Sàn agent

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls.

An agent-first task board, Mission control for your AI workforce.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

A lightweight Python framework for parallel, isolated, collaborative AI reasoning.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.

Building a Multi-Agent AI System with LangGraph and LangSmith

A Production-Ready Framework for Building Composable AI Agents

Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537

My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.

Orchestrate an entire AI dev team on 5GB VRAM. Ephemeral subagents, exact-match diffs. Single static binary, any model. Zero config, zero context bloat.

Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

Restack AI examples for Python

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills

Agent Engineer - a practical course for software engineers

Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

A Massively Parallel Large Scale Self-Play Framework

A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)