Sàn agent

Optimizing inference proxy for LLMs

《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.

High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.

A wonderful list of Game Development resources.

an agentic cms self-hosted on cloudflare, for podcasts, blogs, photos, videos, documents, and curated urls.

Harness LLMs with Multi-Agent Programming

AI system design guide for engineers building production AI systems and evals.

🔍 导出并模糊搜索 Telegram 聊天记录 | Export and fuzzy search your Telegram chat history

AI Agent Orchestration Dashboard - Manage AI agents, assign tasks, and coordinate multi-agent collaboration via OpenClaw Gateway.

196 production-ready AI agent templates for OpenClaw. SOUL.md configs across 24 categories. Submit yours!

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

TimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

A library of reinforcement learning components and agents

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Easiest and laziest way for building multi-agent LLMs applications.

A Python library for building AI agents that leverage the full power of Google Antigravity.

Where people and agents build in tune.

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

Maestro: Netflix’s Workflow Orchestrator

"Paper2Slides: From Paper to Presentation in One Click"

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。

👾 Open source implementation of the ChatGPT Code Interpreter