Agentic Index

The best coding agents in 2026, ranked

The best coding agents of 2026 are Cognition, GitHub Copilot, and Kiro, ranked by verified capability coverage on the Agentic Index. All 97 researched vendors in the category are scored against the same 14 capabilities, and Cognition documents the broadest coverage at 13.5 out of 14.

Agentic Index ranks all 97 coding agents in its index by verified capability coverage. These are tools that write, edit, and ship software with varying degrees of autonomy. Each vendor is scored across the same 14 point taxonomy used throughout the index, most recently verified on 2026-11-01, and this ranking recomputes automatically as new research is verified.

Buyers also search this category as AI coding assistants, autonomous software engineers, and AI pair programming tools.

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

Best coding agents by buyer need

Best for complex multi step work

Cognition

Documents 3.0 of 3 on orchestration, memory, and knowledge grounding, and 13.5 of 14 overall.

Best for developer extensibility

GitHub Copilot

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

Best for production reliability

OpenHands

Documents 2.0 of 2 on testing and observability, and 13.5 of 14 overall.

Best for regulated and governed deployments

Kiro

Documents 3.0 of 3 on security, auditability, and human oversight, and 13.5 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

   C

   Cognition13.5 / 14

   Maker of Devin, an autonomous AI software engineer. Devin Desktop adds an Agent Command Center, Spaces for multi agent context sharing, and ACP support, so one developer can manage several agents from one place. Devin Oncall triages production incidents to a root cause.

2. 2

   G

   GitHub Copilot13.5 / 14

   GitHub's AI coding platform with cloud agents for autonomous PR lifecycle management, MCP support, model choice, and agentic coding from IDE through CI/CD.

   Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 11 more.

3. 3

   K

   Kiro13.5 / 14

   AWS's spec driven agentic development environment across IDE, CLI, Web and Mobile, where structured requirements and design documents are approved before code is written, with Powers plugins, agent hooks and enterprise governance controls.

4. 4

   O

   OpenHands13.5 / 14

   MIT licensed open source agent platform whose Agent Canvas self hosts and automates coding agents across local, VM, cloud and enterprise backends, running its own agent or third party harnesses like Claude Code, Codex and Gemini CLI over ACP.

   Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 11 more.

5. 5

   R

   Replit Agent13.5 / 14

   AI app builder and runtime for the full stack, where an agent builds the app, sets up the database, tests its own work in a real browser and deploys it. Built for builders, students and startups.

   Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 11 more.

6. 6

   Z

   Zencoder13.5 / 14

   Enterprise coding platform with multiple agents, whose Repo Grokking indexes across repositories and generates a persistent repo.md, then runs build, review and audit agents each on a different model, with Zentester for verification and governance that gates changes on approval.

   Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 11 more.

7. 7

   B

   Base4413.0 / 14

   AI app builder (a Wix company) with built in database, auth and hosting, plus Superagents: autonomous agents built from a plain language description that run on schedules and events with persistent memory.

8. 8

   B

   Baz13.0 / 14

   Engineering review platform whose agents govern AI-written code end to end: an AI code reviewer, a Spec Reviewer that runs your app in a sandbox and drives a browser to check the built experience against Figma and Jira, and Planner, whose plans a person approves before code is written.

9. 9

   F

   Factory13.0 / 14

   Agent native development platform whose Droids take a ticket from Linear or Jira and run it end to end, coordinated by Missions across parallel agents, from the app, CLI, headless CI or managed cloud sandboxes.

   Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 10 more.

10. 10

    K

    Kilo Code13.0 / 14

    Open source coding agent across VS Code, JetBrains, CLI, cloud, mobile and Slack, with specialist agents delegating to parallel subagents across git worktrees, browser and terminal control, and 500+ models at zero markup. Acquired by Anaconda July 2026.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 10 more.

11. 11

    O

    OpenAI Codex13.0 / 14

    OpenAI's agentic coding system across desktop, CLI, IDE, web, cloud and remote, with an OS-enforced sandbox and independent approval policy, Auto-review, skills and plugins, browser and computer use, and OpenTelemetry audit export.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 10 more.

