37 best agent frameworks GitHub repos to use
The libraries you build an agent on top of. These handle the loop, the tool calls, and the state so you are not rewriting the same orchestration for the fifth time.
Find GitHub repos worth using by topic, language, license and how active they are. Navid's picks come first, and each one opens its own page.
This is a list of the best agent frameworks GitHub repos.
In fact, it has 37 of them, with Navid's picks first.
So if you want agent frameworks GitHub repos worth your time, you'll love this list.
The libraries you build an agent on top of. These handle the loop, the tool calls, and the state so you are not rewriting the same orchestration for the fifth time.
Here's what's inside:
- Dify by langgenius
- LangChain by LangChain
- Browser Use by Browser Use
- TradingAgents by tauricresearch
- Ragflow by infiniflow
- Taste Skill by Leonxlnx
- Openhands by OpenHands
- WorldMonitor by koala73
- Deer Flow by bytedance
- Rtk by rtk-ai
- Headroom by headroomlabs-ai
- CrewAI by CrewAI
- Shannon by KeygraphHQ
- Langgraph by langchain-ai
- Deeptutor by HKUDS
- AI Engineering Hub by patchy631
- DeepSeek Reasonix by esengine
- Vibe Trading by HKUDS
- Rag_techniques by NirDiamant
- Agentmemory by rohitg00
- 12 Factor Agents by humanlayer
- Genai_agents by NirDiamant
- Easy Vibe by datawhalechina
- Openship by oblien
- Cocoindex by cocoindex-io
- Holaos by holaboss-ai
- Apify MCP Server by apify
- Microsandbox by superradcompany
- Agentic Inbox by Cloudflare
- Superagent by superagent-ai
- Sensenova Skills by OpenSenseNova
- Cloudflare Agents by Cloudflare
- Macro by macro-inc
- Jupyter Ai by jupyterlab
- Automodel by NVIDIA-NeMo
- Pr Af by Agent-Field
- Heygen Cli by heygen-com
Each one comes with what it covers and who it's for.
What are the best agent frameworks GitHub repos?
Here's the list at a glance.
- Owner
- langgenius
- Stars
- ★ 157k
- Owner
- LangChain
- Stars
- ★ 147k
- Owner
- Browser Use
- Stars
- ★ 116k
- Owner
- tauricresearch
- Stars
- ★ 108k
- Owner
- infiniflow
- Stars
- ★ 91k
- Owner
- Leonxlnx
- Stars
- ★ 90k
- Owner
- OpenHands
- Stars
- ★ 89k
- Owner
- koala73
- Stars
- ★ 88k
- Owner
- bytedance
- Stars
- ★ 83k
- Owner
- rtk-ai
- Stars
- ★ 82k
- Owner
- headroomlabs-ai
- Stars
- ★ 74k
- Owner
- CrewAI
- Stars
- ★ 59k
- Owner
- KeygraphHQ
- Stars
- ★ 48k
- Owner
- langchain-ai
- Stars
- ★ 42k
- Owner
- HKUDS
- Stars
- ★ 40k
- Owner
- patchy631
- Stars
- ★ 38k
- Owner
- esengine
- Stars
- ★ 36k
- Owner
- HKUDS
- Stars
- ★ 34k
- Owner
- NirDiamant
- Stars
- ★ 30k
- Owner
- rohitg00
- Stars
- ★ 29k
- Owner
- humanlayer
- Stars
- ★ 26k
- Owner
- NirDiamant
- Stars
- ★ 24k
- Owner
- datawhalechina
- Stars
- ★ 20k
- Owner
- oblien
- Stars
- ★ 12k
Cocoindex- Owner
- cocoindex-io
- Stars
- ★ 12k
Holaos- Owner
- holaboss-ai
- Stars
- ★ 11k
Apify MCP Server- Owner
- apify
- Stars
- ★ 8.8k
Microsandbox- Owner
- superradcompany
- Stars
- ★ 8.4k
Agentic Inbox- Owner
- Cloudflare
- Stars
- ★ 7.9k
Superagent- Owner
- superagent-ai
- Stars
- ★ 6.8k
Sensenova Skills- Owner
- OpenSenseNova
- Stars
- ★ 5.7k
- Owner
- Cloudflare
- Stars
- ★ 5.6k
Macro- Owner
- macro-inc
- Stars
- ★ 4.4k
Jupyter Ai- Owner
- jupyterlab
- Stars
- ★ 4.4k
Automodel- Owner
- NVIDIA-NeMo
- Stars
- ★ 985
Pr Af- Owner
- Agent-Field
- Stars
- ★ 640
Heygen Cli- Owner
- heygen-com
- Stars
- ★ 138
Top 37 agent frameworks GitHub repos
1. Dify by langgenius
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features (including Opik, Langfuse, and Arize Phoenix) and more, letting you quickly go from prototype to production. Here's a list of the core features:
The easiest way to start the Dify server is through Docker Compose. Before running Dify with the following commands, make sure that Docker and Docker Compose v2.24.0 or later are installed on your machine:
After running, you can access the Dify dashboard in your browser at http://localhost/install and start the initialization process.
