Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 3 more. No documented coverage on Model Flexibility & Routing and Prebuilt Agents / Templates / Packs and 2 more.

138. 138

     Deepgram7.5 / 14

     Voice AI infrastructure for real time speech to text (Flux, Nova-3), text to speech (Flux TTS, Aura) and a Voice Agent API that joins listening, thinking and speaking, with function calling and a choice of LLM.

139. 139

     Fluid Topics7.5 / 14

     Product knowledge platform that unifies technical content into an AI ready hub and, through core RAG services and an MCP server, grounds chatbots, copilots, and agents in trusted, cited product information.

     Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 3 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 2 more.

140. 140

     Operant AI7.5 / 14

     Runtime security for AI agents, MCP servers and employee AI tools, with tracing of each run from prompt to tool calls to memory, inline allow, block or redact decisions, and VPC, on prem or air gapped deployment on Enterprise.

141. 141

     Pillar Security7.5 / 14

     AI security platform that inventories the customer's agents and MCP servers, red-teams them with multi-turn and black-box attacks, and applies runtime guardrails that log every tool invocation; deployable in the customer's VPC.

142. 142

     Portkey7.5 / 14

     AI gateway, now presented as Prisma AIRS AI Gateway: one API to many model providers with routing, caching and guardrails, plus MCP and agent gateways, full request and tool-call logging, and enterprise governance.

143. 143

     Smithery7.5 / 14

     MCP registry and connection platform with managed OAuth, a Skills Registry, triggers and server publishing; acquired by Arcade.dev in August 2026.

144. 144

     Cognee7.0 / 14

     Open source AI memory engine combining relational, vector and graph stores, with remember, recall, improve and forget operations, session memory, and Python, REST, CLI and MCP access.

145. 145

     GPT Researcher7.0 / 14

     Open-source autonomous research agent with planner/execution multi-agent architecture and cited reports.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 2 more. No documented coverage on Testing, Debugging & Optimization and Memory & State Persistence and 2 more.

146. 146

     Guardrails AI7.0 / 14

     Open source framework for validating and correcting LLM inputs and outputs with guards built from a hub of prebuilt validators, plus Snowglobe, a simulation product that stress-tests agents with synthetic users before launch.

     Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 3 more. No documented coverage on Browser & Computer Use and Triggers & Channel Coverage and 3 more.

147. 147

     Hyperspell7.0 / 14

     Company brain for AI agents: 50+ OAuth connectors synthesized into a permission-aware context index, served over MCP, CLI and a REST API, with US or EU regions.

148. 148

     Klavis AI7.0 / 14

     Hosted MCP servers with per-user OAuth across more than a hundred apps, the open source Strata server, and sandboxed real-app environments for training and evaluating agents.

149. 149

     Lakera7.0 / 14

     AI security platform, now owned by Check Point, that screens prompts, responses and agent conversations at runtime against configurable guardrails and red teams the customer's models and agents with scored attacks that can gate releases in CI/CD.

     Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 4 more. No documented coverage on Browser & Computer Use and Model Flexibility & Routing and 4 more.

150. 150

     Lasso Security7.0 / 14

     AI security platform that discovers the customer's agents and applications, red-teams them with multi-turn attacks in CI/CD, and enforces intent-based runtime policies at the gateway with audit trails of agent activity.

151. 151

     Lemony7.0 / 14

     On premise AI appliance that runs large language models, secure retrieval, and agents entirely on a local device, giving regulated teams generative AI with no cloud and data sovereignty.

     Full coverage on Model Flexibility & Routing and Deployment & Data Residency and 1 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 1 more.

152. 152

     Noma Security7.0 / 14

     Agent security platform that discovers agents and MCP servers into an approval registry, controls access to each tool at runtime, logs and blocks agent traffic, and red teams the customer's agents continuously.

153. 153

     Stagehand7.0 / 14

     MIT licensed browser automation SDK from Browserbase for TypeScript, Python and Go. Natural language act, extract and observe steps mix with Playwright style code, on a local, attached or Browserbase browser, with the model the developer picks. v4 leaves orchestration to your code.

154. 154

     Steel7.0 / 14

     Open source browser infrastructure for AI agents, with cloud or self hosted Chromium sessions, stealth, CAPTCHA solving, persistent profiles and step by step agent traces.

