Agent SDKs & frameworks
general-purpose libraries for building agents
deepseek-ai/deepseek-harness deepseek-ai/deepseek-harness leads on adoption and offers a plugin-first harness that makes composing complex agent workflows simple; pick it if you want the broadest, componentized way to stitch models and tools together. If you need something else (enterprise controls, local-only operation, typed outputs, or specialized GUIs/trainers) choose a project focused on that gap.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 145.6k +446/7d | CLIIDECIWeb app | BYOKOpenAIAnthropicGemini | Diff/file only | None mentioned | ●●●●● | Cloud-key usage | ●●●●● | Your API key, per-provider pricing |
⭐ 46.8k +72/7d | Web appCLI | BYOKOpenAIAnthropicGeminiOllama / localFixed provider | Diff only | None mentioned | ●●●●● | Can run fully local | ●●●●● | Your API key for cloud models; can use local models. |
⭐ 42.0k +94/7d | CLIWeb appCoding-agent plugin | BYOK | Diff only | Human approval | ●●●●● | Self-hostable | ●●●●● | Free, self-hosted |
⭐ 37.2k +107/7d | Web appCLI | BYOKOpenAIAnthropicGemini | File-level context | Human-in-the-loop | ●●●●● | Self-hostable (cloud optional) | ●●●●● | Your LLM API key (third‑party); optional CopilotKit Cloud (separate pricing). |
⭐ 30.6k +739/7d | CLIWeb app | Fixed provider | Diff + related files | Human-in-the-loop | ●●●●● | Self-hostable | ●●●●● | Requires a model provider API key (provider-dependent). |
⭐ 30.0k +125/7d | CLICoding-agent pluginWeb app | BYOKOpenAIAnthropicGeminiFixed provider | Session/tool scope | Configurable filters | ●●●●● | Cloud w/ your API key | ●●●●● | Requires Composio dashboard API key |
⭐ 29.1k +123/7d | CLIWeb app | BYOKOpenAIAnthropicOllama / localFixed provider | Diff only | None mentioned | ●●●●● | Fully local possible | ●●●●● | Requires provider API keys; provider billing applies. |
⭐ 29.0k +304/7d | CLIWeb app | BYOKOpenAIAnthropicGeminiOllama / local | Whole-repo analysis | Human-in-the-loop | ●●●●● | Fully local | ●●●●● | Your API key for hosted models; can run locally with self-hosted models. |
⭐ 28.5k +19/7d | CLIWeb appCI | BYOKOpenAIOllama / localFixed provider | No repo context | Structured output | ●●●●● | Fully local possible | ●●●●● | Your API key for cloud models; local-hosted models available |
⭐ 27.7k +148/7d | CLIWeb appIDECoding-agent plugin | BYOKOpenAIAnthropicGemini | Repo + related files | Human-in-the-loop | ●●●●● | Self-hostable | ●●●●● | Your API keys for chosen models (per-provider billing) |
⭐ 26.4k +64/7d | CLIWeb app | BYOKOpenAIAnthropicOllama / localFixed provider | Whole-repo analysis | Filtering & ranking | ●●●●● | Local models supported | ●●●●● | Your model provider/API key, or self-hosted (local models) |
⭐ 24.6k +142/7d | CLIWeb app | BYOKOpenAIAnthropic | Diff/file only | None mentioned | ●●●●● | Fully local support | ●●●●● | Cloud requires a Letta API key; local runs free |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
A broad, production-ready agent framework with a large ecosystem of integrations and modular abstractions to swap models, tools, and retrievers without rewriting application code.
A lightweight, full-featured Agent Harness with a one-click Skill Hub, built-in long-term memory, knowledge graph, and self-evolution features that combine multi-channel runtime and plugin skills.
An end-to-end agent framework delivering an SDK, AgentOS runtime, and a management UI with built-in storage, observability, and human approval for running agent platforms.
Provides a multi-platform generative UI and shared-state SDK that lets the same agent run across web, mobile, and chat via the AG-UI Protocol.
A production-ready agent framework offering multi-tenancy, fine-grained permission controls, sandboxed workspaces, and an extensible middleware/event system for building trustworthy agent services.
Provides 1000+ pre-authenticated toolkits plus per-user sessions, authentication, and a sandboxed workbench so agents can discover and execute real app tools at runtime.
Provides a minimal, code-centric agent design where the LLM emits executable Python actions (code-as-actions) rather than only tool-call dictionaries, with built-in sandboxing and Hub/tool integrations.
A batteries-included, opinionated agent harness that bundles filesystem access, sub-agents, context management, skills, and human-in-the-loop controls out of the box.
All repositories (85)
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory a…
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI P…
Build and run agents you can see, understand and trust.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to…
🤗 smolagents: a barebones library for agents that think in code.
Integrate cutting-edge LLM technology quickly and easily into your apps
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Des…
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skil…
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with…
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed…
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage &…
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG,…
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that promp…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-…
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible fro…
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScr…
dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware re…
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget…
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Build distributed, production-grade, long-running agents.
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
A simple yet powerful agent framework that delivers with open-source models
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function call…
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans ou…
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaborat…
A Python library for building AI agents that leverage the full power of Google Antigravity.
J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r…
J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r…
A framework-agnostic, git-native standard for defining AI agents
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the offici…
The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect component…
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, eva…
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi C…
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with…
OctoTools: An agentic framework with extensible tools for complex reasoning
The agent framework where every run is durable, replayable, and resumable by default.
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at r…
Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG…
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,…
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,…
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider,…
A single interface to use and evaluate different agent frameworks
Build your own Cowork, AI Scientist and other SoTA Agents just by editing config files. Support anthropic skil…
Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Dis…
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web a…
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Usin…
The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allow…
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
Integrate LLM in any pipeline - fit/predict pattern, JSON driven flows, and built in concurency support.
HarnessX is a harness foundry: forge any number of agent harnesses from reusable processors and bundles, pair…
Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.
Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm /…
No longer maintained — active development moved to https://github.com/markpollack/agent-client
Agent framework for smart-cockpit apps · 面向智能座舱业务的 Agent 框架:零后端、权限分级、确认流、卡片编排、快慢双层、真实三方集成,加能力=加数据不加代码
OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Q…
笨办法学 Agent · 亲手打造一个 harness——不用框架，32 个练习亲手写出一个 agent harness 的每一层。系列第一本，全书已完结，三本各自独立不分先后。
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dum…
A nano, minimalistic, and lightweight library for building ReACT-based AI agents that use tools to solve tasks…
Self-hosted multi-tenant agent platform for teams: skills, knowledge, API contracts and MCP servers live in th…
Hosted alternatives
If running your own reviewer is more ops than you want, these managed services cover the same job.
The managed side of letta: the same stateful-agent model with long-term memory, run and persisted for you. You keep the agent design and skip hosting the server and its memory store.
Try Letta Cloud →The hosted counterpart to adk-python — build with the open-source ADK, then deploy to Google's Agent Engine runtime with scaling, sessions and tracing handled instead of running the process yourself.
Try Google Vertex AI Agent Builder →A framework-agnostic managed runtime: take agents built with LangChain, CrewAI or any SDK here and get memory, identity, tool gateways and a secure sandbox on AWS rather than assembling that infrastructure around your code.
Try Amazon Bedrock AgentCore →