Stars: 157k
Language: TypeScript
License: Other
Install:
bash docker compose up -d
View Dify on GitHub · More about Dify
2. LangChain by LangChain
LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development, all while future-proofing decisions as the underlying technology evolves.
Just getting started? Check out Deep Agents, a higher-level package built on LangChain for agents that have built-in capabilites for common usage patterns such as planning, subagents, file system usage, and more.
If you're looking for more advanced customization or agent orchestration, check out LangGraph, our framework for building controllable agent workflows.
Stars: 147k
Language: Python
License: MIT
Install:
bash uv add langchain
View LangChain on GitHub · More about LangChain
3. Browser Use by Browser Use
Browser Use lets an AI agent use a web browser the same way humans do, it opens pages, clicks buttons, types, and fills in forms. You describe the task, and it completes it. For example, you can have it:
https://github.com/user-attachments/assets/485fd3ec-61b9-4afc-9e86-ee9b85acb592
If you want to use Browser Use in your agent (Claude Code, Codex, Cursor, Hermes, OpenClaw, etc.), paste this prompt, and it sets everything up itself:
Stars: 116k
Language: Python
License: MIT
Install:
bash uv add browser-use
View Browser Use on GitHub · More about Browser Use
4. TradingAgents by tauricresearch
TradingAgents officially released! We have received numerous inquiries about the work, and we would like to express our thanks for the enthusiasm in our community.
So we decided to fully open-source the framework. Looking forward to building impactful projects with you!
TradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.
Stars: 108k
Language: Python
License: Apache-2.0
Install:
bash git clone https://github.com/TauricResearch/TradingAgents.git
View TradingAgents on GitHub · More about TradingAgents
5. Ragflow by infiniflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale. Powered by a converged context engine and pre-built agent templates, RAGFlow enables developers to transform complex data into high-fidelity, production-ready AI systems with exceptional efficiency and precision.
Try our cloud service at https://cloud.ragflow.io. 2026-06-15 Support multiple chat channels such as Feishu, Discord, Telegram, Line, etc. 2026-04-24 Supports DeepSeek v4. 2026-03-24 RAGFlow Skill on OpenClaw, Provides an official skill for accessing RAGFlow datasets via OpenClaw. 2025-12-26 Supports 'Memory' for AI agent. 2025-11-19 Supports Gemini 3 Pro. 2025-11-12 Supports data synchronization from Confluence, S3, Notion, Discord, Google Drive. 2025-10-23 Supports MinerU & Docling as document parsing methods. 2025-10-15 Supports orchestrable ingestion pipeline. 2025-08-08 Supports OpenAI's latest GPT-5 series models. 2025-08-01 Supports agentic workflow and MCP. 2025-05-23 Adds a Python/JavaScript code executor component to Agent. 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.
Star our repository to stay up-to-date with exciting new features and improvements! Get instant notifications for new releases! Deep document understanding-based knowledge extraction from unstructured data with complicated formats. Finds "needle in a data haystack" of literally unlimited tokens. Intelligent and explainable. Plenty of template options to choose from. Visualization of text chunking to allow human intervention. Quick view of the key references and traceable citations to support grounded answers. Supports Word, Slides, Excel, TXT, images, scanned copies, structured data, web pages, and more. Streamlined RAG orchestration catered to both personal and large businesses. Configurable LLMs as well as embedding models. Multiple recall paired with fused re-ranking. Intuitive APIs for seamless integration with business. CPU = 4 cores RAM = 16 GB Disk = 50 GB Docker = 24.0.0 & Docker Compose = v2.26.1 Python = 3.13 gVisor: Required only if you intend to use the code executor (sandbox) feature of RAGFlow.
Stars: 91k
Language: Go
License: Apache-2.0
Install:
bash git clone https://github.com/infiniflow/ragflow.git
View Ragflow on GitHub · More about Ragflow
6. Taste Skill by Leonxlnx
Portable Agent Skills that upgrade AI-built interfaces: stronger layout, typography, motion, and spacing instead of boilerplate-looking UIs. This repo also includes image-generation skills for reference boards (web, mobile, brand kits). Pair them with ChatGPT Images or similar generators, then hand the frames to Codex, Cursor, or Claude Code for implementation.
Taste Skill has no official token, coin, or crypto project. Any token using my name, image, or project is unaffiliated and not endorsed by me.