12. 12

    R

    Roomote13.0 / 14

    Roomote, from the makers of the retired Roo Code extension, is a source available cloud coding agent that each team runs as its own single tenant deployment, hosted or self hosted. It takes work from Slack, Teams, Discord, Telegram, email, pull requests, Linear and schedules, runs the real dev environment in a sandbox, verifies and cross model reviews its changes, and returns pull requests with live previews, on any model the team chooses.

    Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 10 more.

13. 13

    W

    Warp13.0 / 14

    Agentic development environment born out of the terminal, pairing an open source Rust client with Oz cloud agents and Warp Factories. Factories, in early access, runs fleets of coding agents across the SDLC, defined as code, on any model or harness, with approval gates and audit trails for each tool call.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 10 more.

14. 14

    A

    Anthropic Claude Code12.5 / 14

    Anthropic's agentic coding system across terminal, desktop, IDE, web and CI, running a loop that plans, executes and verifies, with subagents, plugins, MCP tool access and a Chrome integration for driving real browser sessions.

    Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 10 more. No documented coverage on Model Flexibility & Routing.

15. 15

    C

    Capy12.5 / 14

    AI software engineer that runs parallel cloud coding agents in isolated VMs, from issue to merged pull request, with Slack, Linear and GitHub integrations. Built by Scrapybara, Inc., which moved from hosted computers for agents to Capy.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 9 more.

16. 16

    C

    Cursor12.5 / 14

    AI native editor and agent platform built on VS Code, with Tab predictive editing, an agent that runs on Cursor's own Grok and Composer models or outside frontier models, an Agents Window for directing fleets of background and cloud agents, and a plugin marketplace.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 9 more.

17. 17

    G

    Google Antigravity12.5 / 14

    Google's agentic development platform across a desktop app, CLI, Python SDK and IDE extensions, where agents work autonomously across editor, terminal and browser with model choice spanning Gemini and Claude.

18. 18

    G

    Greptile12.5 / 14

    AI code review agent that indexes your whole repository as a graph and keeps a self updating Knowledge Base of it, runs a swarm of parallel hypothesis scoped agents over each PR, with TREX (beta) starting the app in a sandbox and testing it, auto approve under a risk ceiling, and full self hosting including air gapped with customer supplied LLM providers.

    Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 9 more.

19. 19

    R

    Refact.ai12.5 / 14

    Open-source, local-first autonomous coding agent that plans, edits, runs tests and iterates inside your IDE with a thirty-action cap, keeping AST and vector indexes locally and running on your own model keys or local runtimes. The hosted Refact Cloud service is being retired.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 9 more.

20. 20

    A

    Augment Code12.0 / 14

    Augment Code is an AI coding platform built around its Context Engine, now part of Harness after an October 2026 asset acquisition. Its Cosmos product runs teams of specialized agents that coordinate across the software development lifecycle with shared memory, MCP and webhook integrations, and multi agent orchestration.

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

21. 21

    C

    Chipp12.0 / 14

    Chipp is a platform for building AI agents that serve customers and staff on a website, in Slack or Teams, by email, text, WhatsApp and phone, connected to the tools a business already uses. Agents remember users, take actions through integrations and custom APIs, check in proactively and are tested with evals, while Chipp Factory, documented as Alchemist, plans, builds, reviews, deploys and repairs production software from a plain language ticket.

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

22. 22

    Cline12.0 / 14

    Cline is an open source Apache 2.0 coding agent runtime across VS Code, JetBrains, CLI, a desktop app, a browser based cloud agent and an embeddable SDK, with Plan and Act modes, per action approval, an MCP marketplace, browser control and any model on your own key or weights.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 8 more.

23. 23

    CodeRabbit12.0 / 14

    AI code review agent for GitHub, GitLab, Azure DevOps and Bitbucket with review rules customized in YAML, automatic approvals under risk limits, a cross repository Triage queue, learning loops and enterprise self hosting.

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

24. 24

    Goose12.0 / 14

    Vendor neutral open source AI agent under the Linux Foundation's Agentic AI Foundation, running locally as desktop app, CLI or API, with MCP extensions, recipes and subagents, a scheduler, and 30+ model providers on your own keys.

