Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Autonomous and multi-agent systems, agent frameworks, planning and tool use.
Signals: ai-agent, ai-agents, agents, autonomous-agents, agent-framework, multi-agent, multi-agent-systems, agentic
3,218 results
AI agent tooling for data engineering workflows.
AI 课程笔记：langchain / langgraph / python / vibe coding
Write research paper and literature review drafts with an open-source Python engine that checks citation DOIs against scholarly databases. Export PDF, Word, or LaTeX.
Agent Skills for Firebase
[EMNLP 2026 Demo] "PalmClaw: A Native On-Device Agent Framework for Mobile Phones"
An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .
Where people and agents build in tune.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
AI agent to evaluate and score resumes.
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类
Gym-Anything: Turn any Software into an Agent Environment
Open Source Agentic Security Scanner
An AI-powered Scientific Writing Workflow: Agent skills for drafting, revising, auditing, and resubmitting Nature-style journal manuscripts.
OctoTools: An agentic framework with extensible tools for complex reasoning
An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
PlanWeave is a file-backed loop engineering system for long-running coding agents. It turns fuzzy plans into claimable tasks, routes them through implementation and review agents, records every run, and keeps the loop recoverable.
🚀 Writing Agent：开源多智能体对话写作助手。独立 Windows 客户端，无需 Claude Code，配置模型 API 即可使用。写作导演协同主笔、读者审校及“去 AI 味”等专家，从选题到成稿逐步共创，通过自然对话确认与修改。工程化 Harness 管理阶段确认、版本保存与中断恢复。内置 99 项模型连接预设，支持 DeepSeek、智谱 GLM、MiniMax 等及自定义接口；可选 Parallel 免费搜索与 Tavily 辅助事实核查，支持本地项目、版本追溯和排版导出。目前为公开 RC 测试版，原版 Claude Code Skills + Subagents 仍保留，部分能力尚在迁移，欢迎体验反馈。
Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based
Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claude Code
Open-source Wyckoff trading agent and AI stock screener for volume-price analysis, A-share screening, CLI workflows, and MCP tools.灵感来自秋生trader @Hoyooyoo
24,542 repositories in the index in total.
