Agentic Index
AI agent platforms that can be self hosted or run in a private VPC (2026)
Data last verified
Of the 556 agentic AI platforms in the Agentic Index, 281 document deployment inside the customer's own boundary in full, covering self hosted, on premises, air gapped and private VPC options. Only 171 also document bringing your own model or routing between providers. That is 30.8% of the field. This is a bar, not a leaderboard: a platform either documents both in its own public materials or it does not clear, and Partial evidence on either does not count.
The reason the bar has two parts rather than one is the finding underneath the list. Self hosting the software is not the same as containing the data. 110 of the 281 platforms you can run inside your own boundary do not document bring your own model. On those the runtime sits in your VPC and the model call still leaves it, so the prompt, the context and whatever the agent retrieved go to a third party anyway. A buyer who asks only the deployment question gets the wrong half of the answer about two times in five.
Which makes the scarcity ordering the second thing worth carrying out of this page. Of the four capabilities that bear on containment, model flexibility is the scarcest, not deployment. Across the same 556 platforms, full coverage runs observability 326, security and identity 335, deployment and residency 281, and model flexibility and routing 213. It is also the binding constraint on this bar: 110 of the 152 platforms one capability short fail on model flexibility alone. Separately, 42 platforms will take your model but will not run in your environment, which is the right answer for a team whose constraint is which model sees the data rather than where the software runs. Every platform that documents bringing your own model or routing between providers is named on its own page, counted from the model side rather than this one.
The bar, and how the 556 platforms score against it
| Capability | What has to be documented | Full | Only blocker |
|---|---|---|---|
| Deployment and data residency | the platform documents running inside the customer's own boundary, self hosted, on premises, air gapped or in a private VPC, or documents where the data physically sits when it cannot | 281 (51%) | 42 |
| Model flexibility and routing | the platform documents bringing your own model or key, or routing between providers, including local or self hosted models, rather than only calling one vendor hosted model | 213 (38%) | 110 |
Full means the vendor publishes evidence meeting the capability in its own public materials, under the Agentic Index verification standard. Only blocker counts platforms that document the other capability in full and fail on this one alone. One honest limit on the first row: deployment and data residency grades a spectrum, from customer controlled self hosting down to documented regional residency inside the vendor's own cloud. Read each platform's note for which end of that spectrum it clears on.
Clears the bar and scores 12.5 or higher of 14 overall
These 39 platforms document deployment inside your boundary and model flexibility in full, and also sit at the top of the Agentic Index coverage score across all 14 capabilities. Ordered by total coverage, ties broken alphabetically.
-
1.FLOWX.AI
14.0 / 14 capabilities
enterprise operations agents, multi-agent platforms, agent builders
Enterprise agentic platform whose documentation carries a named path for installing and configuring FlowX in the customer's own infrastructure, with every backend service containerized. Model providers are customer configured with the customer's own keys, so both halves of this bar sit in the docs rather than a sales deck.
-
2.Mastra
14.0 / 14 capabilities
agent infrastructure platforms
The Apache 2.0 framework builds and hosts agents anywhere, the licensed self hosted Enterprise edition keeps traces, prompts and outputs inside the customer's VPC, and Enterprise can run the Mastra Platform on premises or in the customer's own cloud. Each agent's model is a provider and model string in the model router, with the customer's own keys accepted.
-
3.Microsoft
14.0 / 14 capabilities
enterprise operations agents, agent builders
Copilot Studio contains data by geography rather than by self hosting: data residency follows the environment's geography, with pages for data locations and for moving data across regions when generative features require it. The maker chooses each agent's primary model, an external model included, from published availability tables.
-
4.Appian
13.5 / 14 capabilities
enterprise operations agents, agent builders
Appian runs as managed SaaS across regions, in Appian Government Cloud inside an AWS GovCloud VPC with AI at feature parity, or self managed on Kubernetes. Each agent uses the model set in its model selection, defaulting to the latest from the configured provider.
-
5.Gumloop
13.5 / 14 capabilities
agent builders
Visual no code canvas for AI pipelines and agents that documents both halves of containment: deployment into the customer's own cloud as a VPC in the region of their choice with data remaining on infrastructure the customer controls, and model choice per agent across every major provider through Agent Preferences, with new models typically available within a day of public release.
