MemTensor/MemOS
quality grade A, 95 out of 100Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
- stars
- 10k
- stars gained this week
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
3,257 results
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.
Developer Control Plane for your AI Agents
Memory that AI Agents Love!
Phistory automatically archives versioned system prompt snapshots from agent CLIs like Claude Code, Codex, OpenClaw, and Hermes.
AI agents that act as your personal venture analyst - from startup idea brainstorming to full validation and go-to-market strategy. Built for developers who'd rather validate in 10 minutes than regret in six months. Powered by Claude Code, OpenAI Codex, and Cursor.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
面向 OA、ERP、CRM、工单等企业系统快速构建智能体,让 AI 在权限、审计与治理约束下安全调用真实业务能力。Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, enabling AI to safely call real business capabilities under permissions, audit, and governance controls.
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等),7位分析师基于A股规则的辩论决策,基于TradingAgents深度改造,适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。
A CLI tool for defining and running multi-agent workflows with the GitHub Copilot SDK and Anthropic Agents SDK.
Agentic RL on Any Harness at Scale
Evaluate and improve models and agents using environments
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
基于 LLM 的极简 PID 自动调参系统 (CLI 版)
An open source distributed agent runtime
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
An open-sourced research agent system deeply rooted in your Zotero library.
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
Набор навыков для AI(ИИ)-агентов (Claude Code, Cursor, Codex и др.), помогающий охватить полный цикл разработки на платформе 1С:Предприятие 8.3. Даёт модели абстракции над XML-форматами и CLI конфигуратора, а также глаза и руки для тестирования через веб-клиент. AI skills for 1C:Enterprise 8.3.
Personal AI Toolbox
from vibe coding to agentic engineering - practice makes claude perfect
24,523 repositories in the index in total.