25. 25

    JetBrains AI12.0 / 14

    Junie is JetBrains' coding agent, working in the IDE and as a standalone CLI. It runs a plan execute verify loop with agentic debugging through the real IDE debugger, and offers model choice across frontier providers and bring your own key.

26. 26

    Lovable12.0 / 14

    Natural-language full-stack app builder with MCP integrations, no-training data posture, regional hosting, and a collaboration-friendly surface for product builders and startups.

    Full coverage on Browser & Computer Use and Testing, Debugging & Optimization and 9 more. No documented coverage on Model Flexibility & Routing.

27. 27

    Qodo12.0 / 14

    An AI code review and governance platform, formerly CodiumAI, with parallel specialist review agents and a judge agent, a Context Engine that indexes the codebase and PR history, a Software Map of repository dependencies, Rule Miner that turns accepted review patterns into rules, PR Triage, and an Agentic Toolbox that brings Qodo's skills into Claude Code, Codex and Kiro.

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

28. 28

    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.

29. 29

    Embedder11.5 / 14

    A firmware coding agent that works on the real bench: Embedder reads datasheets and schematics, writes drivers, flashes boards and checks the result with probes and instruments.

    Full coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 8 more. No documented coverage on Browser / Computer-use.

30. 30

    Figma Make11.5 / 14

    Figma Make is Figma's prompt to app builder that turns ideas and existing Figma designs into code backed, visually editable prototypes and web apps, with plan mode, a Payload or Supabase backend, Make kits that carry a team's design system, and MCP connectors to tools such as Notion, Atlassian and Linear. Builders choose between GPT, Claude and Gemini models, publish to a figma.site address or a custom domain, and Enterprise adds data residency.

    Full coverage on Model Flexibility & Routing and Prebuilt Agents / Templates / Packs and 7 more.

31. 31

    Hoplite11.5 / 14

    Cloud coding agents in isolated sandboxes that import your local Claude Code, Codex or OpenCode setup, run in parallel with subagents, start from Slack, Linear, Sentry or a schedule, and hand back a pull request to review.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 7 more.

32. 32

    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.

33. 33

    Snyk11.5 / 14

    AI security platform whose Evo agents secure AI generated code and the coding agents that write it. It brings AI-SPM visibility across models, agents and MCP servers, continuous autonomous pentesting, runtime enforcement, and agents that fix vulnerabilities and open pull requests.

34. 34

    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.

35. 35

    Tabnine11.5 / 14

    Enterprise AI coding platform, acquired by Tricentis in July 2026 and deployable on premises or fully air gapped, whose Enterprise Context Engine builds a knowledge graph of an organization's systems for its agents to work from.

36. 36

    Anything11.0 / 14

    Anything is an AI app builder whose agent turns a plain language description into a working web app in React or a mobile app in React Native, with a PostgreSQL database, backend functions, sign in and payments, then publishes it to the web or submits it to the App Store and Google Play. Its Max mode builds, runs the app in a real browser or an iOS simulator, tests it like a user and fixes what breaks on its own.

    Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 6 more.

37. 37

    Poolside11.0 / 14

    Coding agent platform built on Poolside's own Laguna models, whose weights are published openly, with the pool CLI for developers and enterprise and government deployments inside the customer's boundary, including air gapped, where every agent action is recorded as a searchable trajectory.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 7 more. No documented coverage on Browser & Computer Use.

38. 38

    Potpie AI11.0 / 14

    Open source context layer that turns a codebase and its development lifecycle into a property graph for Claude Code, Codex, Cursor and OpenCode, sold to large engineering teams as an embedded engagement with forward deployed engineers that runs in the customer's VPC or on premises.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 7 more. No documented coverage on Browser & Computer Use.

39. 39

    Sonar11.0 / 14

    Verification layer for AI and agentic coding, and a standard for automated code review, with Gitar reviewing, fixing and verifying pull requests until CI passes, Sonar Vortex guiding and checking agents as they write, and a self managed SonarQube Server that now carries the agentic features.