We would love your feedback. Suggestions and bug reports: Open a Pull Request or Issue on GitHub DM @lexnlin or @blueemi99 Email us at hello@tasteskill.dev
Stars: 90k
Language: JavaScript
License: MIT
Install:
bash npx skills add https://github.com/Leonxlnx/taste-skill
View Taste Skill on GitHub · More about Taste Skill
7. Openhands by OpenHands
The self-hosted developer control center for coding agents and automations.
Run OpenHands, Claude Code, Codex, Gemini, or any ACP-compatible agent across local, remote, and cloud backends.
OpenHands Agent Canvas turns your coding agents into a self-hosted, always-on engineering team. It's a developer control center for starting conversations and automating everyday tasks, like generating reports that publish to Slack or automatically decomposing GitHub issues into tasks.
Stars: 89k
Language: TypeScript
License: MIT
Install:
bash npm install -g @openhands/agent-canvas
View Openhands on GitHub · More about Openhands
8. WorldMonitor by koala73
Real-time global intelligence dashboard, AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface.
500+ curated news feeds across 15 categories, AI-synthesized into briefs Dual map engine, 3D globe (globe.gl) and WebGL flat map (deck.gl) with 56 map layer types Panel inventory, 109 concrete panel implementations across six specialized variants Cross-stream correlation, military, economic, disaster, and escalation signal convergence Country Instability Index (CII), server-authoritative CII v8 stress scoring for 31 Tier-1 countries Finance radar, 29 stock exchanges, commodities, crypto, and 7-signal market composite Local AI, run everything with Ollama, no API keys required 6 site variants from a single codebase (world, tech, finance, commodity, happy, energy) Native desktop app (Tauri 2) for macOS, Windows, and Linux 28 languages with native-language feeds and RTL support
For the full feature list, architecture, data sources, and algorithms, see the documentation.
Stars: 88k
Language: TypeScript
License: AGPL-3.0
Install:
bash git clone https://github.com/koala73/worldmonitor.git
View WorldMonitor on GitHub · More about WorldMonitor
9. Deer Flow by bytedance
On February 28th, 2026, DeerFlow claimed the #1 spot on GitHub Trending following the launch of version 2. Thanks a million to our incredible community, you made this happen!
DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to do almost anything, powered by extensible skills.
https://github.com/user-attachments/assets/a8bcadc4-e040-4cf2-8fda-dd768b999c18
Stars: 83k
Language: Python
License: MIT
Install:
bash git clone https://github.com/bytedance/deer-flow.git
View Deer Flow on GitHub · More about Deer Flow
10. Rtk by rtk-ai
rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, Full explanation: How RTK Savings Work
Download from releases: macOS: rtk-x8664-apple-darwin.tar.gz / rtk-aarch64-apple-darwin.tar.gz Linux: rtk-x8664-unknown-linux-musl.tar.gz / rtk-aarch64-unknown-linux-gnu.tar.gz Windows: rtk-x8664-pc-windows-msvc.zip
Windows users: Extract the zip and place rtk.exe somewhere in your PATH (e.g. C:\Users\\.local\bin). Run RTK from Command Prompt, PowerShell, or Windows Terminal, do not double-click the.exe (it will flash and close). The full hook system works natively on Windows (and in WSL). See Windows setup below for details.
Stars: 82k
Language: Rust
License: Apache-2.0
Install:
bash brew install rtk
View Rtk on GitHub · More about Rtk
11. Headroom by headroomlabs-ai
AI agents / LLMs: read /llms.txt here, or fetch the live index / full docs blob.
Headroom compresses everything your AI agent reads, tool outputs, logs, RAG chunks, files, and conversation history, before it reaches the LLM. Same answers, fraction of the tokens.
Live: 10,144 1,260 tokens, same FATAL found. Library, compress(messages) in Python or TypeScript, inline in any app Proxy, headroom proxy --port 8787, zero code changes, any language Agent wrap, headroom wrap claudecodexgrokcopilotcursoraideropencodeclinecontinuegooseopenhandsopenclawvibeompzcode in one command; undo with headroom unwrap MCP server, headroomcompress, headroomretrieve, headroomstats for any MCP client Cross-agent memory, shared store across Claude, Codex, Gemini, Grok, auto-dedup headroom learn, mines failed sessions, writes corrections to CLAUDE.local.md (default, gitignored) or CLAUDE.md / AGENTS.md / GEMINI.md / GROK.md Output token reduction, trims what the model writes back (not just what you send): drops ceremony/restated code and skips deep "thinking" on routine steps. See Output token reduction. Reversible (CCR), originals are cached for retrieval on demand ContentRouter, detects content type, selects the right compressor SmartCrusher / CodeCompressor / Kompress-v2-base, compress JSON, AST, or prose CacheAligner - detects and warns about volatile content that can bust provider KV cache prefixes; never rewrites prompts CCR, stores originals locally; LLM calls headroomretrieve if it needs them
Stars: 74k
Language: Python
License: Apache-2.0
Install:
bash uv tool install --python 3.13 "headroom-ai[all]" # CLI, isolated app env
View Headroom on GitHub · More about Headroom
12. CrewAI by CrewAI
CrewAI is an open-source Python framework with high-level abstractions and low-level APIs for building production-ready multi-agent workflows. It gives developers autonomous agent collaboration through Crews and precise, event-driven control through Flows. CrewAI Crews: Optimize for autonomy and collaborative intelligence with role-based AI agents. CrewAI Flows: Build event-driven automations that combine precise workflow control, single LLM calls, and native support for Crews.
