Curated collection
AI Agent Tools You Can Self-Host
38 of the 126 tools in our index can run somewhere you control. This is a deployment question, not a license one: the list mixes MIT- and Apache-2.0-licensed frameworks with no managed cloud at all, open cores paired with optional paid hosted layers, fair-code and source-available builds, and a handful of closed-source products that still ship a real private-deployment path.
On this page
Every listing in our index carries a `deployment` field, set to Cloud, Self-host or Both, researched and sourced the same way as pricing or license. 38 of the 126 current tools set it to Self-host or Both, meaning code and data can stay inside infrastructure you control instead of a vendor's cloud, at some price. See our full [deployment census](/blog/ai-agent-deployment-census-2026/) for the category-by-category breakdown this collection is drawn from.
At a glance
- agents
- 38
- curated for this set
- Free to start
- 34 of 38
- a free or freemium entry tier
- Public API
- 30 of 38
- 6 more only on a paid tier
- Publish a price
- 38 of 38
- an anchor price on their own page
What this collection covers
This list is deliberately not the same set as our [open-source collection](/collections/open-source-ai-agent-tools/), even though the two overlap heavily. 25 of the 26 tools on that list are also here, because a clean open-source license almost always means you can run the code yourself. The single exception is Cartesia, whose Line SDK is Apache-2.0 but whose voice-agent runtime only ever executes on Cartesia's own infrastructure. But 13 more tools clear this list's bar without clearing that one: Mastra and OpenHands are open at the core but gate a separate hosted or enterprise layer (Mastra Cloud, OpenHands Cloud) behind its own paid tier; Warp open-sourced only its terminal client (dual AGPL-3.0/MIT since April 2026), while Warp Factories, the cloud-agent platform that actually runs and coordinates its agents, stays closed-source; n8n and Dify hedge their openness with a license condition their own docs tell you to check (fair-code, an Apache-2.0-derived license); and Claude Agent SDK, Factory, CodeRabbit, Bland AI, Deepgram Voice Agent API, Windsurf, Junie and Augment Code are closed-source products that still sell (or in Windsurf's case, ship free) a genuine private-deployment or local-execution path. If a compliance team's real question is "can this run inside our own network," the license badge alone answers it wrong for 13 of this list's 38 tools.
The category split is uneven in a way worth knowing before you shop by category page alone: agent frameworks are unanimous (15 of 16 offer some self-host path, since a framework you cannot run yourself is arguably not a framework), coding agents are the most genuinely mixed category (17 of 27): Junie's CLI and IDE plugin can point at a local model, but the JetBrains-run orchestration and credit metering behind it stay cloud-side, the same distinction our deployment census draws for Cartesia's speech models. Augment Code is the more straightforward case among this list's coding agents, with loops that can run in Augment's managed cloud or dispatch directly into a team's own AWS or GCP account. Support agents plus sales/marketing agents offer zero: every one of those 17 tools is cloud-only at any price, so a hard data-residency requirement in either category currently has no architectural answer on this site, only a contractual one (a vendor DPA or regional hosting commitment).
How these 38 agents were picked
A tool earns a place here if its own Published, sourced listing sets its `deployment` field to Self-host or Both, verified against the vendor's own docs or pricing page describing an actual self-run, on-premise, air-gapped, or local-execution option, not a roadmap promise or a generic "enterprise-ready" claim. This is a deployment-location question, independent of license: an entry may be open-source with no managed layer at all, open-source with an optional paid cloud add-on, source-available under a fair-code or added-conditions license, or fully closed-source with a paid tier that still lets you keep data inside your own infrastructure. For the license-only question, see the [open-source collection](/collections/open-source-ai-agent-tools/); for the full category-by-category count, see the [deployment census](/blog/ai-agent-deployment-census-2026/) this collection is built from.
The 38 agents on this shelf

LangChain
Open source agent frameworks plus LangSmith, the platform for tracing, evaluating and deploying agents.
Agent frameworksFree, then $39/seat/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering teams building a bespoke, production-grade agent who want the largest integration ecosystem plus real stateful control.
No managed LangChain cloud product exists: MIT-licensed and self-hosted is the only way to run it, alongside the largest integration ecosystem of any framework here.

CrewAI
Open-source multi-agent framework with a managed platform for deploying and governing agent workflows.
Agent frameworksFreeAPIAutonomousClaudeVerified 3 days agoBest for Developers who want to stand up a role-based, collaborating multi-agent system quickly in Python, with a stable MIT-licensed core and a hosted build and runtime for production.
MIT-licensed with no managed CrewAI cloud offering: the orchestration layer runs entirely on your own infrastructure and model keys.