155. 155

     Stepper7.0 / 14

     Stepper, from Paperform, builds workflow automations from a plain language description, combining a conversational AI builder with a visual editor, reusable components and triggers and actions across 489 apps. Skill Sets bundle those authenticated actions into scoped toolkits that Claude, Cursor, any MCP client or the stpr command line tool can call, with locked parameters and a log of every call.

     Full coverage on Model Flexibility & Routing and Triggers & Channel Coverage and 2 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 2 more.

156. 156

     Zep7.0 / 14

     Agent memory on temporal knowledge graphs, with per user memory graphs and standalone knowledge graphs whose facts carry validity windows, delivered through SDKs, a Memory MCP Server and the open source Graphiti engine.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 4 more.

157. 157

     Clawvisor6.5 / 14

     Source available authorization gateway for AI agents that vaults credentials, limits each agent to the task a person approved, holds out of scope or risky calls for approval, and records every tool call in a replayable audit trail.

     Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 5 more.

158. 158

     Dome Systems6.5 / 14

     Agent governance platform that registers every agent, routes its tool and model calls through a governed gateway and model broker, authorizes each call against Cedar rules before it runs, and records an immutable audit event for every action.

     Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 4 more. No documented coverage on Browser / Computer-use and Triggers & Channel Coverage and 5 more.

159. 159

     Exa6.5 / 14

     Web search and retrieval API built for AI agents that finds pages by meaning and returns clean contents, with an asynchronous research agent and scheduled monitors.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 2 more. No documented coverage on Testing, Debugging & Optimization and Deployment & Data Residency and 3 more.

160. 160

     Hamming AI6.5 / 14

     Voice and chat agent testing, red teaming and production monitoring platform that simulates thousands of calls, scores them on 50+ metrics and turns production failures into regression tests.

     Full coverage on Testing, Debugging & Optimization and Triggers & Channel Coverage and 3 more. No documented coverage on Browser & Computer Use and Model Flexibility & Routing and 4 more.

161. 161

     LabWired6.5 / 14

     A firmware simulator for engineers and coding agents: LabWired runs real firmware on modeled boards over a hosted MCP server, with its own firmware agent and CI tests.

     Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility and 2 more. No documented coverage on Browser / Computer-use and Human Oversight & Guardrails and 3 more.

162. 162

     Linx Security6.5 / 14

     Linx Security is an AI native identity security and governance platform that maps and governs human, non human and AI agent identities in real time, with an autonomous remediation agent, Autopilot.

163. 163

     Prime Intellect6.5 / 14

     Infrastructure for training, evaluating and running AI agents. Lab brings reinforcement learning environments, hosted training and evaluations, and Prime Intellect adds secure sandboxes, an inference API and GPUs from 50+ providers.

164. 164

     AIsa6.0 / 14

     Resource and payment gateway for AI agents, with one key to 110+ models and thousands of data and tool APIs, billed per call at provider prices with per key spend caps and machine payments.

165. 165

     Clutch Security6.0 / 14

     Non human identity security platform that discovers, governs and secures machine identities, AI agents and secrets across cloud, SaaS and on premises, built on the Identity Lineage graph, with customer set Agent Guardrails and ephemeral credentials.

166. 166

     Lightpanda6.0 / 14

     A headless browser engine written from scratch in Zig for machines, CDP compatible with Playwright and Puppeteer, with a native MCP server, a built in agent on the LLM of your choice, deterministic PandaScripts, and a self hosted binary or managed cloud in EU and US regions.

167. 167

     Mem06.0 / 14

     Open source memory layer for AI agents that extracts facts from interactions and returns relevant memories on later calls, scoped per user, agent, app and run, via API, SDKs, CLI and MCP.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 3 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 5 more.

168. 168

     OpenBox AI6.0 / 14

     Runtime governance layer that wraps AI agents built on Temporal, LangChain, CrewAI, Mastra and other frameworks, checks each operation against guardrails, policies and trust tiers before it runs, routes risky actions to human approval, and signs every session into a tamper-evident proof certificate.

