#1Top pickFree option
Open-source platform for running autonomous coding agents, formerly OpenDevin
OpenHands (formerly OpenDevin) is an open-source platform for AI coding agents that can write code, run commands and browse the web in a sandbox. You can self-host it for free or use the hosted product. A Teams plan adds a managed setup for up to 10 users.
Why it's here
- +MIT licensed and self-hostable
- +Works with many models
- +Runs agents in isolated sandboxes
Watch out for
- −Self-hosting takes DevOps work
- −Hosted Teams plan is expensive for small teams
- −Less polished than commercial IDE agents
#2Free option
Open-source coding agent for VS Code that uses any model you bring
Cline is an open-source coding agent that runs inside VS Code and other editors, planning changes, editing files and running commands with your approval at each step. It is free for individual developers; you pay only for the AI model usage, using your own API keys or a provider of your choice. An Enterprise plan adds team controls.
Why it's here
- +Apache-2.0 open source
- +Works with many model providers, including local models
- +Clear plan-then-act flow with approvals
Watch out for
- −Model costs can add up with no cap
- −More setup than a subscription tool
- −Approving each step slows long tasks
#3Free option
Open-source personal AI assistant you run on your own computer and chat with
OpenClaw is an open-source personal AI assistant that runs on your own Mac, Windows or Linux machine and that you talk to through chat apps like WhatsApp, Telegram or Discord. It can manage email, calendars and files, browse the web and run shell commands. It is MIT licensed with no subscription; you choose the model it uses.
Why it's here
- +Runs locally and keeps state on your machine
- +Works from chat apps you already use
- +No subscription
Watch out for
- −Setup takes technical skill
- −Broad system access needs care
- −You manage updates and model costs
#4Free option
Workflow automation with AI agent nodes, cloud-hosted or self-hosted
n8n is a workflow automation platform with built-in AI agent nodes that connect models to your apps, databases and APIs. You build flows visually, drop into code when needed and run them in n8n's cloud or on your own servers. Cloud plans start at €20 a month billed annually and a self-hosted Community Edition is on GitHub.
Why it's here
- +Self-hosting option
- +Hundreds of integrations plus custom code
- +Flexible AI agent and tool nodes
Watch out for
- −Steeper learning curve than Zapier
- −Self-hosted license is fair-code, not OSI open source
- −Debugging complex flows takes time
#5Free option
Open-source platform for building AI apps, agents and RAG workflows
Dify is an open-source platform for building AI applications, agents and retrieval workflows with a visual editor. You can self-host the Community Edition with Docker or use Dify Cloud. The cloud Sandbox plan is free with 200 message credits and Professional costs $590 per workspace per year.
Why it's here
- +Self-hostable
- +Visual workflow and RAG tools
- +Works with many model providers
Watch out for
- −License has extra conditions beyond Apache-2.0
- −Self-hosting needs maintenance
- −Less suited to non-technical users
Free · from $49/moTask agent
#6Free option
Open-source framework for building stateful, controllable agents as graphs
LangGraph is an open-source framework from LangChain for building agents as graphs of steps with state, memory and human-in-the-loop checkpoints. It gives developers fine control over how an agent moves between tools and decisions. It is MIT licensed, with LangSmith available for tracing and deployment.
Why it's here
- +Fine control over agent flow
- +Built-in persistence and human approval steps
- +Large ecosystem and docs
Watch out for
- −More code than higher-level frameworks
- −Concepts take time to learn
- −Best tooling ties into LangSmith
#7Free option
Open-source Python framework for teams of role-based AI agents
CrewAI is an open-source Python framework for building multi-agent systems where agents with defined roles work together on tasks. It is known for being quick to start with. CrewAI also runs a hosted platform with a free Basic plan and custom Enterprise pricing.
Why it's here
- +Simple, readable agent definitions
- +MIT licensed
- +Large community and examples
Watch out for
- −Less fine-grained control than LangGraph
- −Multi-agent runs can be costly in tokens
- −Debugging agent hand-offs is hard
#8Free option
Open-source library and cloud for AI agents that control web browsers
Browser Use is an open-source Python library that lets AI agents operate a web browser, plus a cloud service that runs those browsers for you. Developers use it to automate web tasks on sites without APIs. The library is MIT licensed; the cloud is pay-as-you-go with a $5 minimum top-up.
Why it's here
- +Large open-source community
- +Works with many models
- +Hosted browsers when you need scale
Watch out for
- −Requires coding
- −Websites change and break flows
- −Model and proxy costs add up
A#9Free option
Open-source AI pair programmer that edits code in your terminal with git commits
Aider is an open-source AI pair programmer that runs in your terminal and edits code in your local git repository. It works with many LLMs, maps your codebase for context and commits each change so you can review or undo it. It is free to use; you pay only for the model API you connect.