With over 100,000 developers certified through our community courses at learn.crewai.com, CrewAI is rapidly becoming the standard for production-ready agentic automation.
For organizations that need a commercial control plane around CrewAI, CrewAI AMP Suite adds managed deployment, observability, governance, security, and enterprise support.
Stars: 59k
Language: Python
License: MIT
Install:
bash npx skills add crewaiinc/skills
View CrewAI on GitHub · More about CrewAI
13. Shannon by KeygraphHQ
Shannon is an autonomous, AI pentester for web applications and APIs. It analyzes your source code, identifies attack paths, and executes real exploits to prove vulnerabilities before they reach production.
This repository is Shannon Open Source: the full agent, run locally from your command line.
[!TIP] AI agents and LLMs: start with llms.txt for a concise map of this repository, or use llms-full.txt for the README and docs combined into one file. What is Shannon? Shannon in Action Quick Start Key Capabilities Editions Architecture Documentation Safety, Scope, and Limitations License About Keygraph Community and Support
Stars: 48k
Language: TypeScript
License: AGPL-3.0
Install:
bash npx @keygraph/shannon setup
View Shannon on GitHub · More about Shannon
14. Langgraph by langchain-ai
Low-level orchestration framework for building stateful agents.
Trusted by companies shaping the future of agents, including Klarna, Replit, Elastic, and more, LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
If you're looking to quickly build agents, check out Deep Agents, a higher-level package built on LangGraph for agents that can plan, use subagents, and leverage file systems for complex tasks.
Stars: 42k
Language: Python
License: MIT
Install:
bash pip install -U langgraph
View Langgraph on GitHub · More about Langgraph
15. Deeptutor by HKUDS
We welcome any kinds of contributing! Vote on roadmap items or propose new ones at Roadmap, and see our Contributing Guide for branching strategy, coding standards, and how to get started.
[2026.8.13] v1.5.12, Web search rebuilt with six new providers (Doubao, Bocha, Zhipu, Firecrawl, Qianfan, Aliyun IQS), a LiteParse parsing engine, MCP servers that reconnect on credential change, and CodeBuddy + OrcaRouter.
[2026.8.10] v1.5.11, Prose around a DSML tool call stops vanishing, a truncated reply continues instead of ending, live memory usage in Settings, and LightRAG indexing off the event loop.
Stars: 40k
Language: Python
License: Apache-2.0
Install:
bash pip install -U deeptutor
View Deeptutor on GitHub · More about Deeptutor
16. AI Engineering Hub by patchy631
Welcome to the AI Engineering Hub - your comprehensive resource for learning and building with AI!
AI Engineering is advancing rapidly, and staying at the forefront requires both deep understanding and hands-on experience. Here, you will find: 93+ Production-Ready Projects across all skill levels In-depth tutorials on LLMs, RAG, Agents, and more Real-world AI agent applications Examples to implement, adapt, and scale in your projects
Whether you're a beginner, practitioner, or researcher, this repo provides resources for all skill levels to experiment and succeed in AI engineering.
Stars: 38k
Language: Jupyter Notebook
License: MIT
View AI Engineering Hub on GitHub · More about AI Engineering Hub
17. DeepSeek Reasonix by esengine
Open source · MIT · a single Go binary A coding agent you can leave running. One local engine, four ways in, terminal, desktop app, browser, or your editor over ACP. Plan mode, permissions, a workspace sandbox and per-turn checkpoints keep a long autonomous run something you can still read and undo.
[!IMPORTANT] Community · 加入社区, bilingual Discord for setup help (#help / #求助), workflow showcases, and feature ideas. Config-driven. Providers, the agent, enabled tools, and plugins are all declared in reasonix.toml. No hardcoded models. Multi-model & composable. DeepSeek ships as a preset; any OpenAI-compatible endpoint is a config entry, not new code. Optionally run two models together (executor + planner) in separate, cache-stable sessions. Plugin-driven. MCP servers contribute tools, prompts, and resources; Extension Protocol v1 sidecars can also intercept runtime events, contribute Providers and structured UI, and ship versioned plugin packages. Cache-aware context maintenance. Startup injects a small stable environment summary, stale tool output is snipped/pruned before summary compaction, and the built-in tool schema contract is documented for regression review. Zero-friction distribution. CGOENABLED=0 single binary; cross-compile to six targets with one command. The result is a fully self-contained static binary, nothing to install on the target machine beyond the binary itself.