-
6.Pega
13.5 / 14 capabilities
enterprise operations agents, agent builders
Infinity 26 runs on Pega Cloud or in the client's own managed cloud, with Pega Cloud for Government on AWS GovCloud and an EU service boundary controlling where European data lives. The GenAI layer is provider agnostic across Azure OpenAI, AWS Bedrock and Google Vertex, a choice left to the customer's architects.
-
7.ServiceNow
13.5 / 14 capabilities
enterprise operations agents, multi-agent platforms
ServiceNow's containment answer is a named environment rather than self hosting: the Government Community Cloud under FedRAMP beside its standard cloud. An administrator picks the model provider for AI agents from Now LLM Service, AWS Claude, Azure OpenAI and Google Gemini.
-
8.StackAI
13.5 / 14 capabilities
enterprise operations agents, agent builders
No code enterprise agent platform with a dedicated On-Premise page, an enterprise CLI documented for deploying and managing StackAI on customer infrastructure, and an LLM hosting tree covering models in the customer's own Azure or AWS Bedrock account plus Local LLM for models on the customer's own hardware, governed through an LLM provider governance layer.
-
9.UiPath
13.5 / 14 capabilities
enterprise operations agents, multi-agent platforms, agent builders
Agentic automation orchestrating agents, robots and people end to end. Deployable cloud, on premises or hybrid, with Automation Suite to run the full platform yourself, and Autopilot runs on the customer's cloud of choice or their own infrastructure while supporting GPT, Gemini, Claude and any compatible model.
-
10.Agno
13.0 / 14 capabilities
agent infrastructure platforms
High performance agent runtime, formerly Phidata, Apache 2.0 licensed, which is the strongest possible containment position because the runtime is yours. Same evidence caveat as CrewAI: both rows cite the expansion evidence report rather than named documentation pages, a thinner basis than the enterprise platforms carry.
-
11.AutoGPT
13.0 / 14 capabilities
multi-agent platforms, agent builders, agent infrastructure platforms
Self hosting is a right rather than a tier: the platform is open source and runs free via Docker Compose, with the customer's own model keys keeping data and inference on its own infrastructure, and Llama available for local model execution. The hosted cloud is the paid option.
-
12.Base44
13.0 / 14 capabilities
agent builders (secondary lane membership, primary category Coding agent)
Base44 does not self host. Enterprise workspaces choose US, EU or UK storage for app data on the vendor's monitored private infrastructure, which answers residency but not control of the machine.
-
13.CrewAI
13.0 / 14 capabilities
multi-agent platforms
Open source multi agent orchestration for collaborative crews: the MIT framework runs anywhere the customer runs Python, the enterprise platform deploys on CrewAI's cloud, a dedicated VPC or the customer's own infrastructure through CrewAI Factory, and each agent can take its own model from many providers.
-
14.Databricks Agent Bricks
13.0 / 14 capabilities
multi-agent platforms
Runs on AWS, Azure and Google Cloud with a published supported regions list and can be configured against the customer's own cloud account, while administrators connect external model providers on their own keys, alongside hosted open and frontier models, as Unity Catalog securables granted per user.
-
15.Dataiku
13.0 / 14 capabilities
multi-agent platforms, agent builders
Runs as managed Dataiku Cloud or installed on the customer's own infrastructure, with hybrid options through sales, and the LLM Mesh connects most major model providers plus locally running Hugging Face models that keep inference in house.
-
16.HappyRobot
13.0 / 14 capabilities
enterprise operations agents
AI workers for operations teams that document containment on both axes: the platform runs in HappyRobot's managed cloud, multi tenant by default, or in the customer's own single tenant on AWS, GCP or Azure, with regional deployments for in country residency, and workflows can run on OpenAI, Google Gemini, Anthropic Claude or models the customer hosts.
-
17.n8n
13.0 / 14 capabilities
agent builders
Open source workflow automation whose install documentation runs from one line setup, Docker and npm through Kubernetes and every major cloud, alongside managed n8n Cloud. Models attach to the AI Agent node as sub nodes, so different agents in one workflow can run different chat models, and a fully isolated configuration is documented for closed environments.
-
18.Relevance AI
13.0 / 14 capabilities
multi-agent platforms, agent builders
Hosted rather than self hosted, but an organization picks its region at signup from the US, EU or Australia, and each agent picks its model from several providers with a backup model from a different one; bring your own model keys is available on every plan.
