Florian

wanman. wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.

AKernel. Programmable datacenter-scale infrastructure for Agents.

kimi-code. Kimi Code CLI — The Starting Point for Next-Gen Agents

baoyu-skills. TypeScript

multica. The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

C3Flow. Python

loopy. A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

skill2gep. Distill any procedural Skill into GEP Genes and Capsules (@evomap)

textual. The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

GA-Technical-Report. Technical Report & Evaluation Datasets for GenericAgent (GA)

AgentCo-Op. Python

ClawForge. Python

DataFlow. Easy Data Preparation with latest LLMs-based Operators and Pipelines.

pie. Rust port of the pi agent harness — coding agent + LLM runtime stack

WildClawBench. An in-the-wild benchmark for AI agents in the OpenClaw Environment.

skills. Agent Skills for Google products and technologies

agent-skills-hub. Agent Skills Hub is a global library of AI agent skills that work across OpenClaw, Claude Code, Gemini, Cursor, Antigravity, and more.

agent-skills. Production-grade engineering skills for AI coding agents.

OpenCLI. Make Any Website into CLI & Use your logged-in browser by AI agent.

yoyo-evolve. A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.

halo. HALO — Your agent, on your face. An open bridge between any AI agent and smart glasses.

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

SkVM. The Language Virtual Machine for Agent Skills

a-evolve. The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

wechat-article-exporter. 一款在线的 微信公众号文章批量下载 工具，支持导出阅读量与评论数据，无需搭建任何环境，可通过 在线网站 使用，支持 docker 私有化部署和 Cloudflare 部署。 支持下载各种文件格式，其中 HTML 格式可100%还原文章排版与样式。

OpenSpace. "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/

AgentFlow. The First Unified Agent Data Synthesis Framework for Custom Agentic Task with all-in-one envrionment

multi-agent-reference-architecture. Guide for designing adaptive, scalable, and secure enterprise multi-agent systems

hermes-agent-orange-book. Hermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南

awesome-agent-evolution. A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

golutra. 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.

claude-adapter. Transform your OpenAI API into an Anthropic-compatible endpoint for Claude Code

software-agent-sdk. A clean, modular SDK for building AI agents with OpenHands V1.

codex-plugin-cc. Use Codex from Claude Code to review code or delegate tasks.

colleague-skill. 将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

evolver. The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

agentskills. Specification and documentation for Agent Skills

ClawTeam. "ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

ljg-skills. HTML

agenticdataprotocol. Protocol specification of Agentic Data Protocol

wechaty. Conversational RPA SDK for Chatbot Makers. Join our Discord: https://discord.gg/7q8NBZbQzt

GenericAgent. Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

openhands-index-results. Results for the OpenHands Index

openclaw-jina. OpenClaw Jina Plugin.

clawdbot-feishu. TypeScript

awesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AgentIF-OneDay. HTML

skills. Public repository for Agent Skills

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

EverOS. One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

agentic-ai-landscape. Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.

qwen-code. An open-source AI coding agent that lives in your terminal.

bun. Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

claude-code-proxy. Run Claude Code on OpenAI models

claude-code-proxy. Claude Code to OpenAI API Proxy

powerrag. PowerRAG: Build smarter, more accurate RAG systems with OceanBase's multi-modal retrieval.

powermem. PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.

matrix. Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.

seekdb. The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.

freecc. Use any LLM in Claude Code

OmniSQL. [VLDB' 25] Synthesizing High-quality Text-to-SQL Data at Scale. SynSQL-2.5M is the first million-scale cross-domain text-to-SQL dataset.

MemGen. MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

MemoryLLM. The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM with Scalable Long-Term Memory"

MindMap. MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

Awesome-Graphs-Meet-Agents. [Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents).

mcp-agent. Build effective agents using Model Context Protocol and simple workflow patterns

SandboxFusion. Python

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

AWorld. Search, understand, reproduce, and improve an idea with ease

OpenHands. 🙌 OpenHands: AI-Driven Development

terminal-bench. A benchmark for LLMs on complicated tasks in the terminal

xllm. A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

swe-factory. [FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

apache-website-template. Apache Website Template

Kimi-K2. Kimi K2 is the large language model series developed by Moonshot AI team

LLM-Knowledge-Boundary. Implementation of "Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation"

logtoku. Python

MemOS. Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

miniGU. Rust

RAG-Anything. "RAG-Anything: All-in-One RAG Framework"

KAG-Thinker. An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.

servers. Model Context Protocol Servers

graphiti. Build Real-Time Knowledge Graphs for AI Agents

memfuse-python. Official Python SDK for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

moonbit-docs. The docs of MoonBit programming language

memfuse. Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

excalidraw. Virtual whiteboard for sketching hand-drawn like diagrams

potpie. Context Graph for AI Native SDLC

automq. Diskless Kafka® on S3. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency. Multi-AZ Availability.

Agent-S. Agent S: an open agentic framework that uses computers like a human

Ling. Ling is a MoE LLM provided and open-sourced by InclusionAI.

eko. Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

trood. AI-powered CLI for software troubleshooting—detecting and resolving code, dependency, and configuration issues.

community. TuGraph Community

OpenManus. No fortress, purely open ground. OpenManus is Coming.

velox. A composable and fully extensible C++ execution engine library for data management systems.