Choose the path that matches how you want to use Reasonix. The CLI/TUI, desktop app, and VS Code extension all use the same local Reasonix engine.
Stars: 36k
Language: Go
License: MIT
Install:
bash npm i -g reasonix # any OS; pulls the prebuilt native binary
View DeepSeek Reasonix on GitHub · More about DeepSeek Reasonix
18. Vibe Trading by HKUDS
Vibe-Trading is an open-source research workspace for turning finance questions into runnable analysis. It connects natural-language prompts to market-data loaders, strategy generation, backtest engines, reports, exports, and persistent research memory.
It is designed for research, simulation, and backtesting, and, when you choose, autonomous trading through a broker you authorize yourself (e.g. Robinhood Agentic Trading). It holds no funds and never trades outside the limits you set, and you can halt it instantly.
Shadow Account starts from your own trading records instead of a generic strategy template.
Stars: 34k
Language: Python
License: MIT
Install:
bash pip install vibe-trading-ai
View Vibe Trading on GitHub · More about Vibe Trading
19. Rag_techniques by NirDiamant
A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems.
Prompt to Production - my full course on building software with AI the way professionals do: the methods and paradigms behind reliable, efficient, modular production systems, taught systematically. 17 modules, each pairing a video lecture with a hands-on lab, from your first structured prompt to a working production system.
One npm install adds the module's AI assistant to your Claude Code, and it guides you through the tutorial as you build.
Stars: 30k
Language: Jupyter Notebook
License: Other
Install:
bash git clone https://github.com/NirDiamant/RAG_Techniques.git
View Rag_techniques on GitHub · More about Rag_techniques
20. Agentmemory by rohitg00
Your coding agent remembers everything. No more re-explaining. Built on iii engine
Persistent memory for Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, pi, OpenCode, and any MCP client.
The gist extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs, and hybrid search: agentmemory is the implementation.
Stars: 29k
Language: TypeScript
License: Apache-2.0
Install:
bash npm install -g @agentmemory/agentmemory # once — bare agentmemory on PATH
View Agentmemory on GitHub · More about Agentmemory
21. 12 Factor Agents by humanlayer
In the spirit of 12 Factor Apps. The source for this project is public at https://github.com/humanlayer/12-factor-agents, and I welcome your feedback and contributions. Let's figure this out together!
I've tried every agent framework out there, from the plug-and-play crew/langchains to the "minimalist" smolagents of the world to the "production grade" langraph, griptape, etc.
I've talked to a lot of really strong founders, in and out of YC, who are all building really impressive things with AI. Most of them are rolling the stack themselves. I don't see a lot of frameworks in production customer-facing agents.
Stars: 26k
Language: TypeScript
License: Other
View 12 Factor Agents on GitHub · More about 12 Factor Agents
22. Genai_agents by NirDiamant
Welcome to one of the most extensive and dynamic collections of Generative AI (GenAI) agent tutorials and implementations available today. This repository serves as a comprehensive resource for learning, building, and sharing GenAI agents, ranging from simple conversational bots to complex, multi-agent systems.
Prompt to Production - my full course on building software with AI the way professionals do: the methods and paradigms behind reliable, efficient, modular production systems, taught systematically. 17 modules, each pairing a video lecture with a hands-on lab, from your first structured prompt to a working production system.
One npm install adds the module's AI assistant to your Claude Code, and it guides you through the tutorial as you build.
Stars: 24k
Language: Jupyter Notebook
License: Other
Install:
bash git clone https://github.com/NirDiamant/GenAI_Agents.git
View Genai_agents on GitHub · More about Genai_agents
23. Easy Vibe by datawhalechina
Learn AI coding from zero by shipping real products. 从零开始学 AI 编程，把想法真正做成产品。
你好 · Hello · 哈囉 · こんにちは · 안녕하세요 · Hola · Bonjour · Hallo · مرحبا · Xin chào Our tutorial supports 10 languages. Let's code together! 我们的教程支持 10 种语言，欢迎世界各地的朋友一起 coding！
Have your own vibe coding story? Submit it here and inspire others! Why Easy-Vibe News Who This Is For Your Learning Paths Study Suggestions I. Beginner Entry II. Junior and Mid-Level Developers III. Advanced Developers Appendix Knowledge Base How To Learn Run Locally Other Courses Contributing & Contributors LICENSE
Stars: 20k
Language: JavaScript
View Easy Vibe on GitHub · More about Easy Vibe
24. Openship by oblien
Open-source, self-hostable deployment platform with built-in CI/CD. Point it at a repo, it builds, ships, routes, and TLS-terminates your app. Drive it from a desktop app, web dashboard, or CLI.