-
19.Replit Agent
13.0 / 14 capabilities
agent builders (secondary lane membership, primary category Coding agent)
Full stack app builder and runtime whose Full here is about what you build, not where Replit runs: deployment coverage is the documented autoscale, scheduled, static and always on publishing types for customer apps, with intelligent model routing plus a manual model selector on the agent itself. Read it as containment for the apps it ships rather than a self hosted platform.
-
20.Salesforce
13.0 / 14 capabilities
enterprise operations agents
CRM platform whose Agentforce layer runs agents across sales, service and marketing, with the Atlas Reasoning Engine supporting OpenAI, Anthropic and Google Gemini. It clears this bar on data residency and the trust layer, not on self hosting, and its own filed evidence says so. Read this note before treating it as an answer to this question.
-
21.Sema4.ai
13.0 / 14 capabilities
agent builders
Enterprise agent platform from the Robocorp team whose agents run in the customer's own AWS, Azure, Google Cloud or Snowflake account, with the Enterprise Edition running entirely inside the customer's VPC, under a stated bring your own model approach naming OpenAI, Azure, Bedrock and Snowflake Cortex.
-
22.Sim
13.0 / 14 capabilities
multi-agent platforms, agent builders
Open source Apache 2.0 agent workspace. The sharpest single instance on this page: documented Docker Compose and Kubernetes self hosting including a fully offline setup with local models through Ollama, bring your own key at base provider pricing with no markup, and enterprise permission groups that restrict which providers are allowed.
-
23.Tray.ai
13.0 / 14 capabilities
agent infrastructure platforms
A Tray instance runs in a region the customer picks, US, EU or APAC, and an on premise agent with AWS PrivateLink reaches systems behind the firewall. Agents run on Tray's native model or on the customer's own OpenAI or AWS Bedrock keys, chosen per agent.
-
24.Tungsten Automation
13.0 / 14 capabilities
enterprise operations agents, agent builders
TotalAgility runs on the customer's own premises as well as in TotalAgility Cloud, and its Bring Your Own Model capability lets customers combine providers such as Azure OpenAI with their own custom LLMs.
-
25.Warp
13.0 / 14 capabilities
multi-agent platforms (secondary lane membership, primary category Coding agent)
Containment on both axes. Enterprise documents self hosted cloud agents on the customer's own infrastructure with inference routed through the customer's own cloud, Factories runs in Warp's cloud or fully self hosted inside the customer's VPC, and a model picker spans Claude, GPT, Gemini, GLM and Kimi models, with different models on different tasks.
-
26.Writer
13.0 / 14 capabilities
enterprise operations agents, agent infrastructure platforms
Enterprise platform on its own Palmyra model family whose enterprise deployment documentation names self hosting and full data residency as available options, meeting the deployment bar three ways where one would do. The model half clears on the vendor's own FAQ answering who chooses the model.
-
27.Akka
12.5 / 14 capabilities
multi-agent platforms, agent builders, agent infrastructure platforms
Runs self managed on the customer's own VMs, containers or Kubernetes, in the customer's VPC through Akka Automated Operations, or in Akka's serverless cloud, and each agent can take its own model from nine built in providers or a custom one, including local models through Ollama.
-
28.Boomi
12.5 / 14 capabilities
enterprise operations agents, multi-agent platforms, agent builders
Integration platform with an agent control tower over enterprise systems. Runs on a flexible multi cloud autonomous runtime with on premise and multi region deployment options for residency, and is model agnostic with MCP support across Amazon Bedrock, Snowflake Cortex and OpenAI, with roadmap support for custom large and small models.
-
29.Creatio
12.5 / 14 capabilities
enterprise operations agents, agent builders (secondary lane membership, primary category GTM / revenue agent)
Creatio runs as shared software as a service, as a dedicated cloud on the Unlimited tier, or installed on site on the customer's own infrastructure. Its separately deployed LLM instance is hosted in the same region as the customer's Creatio site. The Prompt Agent Designer lets the builder choose among providers such as Anthropic Claude, OpenAI and Google Gemini for each agent.
-
30.Fabrix.ai
12.5 / 14 capabilities
enterprise operations agents, agent builders (secondary lane membership, primary category SRE / DevOps agent)
Deployable on premises or in the customer's private cloud with the model layer included, so open source models such as Llama and Mistral can run inside the customer's infrastructure, beside OpenAI and Anthropic as cloud choices the customer selects.