DeepEP. DeepEP: an efficient expert-parallel communication library

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

gateway. A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

DeepSeek-R1.

open-r1. Fully open reproduction of DeepSeek-R1

Awesome-AI-Agents. A collection of autonomous agents 🤖️ powered by LLM.

langtrace. Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊

simple-icons. SVG icons for popular brands

github-readme-stats. :zap: Dynamically generated stats for your github readmes

kusion. Declarative Intent Driven Platform Orchestrator for Internal Developer Platform (IDP).

swarm. Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

GraphRAG-SDK. Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟

ruleset-recipes. Quickstart your use of Repository Rules with prebuilt rulesets ready to import.

autogen. A programming framework for agentic AI

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

AgentGPT. 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

LLM_MultiAgents_Survey_Papers. Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

R2R. SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

dspy. DSPy: The framework for programming—not prompting—language models

Text2GraphQuery-DataGen. Fine-Tuning Dataset Auto-Generation for Graph Query Languages.

markitdown. Python tool for converting files and office documents to Markdown.

MaxKB. 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

aisuite. Simple, unified interface to multiple Generative AI providers

WrenAI. GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

awesome-rag. Awesome-RAG: Collect typical RAG papers and systems.

tensorzero. TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

openrag. Official Code for Oᴘᴇɴ-RAG: Enhanced Retrieval Augmented Reasoning with Open-Source Large Language Models (EMNLP Findings 2024)

CoTKR. Python

itext2kg. We build KGs the way nature builds matter

RAE. [CIKM2024] Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering

RAT. Implementation of "RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation".

CRAG. Corrective Retrieval Augmented Generation

raptor. The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

filco. [Preprint] Learning to Filter Context for Retrieval-Augmented Generaton

Multi-Meta-RAG. A repository for Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata

GRAG. Python

HtmlRAG. HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems (WWW 2025)

FlashRAG. ⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

GraphRAG-Local-UI. GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

ThinkRAG. A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。

TurboRAG. Python

RuleRAG_ICL_FT. RuleRAG: Rule Meets Retrieval-Augmented Generation for Question Answering

RAGViz. Official repository for RAGViz: Diagnose and Visualize Retrieval-Augmented Generation [EMNLP 2024]

TC-RAG. [ACL Oral 2025] The official GitHub repository for TC-RAG (Turing-Complete RAG)

RAGLAB. [EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

RAGChecker. RAGChecker: A Fine-grained Framework For Diagnosing RAG

SubgraphRAG. [ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

self-rag. This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

VisRAG. Parsing-free RAG supported by VLMs

StructRAG. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

LightRAG. [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

MRAG. Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"

python-sdk. The official Python SDK for Model Context Protocol servers and clients

libro. A Notebook with Flexible Customization and Easy Integration.

Marco-o1. An Open Large Reasoning Model for Real-World Solutions

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

lyric-runtime. Lyric: A Rust-powered secure runtime for AI-Agent.

flask. The Python micro framework for building web applications.

LLM-Agent-Survey.

chat2graph. Chat2Graph: Graph Native Agentic System.

CodeFuse-muAgent. An Innovative Agent Framework Driven by KG Engine

translation-agent. Python

kotaemon. An open-source RAG-based tool for chatting with your documents.

fast-graphrag. RAG that intelligently adapts to your use case, data, and queries

project-sid.

dagrs. High-performance, Rust-based asynchronous task programming framework implementing Flow-Based Programming for scalable directed acyclic graph (DAG) task orchestration

OlaGPT. Official implementation for "OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities" (keep updating)

auron. The Auron accelerator for distributed computing framework (e.g., Spark) leverages native vectorized execution to accelerate query processing

GraphRAG-Survey.

GPTSwarm. 🐝 The First Self-Improving agents with RL / Prompting Optimization

paper-qa. High accuracy RAG for answering questions from scientific documents with citations

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

AgentRE. Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

RWKV-LM. RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

RWKV-RAG. RAG SYSTEM FOR RWKV

petercat. A conversational Q&A agent configuration system, self-hosted deployment solutions, and a convenient all-in-one application SDK, allowing you to create intelligent Q&A bots for your GitHub repositories

triton. Development repository for the Triton language and compiler

hypertrons-crx. A browser extension for insights into GitHub, Gitee projects and developers.

10x. ⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

groovy-graphdb. Groovy

dbgpt-tugraph-plugins. TuGraph plugins python package used in DB-GPT.

G6. ♾ A Graph Visualization Framework in JavaScript.

brew. 🍺 The Package Manager for Everywhere

vsag. vsag is a vector indexing library used for similarity search.

github-roast. Spicy GitHub Roast 🔥

Embodied_AI_Paper_List. [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

nebulagraph-ai. (Pre Alpha)NebulaGraph AI High-Level API, do Graph Algo, Analytics in 4 lines of code.

prompt-poet. Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

jdk. JDK main-line development https://openjdk.org/projects/jdk

FlameGraph. Stack trace visualizer

RAG-Survey. Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

Autogen_GraphRAG_Ollama. Microsoft's GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG Superbot

HippoRAG. [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

graal. GraalVM compiles applications into native executables that start instantly, scale fast, and use fewer compute resources 🚀

wildfly. WildFly Application Server

gravitino. World's most powerful open data catalog for building a high-performance, geo-distributed and federated metadata lake.

code2flow. Pretty good call graphs for dynamic languages

awesome-knowledge-graph. 整理知识图谱相关学习资料

Awesome-Graphs. Think Graphs Like A Graph.