Why it's here
- +Every edit is a git commit you can undo
- +Works with most model providers
- +Lightweight, no editor lock-in
Watch out for
- −Development has slowed in 2026
- −Less autonomous than newer agents
- −No built-in team features
#10Free option
Open-source platform for building and running continuous AI agents
AutoGPT is an open-source project for building, deploying and running AI agents that automate multi-step workflows. It began as one of the first autonomous GPT agents and now includes a low-code platform you can self-host. The code is on GitHub, with the classic agent under MIT and the newer platform under its own license.
Why it's here
- +Free and self-hostable
- +Large, long-running community
- +Visual builder for agents
Watch out for
- −Self-hosting takes effort
- −Less reliable than commercial tools
- −Mixed licenses across the repo
#11Free option
Microsoft's open-source agent SDK for .NET and Python, successor to AutoGen
Microsoft Agent Framework is an open-source SDK for building AI agents and multi-agent workflows in Python and .NET. It brings together ideas from AutoGen and Semantic Kernel, and Microsoft recommends it for new projects instead of AutoGen, which is now in maintenance mode. It is MIT licensed.
Why it's here
- +First-class .NET and Python support
- +Backed by Microsoft
- +Clear migration path from AutoGen
Watch out for
- −Younger than LangGraph or CrewAI
- −Best fit leans toward Azure
- −Docs still catching up
O#12Free option
OpenAI's lightweight open-source SDK for building agents with tools and handoffs
The OpenAI Agents SDK is an open-source framework for building agents that use tools, hand off to other agents and apply guardrails, with tracing built in. It is small and Python-first, with a TypeScript version too. It is MIT licensed and works with OpenAI and other model providers.
Why it's here
- +Few concepts to learn
- +Built-in tracing and guardrails
- +MIT licensed
Watch out for
- −Fewer built-in integrations than LangChain
- −Best experience with OpenAI models
- −Less suited to complex graph workflows
#13Free option
Anthropic's SDK for building agents on the same harness that powers Claude Code
The Claude Agent SDK is an open-source SDK from Anthropic for building agents that use the same tools and agent loop as Claude Code, including file access, command execution, subagents and MCP. It is available for Python and TypeScript. The SDK is MIT licensed; you pay for Claude API usage.
Why it's here
- +Battle-tested agent loop from Claude Code
- +Built-in tools and MCP support
- +Python and TypeScript
Watch out for
- −Designed around Claude models
- −API costs for long sessions
- −Less suited to visual, no-code builders
#14Free option
Type-safe Python agent framework from the team behind Pydantic
Pydantic AI is an open-source Python framework for building agents with typed inputs, outputs and tools, made by the Pydantic team. It works with many model providers and pairs with Pydantic Logfire for observability. It is MIT licensed.
Why it's here
- +Typed, validated outputs
- +Model-agnostic
- +Feels like normal Python
Watch out for
- −Python only
- −Fewer prebuilt integrations
- −Multi-agent patterns are more manual
#15Free option
TypeScript framework for AI agents, workflows, memory and evals
Mastra is a TypeScript framework for building AI agents, workflows and AI-powered apps, with memory, tools and observability included. It suits JavaScript and TypeScript teams that want to stay in their own stack. The core is Apache-2.0 licensed, with some enterprise features under a separate license.
Why it's here
- +Native TypeScript
- +Workflows, memory and evals in one package
- +Local dev playground
Watch out for
- −Not for Python teams
- −Younger ecosystem
- −Enterprise features under a different license
#16Free option
Open-source framework for agents over your documents and data
LlamaIndex is an open-source framework for building agents and retrieval apps that work over your documents and data, with Workflows for multi-step agents. The company also sells LlamaParse, a document parsing and extraction service. The framework is MIT licensed; LlamaParse has a free credit tier and paid plans.
Why it's here
- +Strong document and retrieval tooling
- +Many data connectors
- +MIT licensed
Watch out for
- −Best parsing is a paid service
- −API surface changes often
- −Less focused on general agents
#17Free option
Google's open-source toolkit for building and deploying multi-agent systems
Google Agent Development Kit (ADK) is an open-source framework for building, testing and deploying AI agents and multi-agent systems. It is optimized for Gemini and Google Cloud but works with other models. It is Apache-2.0 licensed.
Why it's here
- +Built-in eval and dev UI
- +Easy deploy to Google Cloud
- +Apache-2.0 licensed
Watch out for
- −Best fit with Gemini and Google Cloud
- −Smaller community than LangGraph
- −Fast-moving APIs
More open source agents
Listed but not yet reviewed in depth.
