modem-dev
★ 600sideshow
The missing visual surface companion for agents - generate UI mockups, data visualizations, code explainers, and more
AI channelAI agents 
★ 590
Open-source AI agents
An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.
How to choose
Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.
Most-starred projects
2,473–2,496 of 3,668normal-computing
★ 600fuji-web
Fuji is an AI agent that lives in your browser's sidepanel. You can now get tasks done online with a single command!
SalesforceAIResearch
★ 600MCP-Universe
MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.
BruceLanLan
★ 599augur
🦉 Augur — 多智能体投资分析系统。13位虚拟投资大师独立分析，加权共识机制，Bloomberg风格Web仪表盘。
kju4q
★ 598ai-weekend-builds
AI projects to build in a weekend. For developers: requires Python or Node.js, an Anthropic API key, and comfort with the terminal. Starter code and READMEs for each project.
tldraw
★ 598tldraw-offline
A desktop app for using tldraw with local files.
memcode-in
★ 597memcode
Memcode: #1 Memory Layer for AI agents, Building Memory infra for every use case
nowledge-co
★ 597con-terminal
The Native Terminal Emulator with a builtin AI Harness
AMA-CMFAI
★ 596LAMBDA
This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html
harbor-framework
★ 595terminal-bench-science
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
FradSer
★ 593dotclaude
A comprehensive development environment with specialized AI agents for code review, security analysis, and technical leadership.
lycohana
★ 593BiliSum
为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.
Station-Sciences
★ 593bot-crossing
A video game for AI agents. Created by Jarren Rocks
SWE-agent
★ 593SWE-ReX
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
strongdm
★ 592leash
Leash by StrongDM - take your AI agents for a walk
crawlseo
★ 591crawlseo
Open-source SEO monitoring. GSC + Site Crawler + Core Web Vitals in one dashboard.
paperboytm
★ 591spool
Store, share, and resume AI coding sessions.
Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore.
matiasbattocchia
★ 590open-bsp-api
Open-source WhatsApp + Instagram Business platform
remyxai
★ 590VQASynth
Compose multimodal datasets 🎹
sharpdeveye
★ 590maestro
Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.
ramziddin
★ 589solid-skills
AI agent skill for writing senior-engineer quality code through SOLID principles, TDD, and clean architecture
spences10
★ 589mcp-sequentialthinking-tools
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
aldefy
★ 588compose-skill
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more.