40. 40

    Superblocks11.0 / 14

    Enterprise internal app platform whose Clark AI agent generates production apps from natural language inside existing user permissions, with a knowledge graph, user preference memory and three deployment models including full cloud prem.

41. 41

    Tabby11.0 / 14

    Open source, self hosted coding assistant serving fill in the middle completion, an Answer Engine for codebase questions, inline chat and a code browser on the customer's own hardware, with open models the customer chooses and no external database or cloud service. TabbyML also makes Pochi, an open source coding agent for VS Code that runs parallel agents, drives a browser and calls MCP tools.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 6 more.

42. 42

    Trae11.0 / 14

    ByteDance's AI coding platform. The all new TRAE joins an AI native IDE window with an Agent window for background, cloud and scheduled tasks, with custom agents, subagents, memories, marketplace plugins, browser use and built in or custom models. The enterprise offering comes through BytePlus.

    Full coverage on Browser & Computer Use and Model Flexibility & Routing and 8 more. No documented coverage on Testing, Debugging & Optimization and Deployment & Data Residency.

43. 43

    v0 by Vercel11.0 / 14

    Vercel's AI app builder that turns natural language into production React and Next.js code, with a VM-backed full-stack sandbox, Git branches and pull requests from chat, one-click deployment, and a Platform API with a TypeScript SDK exposing the whole build-and-ship agent programmatically.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 6 more.

44. 44

    Verdent11.0 / 14

    Verdent is an agentic coding suite whose desktop Manager turns a goal into a plan of subtasks and runs parallel workers in isolated git worktrees, with reviewer, verifier and planner subagents across Claude, GPT and Gemini models. Work can arrive from Slack, Telegram, Feishu or Discord or run on a schedule, and the same credits cover the VS Code and JetBrains extensions and browser based Verdent Cloud, which publishes web apps.

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

45. 45

    Vybe11.0 / 14

    AI coworkers that work inside a team's Slack and across thousands of connected services, with a gallery of ready made coworkers, a real browser, scoped memory, scheduled and event triggers and a full activity log, plus an app builder for internal tools.

    Full coverage on Browser & Computer Use and Model Flexibility & Routing and 7 more. No documented coverage on APIs, SDKs & MCP Extensibility.

46. 46

    Agent Zero10.5 / 14

    Open-source multi-agent framework that gives its agent a full Linux container with desktop and browser, subordinate agents, persistent memory, and scheduled tasks.

    Full coverage on Browser & Computer Use and Model Flexibility & Routing and 6 more. No documented coverage on Security, Identity & Governance.

47. 47

    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.

48. 48

    cubic10.5 / 14

    AI code review agent that reviews every pull request with whole-repository and cross-repo context, learns from reviewer corrections, runs scheduled codebase scans that file tickets and open fix PRs, and can auto-approve clean PRs under a policy you test in shadow mode first.

    Full coverage on Testing, Debugging & Optimization and APIs, SDKs & MCP Extensibility and 7 more. No documented coverage on Browser & Computer Use and Deployment & Data Residency.

49. 49

    depthfirst10.5 / 14

    AI security platform that detects, triages, and remediates software vulnerabilities.

50. 50

    Ellipsis10.5 / 14

    Managed agent platform for coding agents defined as YAML in your repo, running Claude Code, Codex or Gemini CLI in isolated per session sandboxes with scoped credentials and hard spend caps, triggered by GitHub, Slack, Linear and Sentry events or cron, with every session recorded.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 6 more. No documented coverage on Browser & Computer Use.

51. 51

    Emergent10.5 / 14

    An agentic vibe coding platform where builders describe an app in plain English and Emergent's agents plan, code, test and publish a full stack web or native mobile app, with a choice of build agent and model, GitHub export, and hosting on Emergent or, on Enterprise, in the customer's own cloud.

    Full coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 5 more.

52. 52

    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.

53. 53

    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.

54. 54

    OpenCode10.5 / 14

    Open source, model agnostic coding agent from Anomaly, running in the terminal, desktop, web, IDE or as a headless server, with Plan and Build modes and support for 75+ LLM providers using your own keys.