-
31.Harvey
12.5 / 14 capabilities
enterprise operations agents
Enterprise legal platform, the one vertical product in this tier. It clears deployment on documented regional hosting rather than self hosting, with the customer keeping everything in region across EU or Switzerland, US, or Australia and separate regional application hosts, and clears model flexibility on admin controlled rollout of Anthropic and Google models beside OpenAI with an opt in model selector.
-
32.IBM watsonx Orchestrate
12.5 / 14 capabilities
enterprise operations agents
Runs as a managed service on IBM Cloud or AWS or in the customer's own on premises environment, with documented air gapped installation. Models from several providers are imported and assigned per agent, coordinated by policies for load balancing and fallback.
-
33.Kestra
12.5 / 14 capabilities
multi-agent platforms, agent infrastructure platforms
Apache 2.0 open source that self hosts on the customer's infrastructure, cloud or Kubernetes, with the Enterprise Edition on cloud, on premises or air gapped. The model is chosen on each AI task through its provider property, from Anthropic and OpenAI to Bedrock, Gemini, Mistral and local Ollama.
-
34.Latenode
12.5 / 14 capabilities
agent builders, agent infrastructure platforms
Low code agent and automation platform documenting self hosting for teams prioritizing data security, with full control over infrastructure and data across on premise and cloud environments, and one subscription covering GPT, Claude, Gemini, Deepseek, LLaMA and a long tail of further models without separate provider accounts.
-
35.Mendix
12.5 / 14 capabilities
enterprise operations agents, agent builders
Customers choose among Mendix Cloud, Mendix Cloud Dedicated for a single tenant, Mendix on Azure, Kubernetes, StackIT or Server, SAP BTP, and the Private Mendix Platform with an air gapped installation, and agents deploy as part of the app model. The customer picks the model for each agent version from connectors covering Mendix Cloud GenAI, OpenAI, Amazon Bedrock, Google Gemini, Mistral and Snowflake Cortex, and teams can build their own connector.
-
36.OutSystems
12.5 / 14 capabilities
multi-agent platforms, agent builders
Enterprise low code incumbent whose ODC self hosted deployment, published March 2026, runs apps, data and agents in the customer's private cloud, public cloud or on premises Kubernetes while OutSystems manages platform services, and whose Agent Workbench connects a model once for reuse across agents, from Bedrock, Azure OpenAI and Anthropic through custom models on Vertex AI.
-
37.SimplAI
12.5 / 14 capabilities
multi-agent platforms, agent builders, agent infrastructure platforms
Datafuse Technology Inc builds SimplAI, an enterprise agentic AI operating system spanning SimplAI cloud, customer cloud, private cloud, VPC, on premises and air gapped with no architectural change between them, plus customer defined retention and deletion per agent. One caveat a buyer should carry: bring your own models and fine tuning are documented but gated to the enterprise tier.
-
38.Torq
12.5 / 14 capabilities
enterprise operations agents (secondary lane membership, primary category Security / SOC agent)
Security hyperautomation platform whose self hosted step runners run workflow steps inside the customer's own environment, including on EKS and AKS, while workspaces sit in the United States, the European Union or Japan. Customers bring their own model subscription across OpenAI, Azure OpenAI, Vertex AI, Anthropic and Bedrock and pick the model per agent and per task. Qualifies here on secondary lane membership as an enterprise operations platform, which a buyer scanning this list should know.
-
39.Wonderful
12.5 / 14 capabilities
enterprise operations agents, agent builders (secondary lane membership, primary category Customer support agent)
Four deployment models are offered: multi tenant SaaS, dedicated single tenant infrastructure, bring your own cloud on AWS, Azure or Google Cloud with data kept inside the customer's organization, and a fully air gapped on premises install. Each task is routed to the model that fits, and the AI Gateway sets which teams can reach which models and caps budgets.