There's one decision to make first: how you run Openship itself (the control plane). Everything else is the same afterwards.
[!TIP] Solo? Use the desktop app. It runs Openship's control plane on your own machine only while the app is open, nothing is left running on an always-on server, nothing is exposed publicly. You only need an always-on server install once you want push-to-deploy (CI/CD), team access, or to host apps on that box, the things that need a public, always-on endpoint.
Stars: 12k
Language: TypeScript
License: Apache-2.0
Install:
bash git clone https://github.com/oblien/openship.git && cd openship
View Openship on GitHub · More about Openship
25. Cocoindex by cocoindex-io
CocoIndex turns codebases, meeting notes, inboxes, Slack, PDFs, and videos into live, continuously fresh context for your AI agents and LLM apps to reason over effectively, with minimal incremental processing. Get your production AI agent ready in 10 minutes with reliable, continuously fresh data, no stale batches, no context gap
Declare what should be in your target, CocoIndex keeps it in sync forever, recomputing only the Δ.
Run once to backfill. Re-run anytime, only the changed files re-embed.
Stars: 12k
Language: Rust
License: Apache-2.0
Install:
bash pip install -U cocoindex
View Cocoindex on GitHub · More about Cocoindex
26. Holaos by holaboss-ai
Run any agent, Claude Code, Codex, or holaOS, in one local-first workspace, over your tools, your files, and one shared memory. Frontier models built in, or bring your own keys.
Claude Code, Codex, and the built-in holaOS agent, side by side, no switching. Whichever you run, it shares the same memory, tools, skills, and apps. Use the best agent for the job without rebuilding your setup every time. No lock-in, bring the agent you already trust. Shared everything, one context, one set of tools, one workspace. Consistent results, the same skills and integrations, whatever's driving.
Context, preferences, and project history live in a single shared memory, stored locally, as plain files you can read and edit. Switch agents, close the app, come back next week: it already knows where you left off. Never start from zero, durable memory across sessions and agents. Local-first & yours, on your machine, visible and editable, not locked in someone else's cloud. Actually recallable, structured and embedded, so the right context returns when it's needed.
Stars: 11k
Language: TypeScript
License: Other
Install:
bash npm --version
View Holaos on GitHub · More about Holaos
27. Apify MCP Server by apify
The Apify Model Context Protocol (MCP) server at mcp.apify.com enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, and any other website using thousands of ready-made scrapers, crawlers, and automation tools from Apify Store. It supports OAuth, allowing you to connect from clients like Claude.ai or Visual Studio Code using just the URL.
For the best experience, connect your AI assistant to our hosted server at https://mcp.apify.com. The hosted server supports the latest features - including output schema inference for structured Actor results - that are not available when running locally via stdio.
Legacy SSE transport removed. The https://mcp.apify.com/sse endpoint has been removed in favor of Streamable HTTP. Migrate your client to https://mcp.apify.com, drop the /sse suffix from your configuration.
Stars: 8.8k
Language: TypeScript
License: MIT
Install:
bash npx @apify/actors-mcp-server --tools actors,docs,apify/rag-web-browser
View Apify MCP Server on GitHub · More about Apify MCP Server
28. Microsandbox by superradcompany
Microsandbox runs untrusted workloads inside fast, local microVMs: AI agents, user code, plugins, CI jobs, dev environments, scrapers, and automation. Hardware Isolation: Hardware-level isolation with microVM technology. Cross Platform: Runs on Linux, macOS, and Windows. OCI Compatible: Runs standard container images from Docker Hub, GHCR, or any OCI registry. Docker-Like Workflows: Familiar image, command, shell, and volume workflows. Instant Startup: Average boot times[^boot-time] under 100 milliseconds. Embeddable: Spawn VMs right within your code. No setup server. No long-running daemon. Secrets That Can't Leak: Unexploitable secret keys that never enter the VM. Long-Running: Sandboxes can run in detached mode. Great for long-lived sessions. Agent-Ready: Your agents can create their own sandboxes with our Agent Skills and MCP server.
macOS: Apple Silicon. - Linux: KVM enabled. - Windows: WHP enabled.
Warning: Microsandbox is still beta software. Expect breaking changes, missing features, and rough edges.
Stars: 8.4k
Language: Rust
License: Apache-2.0
View Microsandbox on GitHub · More about Microsandbox
29. Agentic Inbox by Cloudflare
Agentic Inbox lets you send, receive, and manage emails through a modern web interface, all powered by your own Cloudflare account. Incoming emails arrive via Cloudflare Email Routing, each mailbox is isolated in its own Durable Object with a SQLite database, and attachments are stored in R2.