55. 55

    Playcode10.5 / 14

    Playcode pairs Playcode AI, an agent with its own cloud computer that builds websites, web apps and React Native mobile apps from a description, runs them and checks them in a real browser, with Playcode Cloud, which hosts the result with a database, file storage, background jobs, email, an AI gateway and custom domains. Models come from six labs at three levels, and an API, CLI, MCP server and SDK open the platform to coding agents and app code.

    Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 5 more.

56. 56

    Blink10.0 / 14

    AI app builder that turns a prompt into a full stack web or native mobile app with a database, sign in, payments and hosting, plus Blink Claw, always on agents that run on their own cloud machines and work in Slack, Telegram and Discord.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 4 more.

57. 57

    Bubble10.0 / 14

    Bubble is a visual app platform whose AI Agent plans and builds complete web and native iOS and Android apps from a prompt, with pages, a database, workflows and sign in, then keeps editing them under the builder's own permissions and approval mode. Its MCP server lets Claude, ChatGPT, Codex or Copilot build in Bubble with their own models, and apps run on Bubble's hosting with SOC 2 Type II and regional dedicated instances on Enterprise.

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

58. 58

    Builder.io10.0 / 14

    Builder.io is a multiplayer AI development platform where engineers, designers and product managers work with coding agents on a team's real codebase and design system. Agents start from Slack threads, Jira tickets or branches pushed from Claude Code or Cursor, run in parallel in cloud containers with live previews, use the company's own components, and return pull requests through the existing Git review, with review agents checking and fixing code first.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 4 more.

59. 59

    Charm10.0 / 14

    Terminal native AI coding agent from Charm with a broad choice of model providers, mid session model switching that keeps context, language server code intelligence, MCP and Agent Skills extensibility, and permission prompts before tool calls, running locally including air gapped.

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

60. 60

    CodeGPT10.0 / 14

    CodeGPT is a coding agent for VS Code, JetBrains IDEs and Cursor that reads the codebase, proposes a plan a developer can edit, then edits files and runs terminal commands with approval at each step. It works with models from more than 15 providers or local runtimes on the developer's own keys, connects MCP servers, and pairs with CodeGPT Studio for knowledge agents and repository graphs.

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

61. 61

    Cosine10.0 / 14

    UK sovereign AI lab whose Lumen coding models power a terminal CLI and cloud workspace, with Swarm mode multi-agent orchestration, a menu of more than 25 models, cross-session memory, and fully air-gapped deployment for regulated industries.

    Full coverage on Browser & Computer Use and Model Flexibility & Routing and 4 more.

62. 62

    UI Bakery10.0 / 14

    Internal tools platform whose AI App Agent turns a prompt into a working React app on the customer's data, with per tool ask or allow controls over migrations, data actions and screenshots, Git, checkpoints and self hosting.

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

63. 63

    Vibecode10.0 / 14

    Vibecode builds native Swift iPhone apps, React Native apps for iPhone and Android and web apps from a description, running Claude Code in a cloud sandbox with a per message choice of Claude, GPT, Gemini, Muse and GLM models. The agent tests its own changes in a browser or simulator, wires in a backend and 30+ APIs, and submits to the App Store, and a CLI and MCP server let other agents build on Vibecode.

    Full coverage on Browser / Computer-use and Testing, Debugging & Optimization and 5 more. No documented coverage on Security, Identity & Governance.

64. 64

    Zed10.0 / 14

    Open-source, GPU-accelerated Rust code editor with a native AI agent panel, parallel agents in isolated worktrees, per-tool permissions, and the open Agent Client Protocol that lets Claude Agent, Codex and OpenCode run inside the editor.

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

65. 65

    Aider9.5 / 14

    Open source, model agnostic terminal coding agent that edits your local git repo directly, with a tree-sitter repository map for whole project context and an architect mode pairing a reasoning model with a cheaper editor model.

66. 66

    AppFactor9.5 / 14

    Agentic platform that runs persistent agents across an enterprise application estate, interrogating running systems to discover, assess, modernize, build, deploy and maintain software continuously, with every change shipped as a pull request a human signs.

    Full coverage on Triggers & Channel Coverage and Prebuilt Agents / Templates / Packs and 7 more. No documented coverage on Browser / Computer-use and APIs / SDKs / MCP Extensibility and 2 more.