GPT PilotGPT Pilot aims to research how much LLMs can be utilized to generate fully working, production-ready apps w…Open sourceBBabyAGIBabyAGI is an AI-powered task management system that leverages OpenAI and vector databases to streamline ta…Open sourceAAIliceAIlice is a fully autonomous, general-purpose AI agent developed by MyShell.ai.Open source
ClippyClippy, also known as Clippinator, is an AI-powered code development assistant that utilizes GPT-4 to enhan…Open source
OpenAgentsOpenAgents is an open platform designed for language agents, featuring a user-friendly interface that suppo…Open source
MentantMentat is an AI coding assistant that integrates seamlessly with your command line, providing developers wi…Open source
AgentOpsAgentOps is an advanced developer platform designed specifically for testing and debugging AI agents.Open source
SellAgentSellAgent introduces a community-driven platform centered around its Large Action Model (LAM).Open source
AgentForgeAgentForge is a cutting-edge brand offering technology solutions and consultation services focused on the d…Open source
OpenBMBOpenBMB is a platform that focuses on delivering large-scale AI models to everyone.Open sourceMMyShellMyShell is an AI platform that empowers users to build, share, and own AI applications with ease.Open source
AutoRPAutoRP is a GitHub-based tool that runs AI-powered workflows over codebases.Open source
Autonomous HRAutonomous HR is an AI agent designed to manage human resources queries autonomously.Open source
Camel AICamel AI is an open-source, multi-agent framework built around the exploration of AI scaling laws.Open source
ChatDevChatDev is an innovative open-source framework designed to facilitate multi-agent collaboration.Open source
ChemcrowChemcrow stands out as an essential tool for researchers and professionals working with chemical data.Open source
CodefuseCodefuse serves as an intelligent assistant throughout the software development lifecycle, built on a power…Open source
SourceGraphSourceGraph provides a comprehensive web app and documentation resource that supports the Sourcegraph ecosy…Open source
ChaindeskChaindesk revolutionizes customer interaction by enabling businesses to train custom ChatGPT AI chatbots fo…Open source
DevonDevon is positioned as an open-source pair programming tool, making it a valuable resource for developers s…Open source
KuaFuAiKuaFuAi introduces a multi-agent system specifically designed for AI-driven software development.Open sourceDDotagentDotagent claims to be faster, cheaper, and smarter than any single large language model (LLM).Open source
EidolonEidolon is a robust, open-source framework built to help developers quickly create and deploy generative AI…Open source
The English CompilerThe English Compiler is a proof-of-concept AI-based compiler designed to convert English-based markdown spe…Open source
AgentcoinAgentcoin offers an exclusive club experience where users can "buy a key" to participate in a collaborative…Open source
DemoGPTGenerator for LangChain code and Streamlit apps powered by AI.Open source
Taxy AIGPT-4-driven browser automation for seamless task execution.Open source
UFOAI framework for UI interaction on Windows OS.Open source
OpenAGIPlatform for creating and managing LLM-powered agents.Open source
Mini AGICompact AI agent with advanced memory and reasoning abilities.Open source
MemGPTCreate LLM agents with persistent memory and customizable capabilities.Open source
SuperAGIDeveloper-first framework for building autonomous AI agents.Open source
AdalaFramework for autonomous data labeling in AI development.Open source
BambooAIData analysis assistant driven by AI for natural language interactions.Open source
BeeBotAutonomous task executor acting as a personal AI worker.Open source
AgentVerseMulti-agent LLM framework for task-solving and simulations.Open source
CodeFuse-ChatBotAI assistant for managing the software development lifecycle.Open source
Cody by ajhous44Coding assistant with AI for efficient codebase navigation.Open source
GPT DiscordAdvanced GPT-powered Discord bot with AI features.Open source
GPT RunnerTool for AI-driven code discussions and preset management.Open source
GPT MigrateAI-based code migration assistant.Open source
GeniAAI-powered engineering assistant for streamlined workflows.Open source
Lemon AgentWorkflow optimization with AI-powered task planning and execution.Open source
bumpgenAI-powered assistant for TypeScript dependency upgrades.Open source
LLM AgentsBuild and manage AI agents using large language models.Open source
WorkGPTFramework for AI agents to complete tasks using diverse APIs.Open source
GitHub Copilot XAI coding assistant to enhance developer productivity.Open source
InstruktTerminal-based AI environment for agent development and instruction.Open source
IXAutonomous GPT-4 agent platform for flexible workflows.Open source
Devika AIDevika AI, developed by Stition.ai, is an advanced AI software engineer capable of understanding high-level…Open source
Micro AgentMicro Agent is an open-source tool developed by Builder.io to address the unreliability of AI-generated code.Open source
JARVISMicrosoft Jarvis is an advanced AI platform developed by Microsoft in collaboration with Hugging Face.Open source
Multi-GPTMulti-GPT is an open-source project that creates a collaborative environment for multiple AI agents, each w…Open source
Teenage-AGITeenage-AGI is a Python-based AI agent inspired by BabyAGI and the "Generative Agents: Interactive Simulacr…Open source