The remaining 132 platforms that clear the bar
Every one of these documents deployment inside the customer's boundary and model flexibility in full. They score below 12.5 of 14 on total coverage, which says something about breadth across the whole taxonomy rather than about how well contained they are. Several of the strongest containment stories in the index are narrow open source runtimes that score low precisely because they do one thing.
| Platform | Lanes | Coverage |
|---|---|---|
| AgentX | multi-agent platforms, agent builders | 12.0 / 14 |
| Airia | agent builders | 12.0 / 14 |
| Atomicwork | enterprise operations agents | 12.0 / 14 |
| Augment Code | multi-agent platforms (secondary, primary Coding agent) | 12.0 / 14 |
| Beam AI | enterprise operations agents | 12.0 / 14 |
| CrowdStrike | multi-agent platforms, agent builders (secondary, primary Security / SOC agent) | 12.0 / 14 |
| Dify | agent builders | 12.0 / 14 |
| Glean | enterprise operations agents | 12.0 / 14 |
| Haystack | agent infrastructure platforms | 12.0 / 14 |
| Langflow | agent builders | 12.0 / 14 |
| LlamaIndex | agent infrastructure platforms | 12.0 / 14 |
| Lyzr | agent builders | 12.0 / 14 |
| MindStudio | agent builders | 12.0 / 14 |
| Moveo.AI | agent builders | 12.0 / 14 |
| Oracle | enterprise operations agents | 12.0 / 14 |
| Pydantic AI | agent infrastructure platforms | 12.0 / 14 |
| Retool | enterprise operations agents, multi-agent platforms, agent builders | 12.0 / 14 |
| SAP | enterprise operations agents | 12.0 / 14 |
| SmythOS | multi-agent platforms, agent builders, agent infrastructure platforms | 12.0 / 14 |
| SnapLogic | agent builders, agent infrastructure platforms | 12.0 / 14 |
| SS&C Blue Prism | enterprise operations agents, agent builders | 12.0 / 14 |
| SuperAGI | multi-agent platforms, agent builders, agent infrastructure platforms | 12.0 / 14 |
| Windmill | agent builders, agent infrastructure platforms | 12.0 / 14 |
| Workato | enterprise operations agents | 12.0 / 14 |
| xpander.ai | agent infrastructure platforms | 12.0 / 14 |
| Activepieces | agent builders | 11.5 / 14 |
| Budibase | enterprise operations agents, agent builders | 11.5 / 14 |
| Coworker | enterprise operations agents, agent builders | 11.5 / 14 |
| Datafold | agent infrastructure platforms (secondary, primary Data analyst agent) | 11.5 / 14 |
| Gnani.ai | agent infrastructure platforms (secondary, primary Voice agent) | 11.5 / 14 |
| Itential | agent infrastructure platforms (secondary, primary SRE / DevOps agent) | 11.5 / 14 |
| LangChain | multi-agent platforms, agent infrastructure platforms | 11.5 / 14 |
| LangSmith | agent infrastructure platforms | 11.5 / 14 |
| Legion Intelligence | multi-agent platforms, agent builders | 11.5 / 14 |
| Rasa | multi-agent platforms | 11.5 / 14 |
| Tines | enterprise operations agents, agent builders (secondary, primary Security / SOC agent) | 11.5 / 14 |
| Anchor Browser | agent infrastructure platforms | 11.0 / 14 |
| Artian | enterprise operations agents, multi-agent platforms | 11.0 / 14 |
| Cohere North | agent builders | 11.0 / 14 |
| ContraForce | enterprise operations agents (secondary, primary Security / SOC agent) | 11.0 / 14 |
| Ema | enterprise operations agents | 11.0 / 14 |
| Joget | enterprise operations agents, agent builders | 11.0 / 14 |
| LexisNexis | enterprise operations agents | 11.0 / 14 |
| Parashift | enterprise operations agents | 11.0 / 14 |
| Smallest AI | agent infrastructure platforms (secondary, primary Voice agent) | 11.0 / 14 |
| Sourcegraph | agent infrastructure platforms | 11.0 / 14 |
| Synera | enterprise operations agents, agent builders | 11.0 / 14 |
| Tembo | agent infrastructure platforms (secondary, primary Coding agent) | 11.0 / 14 |
| Thread AI | agent builders, agent infrastructure platforms | 11.0 / 14 |
| Trigger.dev | agent infrastructure platforms | 11.0 / 14 |
| Vellum | agent builders, agent infrastructure platforms | 11.0 / 14 |
| Vibrium AI | enterprise operations agents | 11.0 / 14 |
| Viktor | enterprise operations agents | 11.0 / 14 |
| Altilia | multi-agent platforms, agent builders | 10.5 / 14 |
| Bernstein | agent infrastructure platforms | 10.5 / 14 |