AutoGen
Microsoft's open-source Python framework for building single- and multi-agent applications; now in maintenance mode.
Agent frameworksFreeAPIAutonomousClaudeVerified 14 days agoBest for Python or .NET developers and researchers exploring multi-agent orchestration who want a mature, free, self-hosted framework.
MIT-licensed research framework with no managed layer: Microsoft's own successor, Agent Framework, is the one in this category that also offers a hosted option.

OpenAI Agents SDK (Python)
Open-source Python framework for building agents with tools, handoffs, guardrails, sandboxes and tracing.
Agent frameworksFreeAPIAutonomousFree tierVerified 14 days agoBest for Developers who want the fastest, lightest way to ship a straightforward agent (support triage, a tool-using assistant or a sandboxed coding agent) with tracing and guardrails included.
MIT-licensed and self-host only: OpenAI does not offer a managed runtime for it, unlike Google ADK's Agent Runtime or Microsoft Agent Framework's Foundry layer.

Pydantic AI
Typed Python agent framework: any model, any surface, with a harness for long-running coding and research agents.
Agent frameworksFreeAPIAutonomousClaudeVerified 14 days agoBest for Python teams building type-safe agents who also want realtime voice, image generation and embeddings in one SDK, with optional durable execution via Temporal, DBOS, Prefect or Restate.
MIT-licensed, Python-native, with no managed hosting layer from the Pydantic team: runs entirely inside a service you own.

Cline
Open-source coding agent for VS Code, JetBrains, the terminal and CI, running on whichever model you bring.
Coding agentsFree, then $9.99/monthAPIAutonomousClaudeVerified 5 days agoBest for Developers and teams who want a transparent, open-source, model-agnostic agent they fully control and pay for by usage, with optional flat-rate access to open-weight models.
Apache-2.0 licensed with no cloud product to opt into: everything runs inside your own VS Code, JetBrains or terminal session.

Aider
Open-source terminal AI pair programmer that edits and commits code in your local git repo.
Coding agentsFreeClaudeFree tierGPTVerified 7 days agoBest for Developers who want free, model-agnostic AI pair programming in their terminal
Apache-2.0, a local terminal process only: there is no Aider cloud tier at any price, so running it yourself is the only way it exists.

Juggler
Visual workbench for AI coding agents: branching conversation trees, inspectable model transactions, local or remote.
Coding agentsFreeAutonomousClaudeFree tierVerified todayBest for Developers who want hands-on visibility into what an AI coding agent is doing to their codebase and accept early-stage, self-hosted, open-source software.
AGPLv3 core with an Apache-2.0 extension SDK and no managed cloud version: the strongest copyleft license in this collection.

OpenCode
Open source AI coding agent for the terminal, desktop, browser and IDE, running any model you connect.
Coding agentsFree, then $10/monthAPIAutonomousClaudeVerified 14 days agoBest for Developers who want a genuinely free, fully open-source coding agent that works with any model provider, including their own local Ollama models, without being locked into one vendor's terminal tool.
MIT-licensed terminal agent with 188,976+ GitHub stars and no managed cloud counterpart: bring your own model key or a local model.

zot
Single-binary terminal coding agent harness in Go: five built-in tools, most providers, extensions in any language.
Coding agentsFreeAPIAutonomousClaudeVerified 14 days agoBest for Developers who want a fast, free, Go-native coding-agent harness with real session-branching control and are comfortable running fast-moving, self-described "beta forever" software from an independent maintainer.
MIT-licensed, a single Go binary with no server component at all: the lightest self-hosting story in this collection.

GPT Researcher
Open-source autonomous research agent that writes cited long-form reports from web and local sources.
Research & data agentsFreeAPIAutonomousClaudeVerified todayBest for Developers and AI engineers who want a free, self-hosted research agent they can embed via Python, REST or MCP and run against their own LLM and search keys.
Apache-2.0 licensed: the only self-hostable pick in the research-agents category; every other listed research agent here is cloud-only.

Microsoft Agent Framework
Open-source SDK for AI agents and multi-agent workflows across .NET, Python and Go.
Agent frameworksFreeAPIAutonomousClaudeVerified 14 days agoBest for .NET or Python teams already invested in Azure or Microsoft Foundry who want one supported agent SDK, an optional managed hosting path, and a documented migration off AutoGen or Semantic Kernel.
MIT-licensed SDK for .NET and Python: self-host free, or use Microsoft's optional Foundry Hosted Agents managed layer on top.