169. 169

     PRE Security6.0 / 14

     AI native predictive SecOps platform with parserless ingestion, a SignalGate data fabric and an Autonomous Security Operator (SOARGPT, SOCGPT, ReportGPT, BreachGPT) that triages and acts across the security stack, deployable on premises, in a private cloud or as SaaS.

170. 170

     Stripe6.0 / 14

     Stripe's surface for agents, with the Agentic Commerce Suite and ACP for selling through AI agents, Shared Payment Tokens and machine payments for agent purchases, Link Agent Wallet approvals, and an MCP server into the Stripe account.

171. 171

     Unikraft6.0 / 14

     Cloud platform that runs any Dockerfile as a microVM with hardware isolation, millisecond cold starts and scale to zero, used for agent sandboxes, headless browsers and MCP servers.

     Full coverage on APIs / SDKs / MCP Extensibility and Triggers & Channel Coverage and 2 more. No documented coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 4 more.

172. 172

     Vocode6.0 / 14

     Open source Python library for building real time voice agents over phone, Zoom and WebRTC on the builder's choice of speech and language models. Its hosted API is no longer reachable.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 2 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 4 more.

173. 173

     Voker6.0 / 14

     Agent analytics platform whose drop-in SDK records every agent call and automatically annotates user intents, corrections and resolutions, reporting resolution and correction rates by agent version.

174. 174

     AgentQL5.5 / 14

     A self healing query language for the web, with natural language selectors that find elements by meaning, survive layout changes, and return structured JSON or Playwright locators. SDKs, a REST API, an MCP server and framework integrations make it the semantic selector layer beneath agents.

175. 175

     Apaleo5.5 / 14

     Open, API-first hospitality property management platform with its own embedded agentic layer, Apaleo Copilot, plus an MCP Server and an agent marketplace that let third-party agents run hotel operations across the same open APIs.

176. 176

     BAND5.5 / 14

     Interaction infrastructure for AI agents: a shared layer where agents from any framework and humans collaborate in chat rooms, with framework adapters, REST, WebSocket, MCP and A2A access.

177. 177

     Causa Prima5.5 / 14

     Agent to agent network for B2B finance where buyer and supplier AI agents settle invoices, disputes, and payment terms directly in real time, aiming to retire fixed net payment terms.

178. 178

     Coral5.5 / 14

     Coral, formerly Phoebe, is an open source data retrieval layer that gives the customer's AI agents one read only SQL interface across SaaS, internal systems and files, over SQL, a CLI and MCP.

179. 179

     AgentOps5.0 / 14

     Agent observability and debugging platform: open source SDKs trace LLM calls, tools and multi agent runs for step by step replay and cost tracking across 400+ models, with a public API, MCP server and self hosting.

180. 180

     Evoke Security5.0 / 14

     Detection and response for AI agents that records every prompt, tool call and action of the customer's agents across endpoint, web and cloud, inventories agents, MCP servers and Skills, and blocks or redirects risky actions in real time.

     Full coverage on Triggers & Channel Coverage and Observability & Auditability and 1 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 5 more.

181. 181

     Jina AI5.0 / 14

     Search foundation models and APIs. Reader turns URLs into markdown ready for an LLM, and Jina adds web search, multimodal embeddings and rerankers, served by API and MCP or deployed air gapped.

182. 182

     Rye5.0 / 14

     Agentic commerce infrastructure whose Universal Checkout API turns a product URL and tokenized payment into a placed order on the merchant's site, with a confirmation hold, price limits, and returns and product data APIs.

183. 183

     Bright Data Agent Browser4.5 / 14

     Bright Data's cloud browser runtime for AI agents (the Browser API), running headful or headless Chromium sessions with built in unblocking, CAPTCHA solving and IP rotation, driven over CDP from Puppeteer, Playwright or Selenium, with SSO and audit logs on Enterprise.

184. 184

     Catalog4.5 / 14

     Agentic experience platform for brands that keeps a verified, continuously synced record of every product and runs a parallel AI storefront with cart and checkout tools for shopping agents, distributed over ACP and UCP.

     Full coverage on APIs / SDKs / MCP Extensibility and Knowledge Grounding & RAG and 1 more. No documented coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 6 more.

