agent

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al...

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

AI writes code. This automates everything else · 19 plugins, 47 agents, and 40 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

Blades is a Go-based multimodal AI Agent framework.

Practical LangChain patterns and implementations for real-world LLM applications. 极客时间：LangChain实战课 - 这是LangChain框架早期设计的一系列重点模...

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observabilit...

Nuwax Agent OS - The world's first universal agent operating system, building your private vertical general-purpose agent. 通用智能体操作系统，打造你...

Science-Star: A Platform for Building, Extending, and Experimenting with Scientific Agents.

A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.

[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

OpenYak — open-source local AI agent for Windows, macOS, and Linux. A private, BYOK alternative to Claude Code, Claude for Work, and OpenAI Codex with...

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing pr...

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent...

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

Figma MCP for free users — no rate limits, full read/write, text to designs, designs to code

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" b...

An open source implementation of code execution with MCP (Programatic Tool Calling)

End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向...

Empower agents with professional capabilities in specific fields (such as full-stack development, complex logic planning, multimedia processing, etc.)...

Playing Mario with Deep Reinforcement Learning

Java Agent is a Java application probe of DongTai IAST, which collects method invocation data during runtime of Java application by dynamic hooks.

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI...

An agent benchmark with tasks in a simulated software company.

Automatic view component renderer by AI agent

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 L...

The official repo of EurekaClaw

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved b...

ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and...

A clean, modular SDK for building AI agents with OpenHands V1.

🦞 OpenClaw 核心架构的极简复现，涵盖 sessionKey 会话域、队列串行、工具化记忆检索、按需上下文加载、可扩展技能与主动心跳唤醒机制

A Cursor-inspired AI assistant for Obsidian that offers smart autocomplete and interactive chat with your selected notes

One-click backup & restore for OpenClaw instances — workspace, credentials, skills, agent history. Powered by MyClaw.ai

Shell and coding agent on mcp clients

The AWS Secrets Manager Agent is a local HTTP service that you can install and use in your compute environments to read secrets from Secrets Manager a...

The open context engine for AI agents support 15+ data sources. Built on Rust and Apache DataFusion.

Open-source, customer support platform with fully customizable AI support agents for developers / startups shipping SaaS.

Cursor Custom Slash Commands

Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.

Latest Advances on Long Chain-of-Thought Reasoning

Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉

All-in-one terminal workspace — local shells, SSH, SFTP, remote IDE, AI agent, and file manager in a single native binary. Built with Tauri 2 and pure...

A proxy server for multiple ollama instances with Key security

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

Realm is a cross platform Red Team engagement platform with a focus on automation and reliability.

Hardware-based SSH/GPG/age agent

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

Collects system metrics from DigitalOcean Droplets