LlamaIndex
Open-source agent framework plus a credit-metered document parsing, extraction and indexing platform.
Agent frameworksFree, then $50/monthAPIClaudeEnterpriseVerified 14 days agoBest for Engineers building RAG-heavy or document-heavy agents who want an MIT-licensed OSS core with an optional managed parsing and extraction platform on top.
MIT-licensed core self-hosts free; the paid LlamaCloud layer adds managed parsing on top, entirely optional.

LangGraph
Open-source orchestration framework and runtime for stateful, long-running LLM agents, from LangChain.
Agent frameworksFree, then $39/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering teams building production agents who need cyclical graphs, durable state and replayable runs
MIT-licensed graph orchestration engine that self-hosts free; a separate, optional LangSmith platform adds deployment, tracing and evaluation on a metered basis, the same shape as LangChain's own optional LangSmith layer. It also clears the clean-license open-source collection's bar.

Mastra
Open-source TypeScript framework for building AI agents, with a hosted platform for running and observing them.
Agent frameworksFree, then $250/monthAPIAutonomousClaudeVerified 14 days agoBest for Full-stack JavaScript and TypeScript teams, especially those already building in Next.js or Node, who want agents, durable workflows and memory unified in one framework without adopting a Python-first stack.
Apache-2.0 core self-hosts free; a separate, optional Mastra Cloud platform adds hosting, a visual Studio and observability on a metered basis: open at the core, but that managed layer is why it sits outside the clean-license open-source collection.

Letta
Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory.
Agent frameworksFree, then $20/monthAPIAutonomousClaudeVerified 14 days agoBest for Developers and researchers who specifically need an agent whose memory, skills and identity genuinely persist and evolve across long-running sessions, rather than reset on every call.
Apache-2.0 licensed with persistent memory: self-host free, or opt into managed Letta Cloud later without changing your integration code.

Google Agent Development Kit (ADK)
Open-source framework for building, evaluating and deploying AI agents in Python, TypeScript, Go, Java or Kotlin.
Agent frameworksFreeAPIAutonomousClaudeVerified yesterdayBest for Teams that want Google's own official, actively-developed agent SDK, especially polyglot teams (Python/Go/Java/TypeScript/Kotlin) or anyone building multi-agent systems that need to interoperate across vendors via the A2A protocol.
Apache-2.0 licensed across five language runtimes (Python, TypeScript, Go, Java, Kotlin): self-host anywhere, or use Google's own Agent Runtime managed layer on top.

Agno
Python SDK, open-source AgentOS runtime and hosted control plane for building and operating agents.
Agent frameworksFree, then $150/monthAPIAutonomousClaudeVerified 14 days agoBest for Python developers who want an Apache 2.0 SDK with memory, knowledge, learning, guardrails and a Control Plane they run inside their own cloud account, and who are comfortable running Docker or a cloud deploy template themselves.
Apache-2.0 licensed, and there is no Agno-hosted alternative at any price: even the paid AgentOS production tier deploys into your own AWS, GCP, Railway or airgapped account rather than Agno's cloud.

Claude Agent SDK
Python and TypeScript library that runs Claude Code's agent loop and tools inside your own application.
Agent frameworksFrom $1/million input tokensAPIAutonomousClaudeVerified 14 days agoBest for Developers already building on Claude (or Claude Code) who want its exact agent loop, tools and context management as a callable library, and are comfortable being single-vendor on Anthropic in exchange for the tightest possible integration with Claude Code's own capabilities.
The wrapper package is MIT-licensed and the subprocess it spawns runs locally under your own control, but Anthropic's Commercial Terms of Service govern the SDK as a whole and the Claude Code binary it bundles isn't published as source: self-hostable in practice, just not on the clean-license open-source collection.

Codex CLI
OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell.
Coding agentsFree, then $8/monthAPIAutonomousFree tierVerified 14 days agoBest for Developers who already pay for a ChatGPT plan and want a terminal-native agent with granular, inspectable sandbox/permission controls across CLI, desktop and IDE surfaces.
Apache-2.0 licensed CLI, free to self-host: OpenAI also offers a `codex cloud` managed alternative if you'd rather not run it yourself.

OpenHands
Open-source software engineering agent with a browser client, CLI and Python SDK; local, cloud or self-hosted.
Coding agentsFree, then $0.10/1m input tokensAPIAutonomousClaudeVerified 14 days agoBest for Open source-minded engineering teams and enterprises that want a self-hostable coding agent platform
A free local OSS release (81,000+ GitHub stars) or a fully self-hosted enterprise deployment inside your own VPC: the hosted Cloud tier is the third, optional path, not the only one.