| Box | enterprise operations agents, agent builders | 10.5 / 14 |
| Cartesia | agent infrastructure platforms | 10.5 / 14 |
| Forest | enterprise operations agents, agent infrastructure platforms | 10.5 / 14 |
| Netlify | agent infrastructure platforms | 10.5 / 14 |
| OpenRouter | agent infrastructure platforms | 10.5 / 14 |
| Palo Alto Networks | enterprise operations agents (secondary, primary Security / SOC agent) | 10.5 / 14 |
| Pipecat | agent infrastructure platforms | 10.5 / 14 |
| Swimlane | agent builders (secondary, primary Security / SOC agent) | 10.5 / 14 |
| ToolJet | agent builders | 10.5 / 14 |
| Agent Zero | multi-agent platforms, agent builders | 10.0 / 14 |
| Braintrust | agent infrastructure platforms | 10.0 / 14 |
| Browserbase | agent infrastructure platforms (secondary, primary Browser / computer-use agent) | 10.0 / 14 |
| Dust | enterprise operations agents | 10.0 / 14 |
| Inngest | agent infrastructure platforms | 10.0 / 14 |
| LangWatch | agent infrastructure platforms | 10.0 / 14 |
| Letta | agent infrastructure platforms | 10.0 / 14 |
| Nexus Intelligence | enterprise operations agents | 10.0 / 14 |
| Paragon | agent infrastructure platforms | 10.0 / 14 |
| AlphaBitCore | agent infrastructure platforms | 9.5 / 14 |
| Avesha | agent infrastructure platforms (secondary, primary SRE / DevOps agent) | 9.5 / 14 |
| Jet Admin | agent builders | 9.5 / 14 |
| LiteLLM | agent infrastructure platforms | 9.5 / 14 |
| TrueFoundry | agent infrastructure platforms | 9.5 / 14 |
| Uniphore | enterprise operations agents, multi-agent platforms | 9.5 / 14 |
| Arize AI | agent infrastructure platforms | 9.0 / 14 |
| F5 AI Guardrails | agent infrastructure platforms | 9.0 / 14 |
| Galileo | agent infrastructure platforms | 9.0 / 14 |
| Imbue | agent builders | 9.0 / 14 |
| Kinaxis | enterprise operations agents | 9.0 / 14 |
| Maisa | agent builders | 9.0 / 14 |
| MakinaRocks | enterprise operations agents, agent infrastructure platforms | 9.0 / 14 |
| Opik | agent infrastructure platforms | 9.0 / 14 |
| W&B Weave | agent infrastructure platforms | 9.0 / 14 |
| Composio | agent infrastructure platforms | 8.5 / 14 |
| Confident AI | agent infrastructure platforms | 8.5 / 14 |
| E2B | agent infrastructure platforms | 8.5 / 14 |
| Fiddler AI | agent infrastructure platforms | 8.5 / 14 |
| Firecrawl | agent infrastructure platforms | 8.5 / 14 |
| HoneyHive | agent infrastructure platforms | 8.5 / 14 |
| Inworld AI | agent infrastructure platforms | 8.5 / 14 |
| Kong | agent infrastructure platforms | 8.5 / 14 |
| Langfuse | agent infrastructure platforms | 8.5 / 14 |
| Maxim AI | agent infrastructure platforms | 8.5 / 14 |
| Daytona | agent infrastructure platforms | 8.0 / 14 |
| Freeplay | agent infrastructure platforms | 8.0 / 14 |
| Gentoro | agent infrastructure platforms | 8.0 / 14 |
| Helicone | agent infrastructure platforms | 8.0 / 14 |
| Hyperbrowser | agent infrastructure platforms | 8.0 / 14 |
| Metorial | agent infrastructure platforms | 8.0 / 14 |
| Modal | agent infrastructure platforms | 8.0 / 14 |
| Stacklok | agent infrastructure platforms | 8.0 / 14 |
| Temporal Cortex | agent infrastructure platforms | 8.0 / 14 |
| Traceloop | agent infrastructure platforms | 8.0 / 14 |
| Trent AI | agent infrastructure platforms (secondary, primary Security / SOC agent) | 8.0 / 14 |
| WISEnut | enterprise operations agents (secondary, primary Customer support agent) | 8.0 / 14 |
| Arcade | agent infrastructure platforms | 7.5 / 14 |
| Beam | agent infrastructure platforms | 7.5 / 14 |
| Deepgram | agent infrastructure platforms | 7.5 / 14 |
| Khoj | agent builders | 7.5 / 14 |
| Portkey | agent infrastructure platforms | 7.5 / 14 |
| Smithery | agent infrastructure platforms | 7.5 / 14 |
| Cognee | agent infrastructure platforms | 7.0 / 14 |
| GPT Researcher | agent infrastructure platforms | 7.0 / 14 |
| Guardrails AI | agent infrastructure platforms | 7.0 / 14 |
| Hyperspell | agent infrastructure platforms | 7.0 / 14 |
| Klavis AI | agent infrastructure platforms | 7.0 / 14 |
| Lemony | agent builders, agent infrastructure platforms | 7.0 / 14 |
| Mastery AI | enterprise operations agents, multi-agent platforms | 7.0 / 14 |