185. 185

     Circuit & Chisel4.5 / 14

     ATXP gives AI agents their own funded accounts, with a wallet, an email address, an OpenAI compatible model gateway and pay per call tools, and lets developers charge agents per call from their own MCP servers.

186. 186

     Corellium4.5 / 14

     Virtual Arm hardware for firmware teams and their agents: Corellium boots real firmware on modeled boards, driven through a REST API, SDKs and MCP servers.

     Full coverage on APIs / SDKs / MCP Extensibility and Deployment & Data Residency and 1 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 6 more.

187. 187

     Cyara4.5 / 14

     CX assurance platform whose Botium and AI Trust products test, stress test and monitor customer facing AI agents and bots across voice and chat with goal based scoring, adversarial probes, compliance rules and live monitoring.

188. 188

     Nektar.ai4.5 / 14

     GTM telemetry that captures every customer interaction and writes it into the CRM and warehouse automatically, plus DAISY, an AI agent for buying-group, deal-health and forecast intelligence.

     Full coverage on Triggers & Channel Coverage and Knowledge Grounding & RAG and 1 more. No documented coverage on Browser / Computer-use and Testing, Debugging & Optimization and 6 more.

189. 189

     Nevermined4.5 / 14

     Payments infrastructure for AI agents: delegated cards and capped budgets for agents that buy, per request payment plans for agents and tools that sell, a Router and Catalog for external services, and one payment ledger.

190. 190

     Prefactor4.5 / 14

     Records every step AI agents take in production, ties each run to its agent version and environment, scores its data risk under profiles you set, and stores your own evaluation results per run, with SDKs and APIs across frameworks.

     Full coverage on APIs / SDKs / MCP Extensibility and Observability & Auditability. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 5 more.

191. 191

     Skyfire4.5 / 14

     Identity and payment tokens for AI agents: verified KYA identity, wallet or card backed payments that sellers charge after delivery, and a directory of services agents can pay for.

192. 192

     Tavily4.5 / 14

     A web access API for AI agents. It offers real time search, extraction, crawling, mapping and cited research, returned as clean content ready for LLMs through an API, SDKs, a CLI and remote MCP.

     Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing. No documented coverage on Testing, Debugging & Optimization and Triggers & Channel Coverage and 5 more.

193. 193

     Rime3.5 / 14

     Rime is text to speech infrastructure for voice agents, not a full agent. It offers Coda and Mist speech models over a streaming API, with pronunciation control and on premise deployment.

     Full coverage on APIs, SDKs & MCP Extensibility and Deployment & Data Residency and 1 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 8 more.

194. 194

     Speechmatics3.5 / 14

     Speech to text and text to speech APIs for voice agents and transcription, including Agent STT for turn based agent input, with cloud, on premise, virtual appliance and on device deployment and SOC 2 Type II and ISO 27001 certification.

195. 195

     Wokwi3.5 / 14

     An embedded and IoT simulator with a CI runner: Wokwi simulates ESP32, Arduino, STM32 and Pico boards, and its CLI ships an experimental MCP server for coding agents.

     Full coverage on Testing, Debugging & Optimization and APIs / SDKs / MCP Extensibility. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 7 more.

196. 196

     Lemrock3.0 / 14

     Agentic commerce infrastructure that ingests a brand's catalog, structures it for language models and builds the brand an agent storefront for discovery, recommendations and purchases inside AI assistants.

197. 197

     Veecle3.0 / 14

     Agent infrastructure for firmware: Chiplab, an MCP server that lets AI coding agents run and test firmware on virtual microcontrollers without physical hardware.

     Full coverage on Deployment & Data Residency. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 7 more.

198. 198

     TectoAI2.5 / 14

     AI governance for law firms and regulated organizations: find the AI tools people use, enforce AI policy per client and matter in the browser, and redact sensitive data on the device.

199. 199

     Within2.5 / 14

     AI transformation platform that observes how work actually happens across an enterprise, structures it into a living context graph it calls Company Brain, and serves that context to the customer's own agents, models and AI platforms over MCP. Companion handles discovery, Advisor ranks automation opportunities by ROI and packages reusable skill files, and the solutions surface spans finance, IT, GTM, HR and operations transformation. Within was formerly Klarity. Its Automate accounting platform was divested to Cognida in August 2026 and is no longer sold by Within.