Factory
Droid coding agents that run in the desktop app, CLI, IDEs, CI and Factory-managed cloud computers.
Coding agentsFrom $20/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering organizations that want AI agents handling more of the SDLC than code generation alone (triage, testing, release and documentation) and are willing to pay enterprise pricing for deployment flexibility and compliance controls.
The Enterprise tier spans fully managed SaaS, a hybrid cloud/customer-compute split, full on-premise, or air-gapped deployment across AWS, Azure or GCP with customer-managed encryption keys: the deepest self-hosting spread of any closed-source listing here.

CodeRabbit
AI code review across pull requests, IDE and CLI, with agentic fixes, pre-merge checks and security review.
Coding agentsFree, then $30/monthAPIAutonomousClaudeVerified yesterdayBest for Engineering teams, using a coding agent or writing code by hand, that want automatic, consistent PR review plus triage, explanation and continuous security across GitHub, GitLab, Bitbucket or Azure DevOps before a human reviewer looks at it.
The Enterprise tier adds self-hosting and API access on top of the default managed SaaS code-review product.

Warp
Agentic development environment: a terminal, a standalone agent CLI, and unattended cloud coding agents.
Coding agentsFree, then $20/monthAPIAutonomousClaudeVerified 14 days agoBest for Developers and teams who want one open platform that runs and coordinates multiple coding agents (Claude Code, Codex, Gemini CLI, Warp Agent) side by side across terminal, CLI and cloud, with shared team context and programmatic API access to cloud agent runs.
Open-sourced its terminal client under a dual AGPL-3.0/MIT license in April 2026, but Warp Factories (the cloud-agent platform that actually runs and coordinates agent work) stays closed and cloud-only; the self-hostable part is the terminal shell, not the agent backend.

Zed
Rust code editor with an Agent Panel running Zed's own agent, ACP external agents, or terminal agent CLIs.
Coding agentsFree, then $10/monthClaudeEnterpriseFree tierVerified 14 days agoBest for Developers who want a fast, open-source editor and the freedom to run Claude Code, Codex, Gemini CLI or other vendors' own agents natively via the Agent Client Protocol Zed created, instead of being locked into one editor's built-in agent.
GPL-3.0-or-later (Apache-2.0 for select components): a full IDE you can self-host and modify, not just a CLI wrapper.

Devin Desktop
AI IDE with a Kanban command center for running local and cloud coding agents; the renamed Windsurf.
Coding agentsFree, then $20/monthAutonomousClaudeEnterpriseVerified 14 days agoBest for Developers who want a full, agent-native desktop IDE and the freedom to run several coding agents, including third-party ones, side by side.
The desktop IDE rebranded to Devin Desktop after Cognition's acquisition; a local execution mode runs the coding agent on your own machine instead of dispatching to Devin Cloud: a desktop-local mode, not a team-deployable server, so weigh it differently than the enterprise on-prem entries here.

n8n
Workflow automation platform for building and running AI agents on a visual canvas, with code where needed.
Agent platformsFree, then €24/monthAPIAutonomousClaudeVerified 14 days agoBest for Ops and automation teams who want to build agentic workflows visually while keeping data on self-hosted infrastructure.
Source-available (fair-code): self-host free with full functionality, or use n8n Cloud from €20/month; the license carries a condition worth reading before assuming it behaves like a no-strings open-source grant.

Dify
Open-source platform for building agentic workflows, AI agents and RAG knowledge pipelines.
Agent platformsFree, then $59/monthAPIAutonomousClaudeVerified 14 days agoBest for Developers and teams who want an open-source, self-hostable platform to build RAG apps and agents with full data control.
Apache-2.0-derived core (149K+ GitHub stars): self-host with Docker for free, or use Dify's managed cloud; the built-in RAG pipeline runs the same either way.

LiveKit Agents
Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability.
Voice agentsFree, then $50/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering teams that want to own their voice-agent stack end to end, self-hosted or on LiveKit Cloud, without being locked into one vendor's API.
Apache-2.0 licensed: the one clean open-source, self-hostable pick in an otherwise all-cloud voice-agents category.

Bland
Enterprise voice AI platform for inbound and outbound phone agents, running on Bland's own self-hosted models.
Voice agentsFree, then $0.14/minuteAPIAutonomousEnterpriseVerified 5 days agoBest for Security-conscious enterprises in regulated industries that want a compliant, infrastructure-owned voice platform with deterministic call flows.
The Enterprise tier adds dedicated infrastructure with self-hosted or on-premises deployment, US/EU/APAC data residency, and SOC 2/HIPAA/PCI DSS compliance: the only voice agent here with a private-deployment path; every other listed voice agent is cloud-only.