An AI-powered Email Agent can read your inbox, search conversations, and draft replies, built with the Cloudflare Agents SDK and Workers AI.
Read the blog post to learn more about Cloudflare Email Service and how to use it with the Agents SDK, MCP, and from the Wrangler CLI: Email for Agents.
Stars: 7.9k
Language: TypeScript
License: Apache-2.0
Install:
bash npm install
View Agentic Inbox on GitHub · More about Agentic Inbox
30. Superagent by superagent-ai
An open-source SDK for AI agent safety. Block prompt injections, redact PII and secrets, scan repositories for threats, and run red team scenarios against your agent.
Detect and block prompt injections, malicious instructions, and unsafe tool calls at runtime.
Analyze repositories for AI agent-targeted attacks such as repo poisoning and malicious instructions.
Stars: 6.8k
Language: TypeScript
License: MIT
Install:
bash npm install safety-agent
View Superagent on GitHub · More about Superagent
31. Sensenova Skills by OpenSenseNova
The SenseNova model family plugs directly into agent runtimes such as OpenClaw and hermes-agent, with the skills in this repository extending the models with concrete, end-to-end office capabilities.
In this repository each skill lives in its own directory and declares triggers, capabilities, and execution flow through a SKILL.md file, following the Agent Skills convention.
The skills cover image generation & visualization, slide-deck (PPT) generation, Excel data analysis, and deep research, usable standalone or composed into end-to-end workflows.
Stars: 5.7k
Language: JavaScript
License: MIT
Install:
bash git clone https://github.com/OpenSenseNova/SenseNova-Skills.git --depth=1
View Sensenova Skills on GitHub · More about Sensenova Skills
32. Cloudflare Agents by Cloudflare
Agents are persistent, stateful execution environments for agentic workloads, powered by Cloudflare Durable Objects. Each agent has its own state, storage, and lifecycle, with built-in support for real-time communication, scheduling, AI model calls, MCP, workflows, and more.
Agents hibernate when idle and wake on demand. You can run millions of them, one per user, per session, per game room, each costs nothing when inactive.
Read the docs, getting started, API reference, guides, and more.
Stars: 5.6k
Language: TypeScript
License: MIT
Install:
bash npm create cloudflare@latest -- --template cloudflare/agents-starter
View Cloudflare Agents on GitHub · More about Cloudflare Agents
33. Macro by macro-inc
Macro is the all-in-one workspace for you and your team. It unifies email + messages + docs + tasks + agents + CRM into a single fast interface with shared team-level memory. Everything in your workspace is @linked and searchable so your team (and your agents) never have to switch tools.
We built Macro because we wanted a single operating system for our startup. There are many good software products, and we used them all, Slack, Linear, Notion, HubSpot, and Superhuman, but they don't work together as one system. As we scaled our last venture to ~20 people things started to break: every team got their own tools and the company was held together by MCP and Zapier. The company was not computable. It was chaotic.
Macro is a complete redesign of work software from the ground up as a single system.
Stars: 4.4k
Language: Rust
License: AGPL-3.0
View Macro on GitHub · More about Macro
34. Jupyter Ai by jupyterlab
An open source extension that connects AI agents to computational notebooks in JupyterLab.
Jupyter AI brings agentic AI to JupyterLab. It provides a native chat UI where you can collaborate with frontier AI agents, including Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode, all integrated through the Agent Client Protocol (ACP). Agents are automatically detected when their dependencies are installed, so getting started is as simple as installing Jupyter AI and the agent of your choice.
Agents in Jupyter AI can read and write files, run terminal commands, and interact with notebooks through a built-in Jupyter MCP server. A permission system gives you guardrails over agent actions, agents request approval before writing files or executing commands. You can also create multiple concurrent chats, drag and drop files or notebook cells as context, and collaborate in real time with other users connected to the same server.
Stars: 4.4k
Language: Python
License: BSD-3-Clause
View Jupyter Ai on GitHub · More about Jupyter Ai
35. Automodel by NVIDIA-NeMo
Nemo AutoModel is a Pytorch DTensor‑native SPMD open-source training library under NVIDIA NeMo Framework, designed to streamline and scale training and finetuning for LLMs, VLMs, diffusion models, and retrieval models. Designed for flexibility, reproducibility, and scale, NeMo AutoModel enables both small-scale experiments and massive multi-GPU, multi-node deployments for fast experimentation in research and production environments.