67. 67

    camelAI9.5 / 14

    camelAI makes camelCode, an MIT licensed coding agent that builds projects in a persistent workspace, connects to more than 50 services, runs scheduled agent turns and publishes to live URLs, hosted or self hosted on the customer's own model keys. It also sells camelRun, the hosted agent runtime camelCode runs on, and camelBot, a Discord bot builder.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 6 more. No documented coverage on Testing, Debugging & Optimization and Prebuilt Agents / Templates / Packs and 1 more.

68. 68

    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.

69. 69

    StackBlitz Bolt9.5 / 14

    Browser-native AI app builder from StackBlitz with open-source roots, token-based billing, and a visual edit-and-deploy experience for instant web app creation.

    Full coverage on Prebuilt Agents, Templates & Packs and Deployment & Data Residency and 4 more. No documented coverage on Browser & Computer Use.

70. 70

    Zite9.5 / 14

    AI app builder for internal tools and portals whose agent plans, builds and edits apps on a built in database in approve or auto modes, with model tier choice, an MCP server, SOC 2 Type II and unlimited users on every plan.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 5 more. No documented coverage on Browser & Computer Use and Deployment & Data Residency.

71. 71

    10Web9.0 / 14

    Agentic website platform whose AI agents build, host and manage websites, apps and online stores, including WordPress and WooCommerce sites, from a prompt, a URL clone or a Figma import through post launch care.

    Full coverage on APIs / SDKs / MCP Extensibility and Prebuilt Agents / Templates / Packs and 4 more. No documented coverage on Browser / Computer-use and Memory & State Persistence.

72. 72

    Choicely9.0 / 14

    Choicely is an AI app builder that creates native Swift and Java apps for iPhone and Android by chat, from an idea, a website or a template, with built in voting, polls, shops and push notifications for content driven businesses. It connects Supabase, Shopify, Squarespace and any HTTP API, publishes to both stores through its Publish Assistant, and offers a REST API and native SDKs, with EU or US data residency.

    Full coverage on APIs / SDKs / MCP Extensibility and Prebuilt Agents / Templates / Packs and 2 more.

73. 73

    Codebuff9.0 / 14

    Open source terminal coding agent that splits each change across specialized agents, an orchestrator with file picker, thinker, editor and reviewer agents, with per agent model choice on OpenRouter, a TypeScript SDK for embedding, and a public Agent Store of reusable agents.

    Full coverage on APIs, SDKs & MCP Extensibility and Model Flexibility & Routing and 3 more. No documented coverage on Security, Identity & Governance.

74. 74

    Google Jules9.0 / 14

    Google's asynchronous coding agent: takes a GitHub issue, plans it for your approval, works in an isolated cloud VM with Playwright browser verification, and opens a pull request, driveable from a REST API, CLI and scheduled tasks.

    Full coverage on Browser & Computer Use and APIs, SDKs & MCP Extensibility and 5 more. No documented coverage on Model Flexibility & Routing and Deployment & Data Residency and 1 more.

75. 75

    Ideavo9.0 / 14

    Ideavo is a free full stack AI app builder that runs on the customer's own AI subscription or API key, from ChatGPT through OAuth to Anthropic, OpenRouter or local models, with an autonomous Build Mode, a read only Plan Mode and parallel tasks in isolated sandboxes. It connects MCP servers, Neon, Better Auth, Razorpay and GitHub, and deploys to the customer's own Vercel or Railway account with exportable code.

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

76. 76

    Rocket9.0 / 14

    Rocket, formerly DhiWise, builds web apps in Next.js, mobile apps in Flutter, landing pages and websites from a prompt, a document, a live URL or a GitHub repository, wires in more than 25 services and launches to staging and production. Solve, its research engine, turns a business question into a structured report that can feed the next build, all on one credit balance with unlimited team members.

    Full coverage on Prebuilt Agents / Templates / Packs and Security, Identity & Governance and 4 more. No documented coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing.