Botpress
AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation.
Agent platformsFree, then $189/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering-led teams building a multi-channel AI support agent who want an open-source, self-hostable core with an optional managed cloud layer.
The agent-platform entry you can actually run yourself: the core is MIT-licensed and free to self-host, with a managed cloud alongside it rather than instead of it.

Deepgram Voice Agent API
One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents.
Voice agentsFrom $0.05/minuteAPIAutonomousClaudeVerified 14 days agoBest for Engineering teams that want a managed speech pipeline with real LLM-provider choice, and regulated enterprises that need a self-hosted or VPC deployment option a typical closed-source voice-agent vendor does not offer.
The only closed-source platform here that still offers a real deployment choice: fully managed, VPC-hosted or fully self-hosted, backed by SOC 2 Type II and signed HIPAA BAAs.

AgentsKit.js
TypeScript foundation for AI agents: runtime, tools, memory, RAG, model adapters and headless chat UI bindings.
Agent frameworksFreeAPIAutonomousClaudeVerified 7 days agoBest for JS/TS developers who want an ownable, dependency-light agent toolkit
An MIT-licensed TypeScript library rather than a service: its own hosted layer, AgentsKit OS, is enterprise-only early access with no self-serve signup, so self-hosting remains the only way to actually run it today, with 50 built-in integrations and a 10KB zero-dependency core letting you point it at a local runtime as easily as a frontier API.

Junie
JetBrains' coding agent: runs in JetBrains IDEs, the terminal and CI, on JetBrains models or your own keys.
Coding agentsFree, then $10/monthAPIAutonomousClaudeVerified 14 days agoBest for Developers and teams already standardized on a JetBrains IDE who want an agent that shares the same debugger, project index, and version control already built into their editor.
The only IDE-native agent here with a documented on-premise path: JetBrains includes Junie in AI Enterprise, which deploys cloud, on-premises or air-gapped. The isolated-infrastructure guide covers completion and Mellum rather than agent mode, so confirm Junie specifically before committing to an air-gapped rollout.

OpenClaw
Self-hosted gateway that connects chat apps like WhatsApp, Telegram and Slack to AI agents on your own machine.
Agent platformsFreeAPIAutonomousClaudeVerified 14 days agoBest for Developers and self-hosters who already run their own infrastructure and want one personal AI agent that reaches WhatsApp, Telegram, Slack, Discord, Signal and iMessage instead of a separate app.
The only agent-platform entry in this collection with no managed-cloud alternative at all: MIT-licensed, and it runs on your own machine or nowhere.

Augment Code
Cosmos platform running fleets of coding agents across the SDLC, plus Auggie CLI and IDE extensions.
Coding agentsFrom $100/monthAPIAutonomousClaudeVerified 14 days agoBest for Engineering leaders at organizations who want AI agents running full SDLC loops end to end, with humans at the quality gates, rather than inline completion assistants.
Loops run in Augment's managed cloud, a team's own AWS or GCP account, laptops, or dev VMs: closed-source, but the own-account path is a genuine private-deployment option, not a roadmap promise.

goose
Open-source local AI agent — desktop app, CLI and ACP server — running on the LLM provider you bring.
Coding agentsFreeAPIAutonomousClaudeVerified yesterdayBest for Devs who want an open source coding agent that reuses an existing Claude or ChatGPT plan
Apache-2.0 licensed and stewarded by the Linux Foundation's Agentic AI Foundation: a Rust-built desktop app, CLI and embeddable API with no managed cloud counterpart, authenticating against 15+ LLM providers or an existing Claude, ChatGPT or Gemini subscription instead of a hosted account.

Kilo Code
Open source AI coding agent for VS Code, JetBrains, CLI and cloud, with 500+ models at provider rates.
Coding agentsFree, then $15/monthAPIAutonomousClaudeVerified 14 days agoMIT-licensed end to end: extension, CLI and cloud-agent code all self-host; published pricing is Free Individual or $15/user/month Teams, with BYO API key or Kilo Pass credits from $19/month (Starter) to $199/month (Expert) plus a 5% processing fee on credit top-ups.
Browse wider than this shelf
A collection is one cut through the index. These are the full categories the agents above sit in, unfiltered.
Advertise here
Reach buyers mid-decision. Reach builders choosing their next agent. Promote your brand with a display placement or bring your listing into focus with Featured.
Explore owner options →Advertise on this page →The digestFree
Which agents actually ship.
What we re-checked, what got added, and one number from the index. Tuesdays.
One-click unsubscribe