What you can expect: Hackable with a modular design that allows easy integration, customization, and quick research prototypes. Minimal ceremony: YAML-driven recipes; override any field using CLI. High performance and flexibility with custom kernels and DTensor support. Seamless integration with Hugging Face for day-0 model support, ease of use, and wide range of supported models. Efficient resource management using Kubernetes and Slurm, enabling scalable and flexible deployment across configurations. Documentation with step-by-step guides and runnable examples. One program, any scale: The same training script runs on 1 GPU or 1000+ by changing the mesh. PyTorch Distributed native: Partition model/optimizer states with DeviceMesh + placements (Shard, Replicate). SPMD first: Parallelism is configuration. No model rewrites when scaling up or changing strategy. Decoupled concerns: Model code stays pure PyTorch; parallel strategy lives in config. Composability: Mix tensor, sequence, and data parallel by editing placements. Portability: Fewer bespoke abstractions; easier to reason about failure modes and restarts. Feature Roadmap Getting Started LLM Pre-training Supervised Fine-Tuning (SFT) Parameter-Efficient Fine-Tuning (PEFT) VLM Supervised Fine-Tuning (SFT) Parameter-Efficient Fine-Tuning (PEFT) Supported Models Performance Interoperability Contributing License
TL;DR: SPMD turns “how to parallelize” into a runtime layout choice, not a code fork.
Stars: 985
Language: Python
License: Apache-2.0
Install:
bash uv venv
View Automodel on GitHub · More about Automodel
36. Pr Af by Agent-Field
PR-AF is the #1 open-source code reviewer on Martian Code-Review-Bench. It is built for deep code review, not shallow diff summaries: turn each PR into a task-specific review plan, spawn focused reviewer agents, ground findings in code evidence, challenge the results, and squeeze more useful review intelligence out of cheaper models. Run DeepSeek-class models for routine PRs, GLM-5.2 for deep open-model reviews, or Opus-class frontier models for major PRs, where PR-AF tops the benchmark by a wide margin.
On the 38 runnable Martian Code-Review-Bench PRs, PR-AF with GLM-5.2 is the #1 open-source reviewer in golden recall: 0.706 across 42 compared tools. It is ahead of cubic-v2 and every qodo, coderabbit, greptile, copilot, and devin variant in this snapshot.
strength result ------ Known bug recall 0.706 golden recall, #1 open source across 42 compared tools. More real issues found 595 independently valid findings, ~3× more than the leading commercial tools in the adjusted comparison. Open + reproducible Single open model (GLM-5.2), public results, per-PR judge verdicts, and reproduction scripts. Self-hosted API Run locally with Docker; trigger reviews by CLI, curl, CI, or other agents. Model-flexible Use cheaper models for regular PRs, GLM-5.2 for open-model CI gates, and Opus-class frontier models for highest-stakes reviews. Frontier ceiling With Opus-class commercial models, PR-AF tops the benchmark by a wide margin. Cost position About 10× cheaper per review than closed-source tools.
Stars: 640
Language: Go
Install:
bash git clone https://github.com/Agent-Field/pr-af
View Pr Af on GitHub · More about Pr Af
37. Heygen Cli by heygen-com
Make AI videos from the command line. Drive HeyGen with code, not clicks.
Full reference and examples: developers.heygen.com/cli. Coding agents, Claude Code, Codex, and others CI/CD pipelines, weekly recap videos, release-note vlogs Bulk operations, translate 100 videos in one shell loop Custom integrations, wrap it in your own tool
heygen-com/skills, one-line install for Claude Code, Codex, and other agents. Create your own avatar and generate a video in a single conversation. JSON on stdout, structured errors on stderr, stable exit codes. Self-describing. --request-schema and --response-schema return JSON Schema without auth or API calls. Non-interactive by default. Set HEYGENAPIKEY and nothing reads a TTY. Tell us how it went. After a flow works (or when you hit a bug), run heygen feedback --rating --comment ".". It sends an anonymous rating + note (no API key needed); honors the analytics opt-out. Agents should use this for bugs rather than opening GitHub issues automatically (see Reporting bugs).
Stars: 138
Language: Go
License: Apache-2.0
Install:
bash curl -fsSL https://static.heygen.ai/cli/install.sh | bash
Final thoughts on agent frameworks GitHub repos
The best agent frameworks repo is the one you come back to. Pick 2 or 3 from this list, give them a month, and keep the ones you look forward to.
Navid Moazzez
AI business strategist & AI OS builder
Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.
Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.
More GitHub repos
More repo topics
More free tools
X
Bluesky
LinkedIn
Threads
Mastodon
Instagram
TikTok
Pinterest
YouTube
Amazon KDP
Apple Books
Amazon
Substack
Spotify
Apple Podcasts
Related MCP servers & CLIs
Free AI newsletterThe most actionable AI newsletter for founders
Every week, get proven AI strategies, curated tools, and step-by-step systems to grow your audience, create better content, and build a profitable creator business.
No fluff, no filler, no BS. Just five minutes each week that might level up your online business and life.
P.S. Sign up now to get free access to my ultimate AI tools guide for creators.