77. 77

    Tadabase9.0 / 14

    AI and no code app platform: Tadabase AI builds React apps on Tadabase's database from chat, with action agents that run on record events and schedules behind approval gates, a published MCP server and SDKs and a retained log of every agent turn, beside classic no code plans with unlimited users and a HIPAA edition.

    Full coverage on APIs, SDKs & MCP Extensibility and Prebuilt Agents, Templates & Packs and 4 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization.

78. 78

    XBOW9.0 / 14

    Autonomous offensive security platform where a coordinator directs short lived attack agents that chain and validate exploits against web applications and APIs, now across a whole external application estate with Autonomous Exposure Management. Scope, rate and testing window controls, every agent action logged, a versioned REST API and webhooks for CI triggers, Jira and Microsoft Sentinel integrations, and regions in the US, EU and Singapore, with Australia, Canada and Japan in preview. Usage based credits, with a $50,000 a year package on AWS Marketplace.

79. 79

    Blackbox AI8.5 / 14

    Frontier inference platform with coding agents: an OpenAI compatible inference API and router over 300+ models, plus an agentic CLI and cloud agents that run Blackbox, Claude Code, Codex or Gemini on a repository, deployable from multi tenant SaaS to fully air gapped.

80. 80

    Blitzy8.5 / 14

    Autonomous enterprise software platform orchestrating thousands of agents against a knowledge graph of your codebase, running for days to return compiled and tested code, deployable in Blitzy's cloud, a VPC or on premises, including black box options.

81. 81

    Graphite8.5 / 14

    AI code review and pull request platform built around stacked PRs, a stack aware merge queue and Graphite Agent, which reviews, chats, applies fixes and merges. Graphite joined Cursor after a December 2025 agreement, and Cursor Cloud Agents open and update pull requests inside it.

    Full coverage on Testing, Debugging & Optimization and Triggers & Channel Coverage and 3 more. No documented coverage on Browser & Computer Use and Deployment & Data Residency.

82. 82

    ThinkReview8.5 / 14

    AI code review that opens in a private sidebar beside the diff on GitHub, GitLab, Azure DevOps and Bitbucket, in the cloud or self hosted. The review engine pulls related files, linked issues and overlapping pull requests through its own tool calls, runs up to ten custom review agents in parallel, and posts a finding only when a reviewer clicks Post. An MCP server and a Cursor plugin bring the same review into coding assistants. Free with 30 credits a month, paid plans from $15.

    Full coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing and 3 more. No documented coverage on Browser / Computer-use and Security, Identity & Governance.

83. 83

    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.

84. 84

    Superapp8.0 / 14

    Superapp is an AI builder that turns a plain English description into native Swift apps for iPhone, iPad, Apple Watch and Mac plus a website, with a managed Superapp Cloud backend or Supabase, RevenueCat payments and guided App Store submission. Its Selfdrive agent then markets the published app every night across Apple Ads, App Store optimization, SEO and creator campaigns, acting only on tasks the owner approves.

    Full coverage on Human Oversight & Guardrails and Triggers & Channel Coverage and 2 more. No documented coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing.

85. 85

    CatDoes7.5 / 14

    CatDoes is an autonomous cloud agent with its own computer that plans, writes and tests React Native Expo mobile apps and React websites from a description, provisions a backend with database, sign in, storage and edge functions, and prepares App Store, Google Play and web releases. It also rebuilds an existing website as a native app, works on imported GitHub codebases and fixes errors caught by built in crash monitoring.

    Full coverage on Testing, Debugging & Optimization and Human Oversight & Guardrails and 1 more. No documented coverage on APIs / SDKs / MCP Extensibility and Model Flexibility & Routing.

86. 86

    Google AI Studio7.5 / 14

    Google AI Studio's Build mode turns a prompt into a working app: a full stack web app with a React front end and a Node.js server, or a native Android app in Kotlin and Jetpack Compose. Its coding agent installs packages, provisions Firestore and Firebase Authentication, wires Gmail, Sheets, Drive and other Workspace APIs with OAuth handled, syncs both ways with GitHub and publishes to Cloud Run.

    Full coverage on Prebuilt Agents / Templates / Packs and Workflow Orchestration and 1 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing.