| Stagehand | agent infrastructure platforms (secondary, primary Browser / computer-use agent) | 7.0 / 14 |
| Zep | agent infrastructure platforms | 7.0 / 14 |
| Clawvisor | agent infrastructure platforms | 6.5 / 14 |
| LabWired | agent infrastructure platforms | 6.5 / 14 |
| Prime Intellect | agent infrastructure platforms | 6.5 / 14 |
| Lightpanda | agent infrastructure platforms | 6.0 / 14 |
| Mem0 | agent infrastructure platforms | 6.0 / 14 |
| Vocode | agent infrastructure platforms | 6.0 / 14 |
| Jina AI | agent infrastructure platforms | 5.0 / 14 |
Common questions
Which AI agent platforms can be self hosted or run in a private VPC?
281 of 556 agentic AI platforms in the Agentic Index document deployment inside the customer's own boundary in full, covering self hosted, on premises, air gapped and private VPC options. Only 171 of those also document bring your own model or routing between providers in full, which is the bar used on this page, because a runtime inside your boundary that can only call one vendor hosted model has not contained your data. That is 30.8% of the field. Graded from public evidence only.
Is self hosting an AI agent platform the same as keeping your data private?
No, and this is the gap the page exists to show. 110 of the 281 platforms documenting deployment in your own boundary do not document bring your own model. On those platforms the software runs inside your perimeter and the model call still leaves it, so the prompt, the context and whatever the agent retrieved go to a third party anyway. Self hosting the runtime and containing the data are two different purchases.
Which is harder to find, self hosting or model flexibility?
Model flexibility. Across the same 556 platforms, full coverage runs observability 326, security and identity 335, deployment and residency 281, and model flexibility and routing 213. It is the scarcest of the four, and it is the binding constraint here: 110 of the 152 platforms one capability short of the bar fail on model flexibility alone.
Can you point an AI agent platform at your own model without self hosting it?
On 42 platforms, yes. They document bringing your own model or routing between providers while running in the vendor's cloud rather than yours. That is a real option for teams whose constraint is which model sees the data rather than where the software runs, and it is a different shape of answer from the 171 platforms that document both.
Does every platform on this list actually let you self host?
Not necessarily. The deployment and data residency capability grades a spectrum, from customer controlled self hosting down to documented regional residency inside the vendor's own cloud. Where a cleared platform's filed evidence states in terms that customer self hosting is not the model, a disclosure sits beside its entry so nobody reads it as self hostable. No platform on the current list carries that disclosure. The rule is mechanical and applied to every vendor equally.
Is this ranking paid or sponsored?
No. No vendor pays for placement, no vendor has reviewed this page, and every grade comes from the vendor's own public materials under the Agentic Index verification standard. 1,165 vendors are graded against the same 14 capabilities. Data last verified November 9, 2026.
Method: membership is the same 556 platform pool used by the best agentic AI platforms in 2026, drawn from 1,165 researched vendors. The editorial pages over this pool are one method with different bars, not several opinions. Every grade comes from the vendor's own public materials under the Agentic Index verification standard. No vendor pays for placement and no vendor has reviewed this page. Data last verified November 9, 2026. How this evidence is graded
Related: enterprise security and compliance platforms, platforms that require human approval, agent observability platforms, how every vendor scores on deployment and data residency, platforms that let you bring your own model or route between providers, how every vendor scores on model flexibility, agent infrastructure platforms ranked on the production contract, compare platforms side by side.