87. 87

    Locofy7.5 / 14

    Locofy converts Figma and Penpot designs into production frontend code for React, React Native, Next.js, Vue, Angular, Flutter, HTML, SwiftUI and Jetpack Compose using its own Large Design Models, then lets an Agent Mode refine the code by prompt. Its MCP server and CLI bring the conversion into Claude Code, Cursor, Copilot and Windsurf, and enterprises can run it in a private cloud or on premises.

    Full coverage on Prebuilt Agents / Templates / Packs and Deployment & Data Residency and 1 more. No documented coverage on Browser / Computer-use and Model Flexibility & Routing.

88. 88

    AgentUI7.0 / 14

    Managed AI app builder for operations teams that generates and hosts internal tools with a human support team behind them, audit logs, role based access, a SOC 2 badge and a JSON CLI for outside coding agents.

    Full coverage on Prebuilt Agents, Templates & Packs and Security, Identity & Governance and 2 more. No documented coverage on Browser & Computer Use and Testing, Debugging & Optimization and 2 more.

89. 89

    GoCodeo7.0 / 14

    VS Code extension that builds, tests and deploys full stack apps from a prompt, with ASK, BUILD, TEST and MCP flows, a model selector across four providers, 100+ tools via customer defined MCP servers, and one click Supabase and Vercel setup.

    Full coverage on Testing, Debugging & Optimization and Model Flexibility & Routing and 1 more. No documented coverage on Browser & Computer Use and Triggers & Channel Coverage and 1 more.

90. 90

    NxCode7.0 / 14

    NxCode is an AI app builder whose Studio pairs two agents: Conductor, an AI product manager that turns a plain English description into tasks with acceptance criteria, and Virtuoso, an AI engineer that writes, installs, builds and tests the code in an isolated Docker container, fixing failures before deploying to Cloudflare's edge. Plans start at $5 a month with credits, and a marketplace lets creators sell their apps for a 70% revenue share.

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

91. 91

    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.

92. 92

    BootLoop6.0 / 14

    A firmware agent paired with a hardware in the loop test platform: BootLoop writes firmware from board design files, flashes and tests it on real hardware, and turns each check into a CI test.

    Full coverage on Testing, Debugging & Optimization and Deployment & Data Residency. No documented coverage on Browser / Computer-use and Model Flexibility & Routing and 2 more.

93. 93

    ChipAgents6.0 / 14

    Agentic AI environment for chip design and verification, reached through a web workspace, that reads specifications to generate synthesizable RTL, testbenches and assertions and traces verification failures back through the RTL hierarchy, in the cloud, single tenant or on premises.

94. 94

    Hostinger AI Builder6.0 / 14

    Hostinger's AI app and website builder, formerly Horizons, with Manual and Agentic modes that turn plain language, images or voice into a deployed web app or store, with hosting, domain, SSL and an integrated backend bundled into one plan.

95. 95

    OnSpace6.0 / 14

    OnSpace is a no code AI builder whose agent turns a description, screenshot or Figma file into an iOS, Android or web app in React Native, sets up a managed backend with database, sign in, edge functions and secrets, wires in Stripe and in app purchases, and submits builds to the App Store. Apps can be built from a phone, and a built in AI service gives them text, image and video models.

    No documented coverage on Browser / Computer-use and APIs / SDKs / MCP Extensibility.

96. 96

    iGent5.0 / 14

    Autonomous software engineering agent (Maestro) that works from a prompt, upload or cloned repository, running an ensemble of frontier models in cloud sandboxes to plan, write, execute, test and optimize code across codebases of thousands of files. Access is through a waitlist with incremental rollout.

    No documented coverage on Browser / Computer-use and Triggers & Channel Coverage and 2 more.

97. 97

    Proofs3.5 / 14

    Agentic platform for sales engineering teams. From a short project prompt, AI agents research the prospect, read the customer's APIs and build a tailored proof of concept, delivering a preview URL and a Docker image and committing a tested, documented codebase to the customer's repository. Early stage.

    No documented coverage on Browser / Computer-use and APIs / SDKs / MCP Extensibility and 5 more.