Tag: #agent
157 packages • ⭐ 829,483 total stars
Production-ready platform for agentic workflow development.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effo
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 ta
⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, m
Build and run agents you can see, understand and trust.
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need throu
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Autonomous agents for everyone
Agent Zero AI framework
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
The open-source hub to build & deploy GPT/LLM Agents ⚡️
MCP Toolbox for Databases is an open source MCP server for databases.
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
An open source, privacy focused alternative to NotebookLM for teams with no data limit's. Join our Discord: https://discord.gg/ejRNvftDp9
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Memori is agent-native memory infrastructure. A SQL-native, LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
Open-source, secure environment with real-world tools for enterprise-grade agents.
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SF
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency;
⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡️, supports Ch
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedbac
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
AgentScope Java: Agent-Oriented Programming for Building LLM Applications
An AI agent for teams, communities, and multi-user environments.
The PHP Agentic Framework to build production-ready AI driven applications. Connect components (LLMs, vector DBs, memory) to agents that can interact with your data. With its modular architecture it's
Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.
An open-source AI assistant framework with skills and agent architecture
Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Linkedin Automation Tool: Describe your product. Define your target market. The AI finds the leads for you.
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.
A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code
Humans and AI agents, building knowledge bases together. Self-hosted document annotation, version control, semantic search, and MCP.
The Context Optimization Layer for LLM Applications
Autonomous Agents (LLMs) research papers. Updated Daily.
Agents-flex is A Lightweight Java AI Application Development Framework.
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
A collection of autonomous agents 🤖️ powered by LLM.
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible codeb
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，打造你私有的垂类通用智能体。新一代AI应用设计、开发、实践平台，无需代码，轻松创建，适合各类人群，支持多种端发布及API，提供完善的
AI Agent Development Platform - Supports multiple models (OpenAI/DeepSeek/Wenxin/Tongyi), knowledge base management, workflow automation, and enterprise-grade security. Built with Flask + Vue3 + LangC
A unified workspace for local AI coding agents (Claude Code, Codex, Gemini CLI, etc.) — desktop app, standalone server, or Docker. Conversation aggregation, git worktree workflows, MCP/Skills manageme
Shell and coding agent on mcp clients
BitFun is a next-generation AI assistant with built-in Code Agent and Cowork Agent. It has memory, personality, and the ability to evolve over time. You can remotely control the desktop through mobile
A fast and minimal framework for building agentic systems
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
🤖 An AI agent framework built with Rust.
Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
OpenClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
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 Rust SSH (no OpenSSL). Smart reconnect, MCP, RAG,
Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。
🤖🌊 aiFlows: The building blocks of your collaborative AI
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
The AI agent that lives in your framework/browser
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and submits PRs
Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger restaurant
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
AIGNE DocSmith is a powerful, AI-driven documentation generation tool built on the AIGNE Framework. It automates the creation of detailed, structured, and multi-language documentation directly from yo
QuickDesk is the first AI-native remote desktop — an open-source, free application with a built-in MCP (Model Context Protocol) Server that lets any AI agent see and control remote computers.
Ultra-Lightweight, Pure Python Multimodal Agent.
A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server)
The open-source TypeScript SDK for running AI coding agents in sandboxes. One unified API — swap agents and infrastructure providers without changing your code.
Agent Sandbox is an E2B compatible, enterprise-grade ai-first, cloud-native runtime environment for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, an
A simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities in the most "Code-Centric" manner. LLM As Function, Prompt As Code. 一个简单的恰到
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
Your Very Own Agent: The Ultimate, Complete Edition
Multi-Agent workflow running into a Laravel application with Neuron PHP AI framework
Autospec is an open-source AI agent that takes a web app URL and autonomously QAs it, and saves its passing specs as E2E test code
Run AI coding agents in hardened container sandboxes.
🦾 A production‑ready research outreach AI agent that plans, discovers, reasons, uses tools, auto‑builds cited briefings, and drafts tailored emails with tool‑chaining, memory, tests, and turnkey Dock
An ntfy MCP server for sending/fetching ntfy notifications to self-hosted or ANY ntfy.sh server from AI Agents 📤 (supports secure token auth & more - use with npx or docker!)
Your personal AI knowledge system — self-hosted, agent-driven, and always private.
A comprehensive MCP server for Gradle.
🤖 Kubernetes for AI Agents. Self-hosted, production-grade runtime for orchestrating LLM swarms and autonomous agents. TypeScript-native.
Telegram MCP Server and HTTP-MTProto bridge | Multi-user, web setup, Docker and MTProto-Proxy ready
The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.
ToolAgents is a lightweight and flexible framework for creating function-calling agents with various language models and APIs.
Pan by Euraika — a self-hosted AI workspace for Hermes Agent. Chat, skills, extensions, memory, profiles, and runtime controls.
🤖 A composable framework for building AI applications.
Agent Interface Discovery
An Agent Harness crafting around your project. From Desktop, CLI, editors, chatbots, APIs — everywhere you work.
Modular multi-agent orchestration framework powered by LangGraph and FastAPI.
🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compatible with Claude Code workflows.
The Maestro App Factory: a highly-opinionated multi-agent orchestration tool for app development that emulates the workflow of high-functioning human development teams using AI agents
Deep research agent built with Neuron PHP AI framewokrk
Your smart, reliable, and friendly personal AI assistant.
A simple task management system for managing AI dev in Cursor
Automate Codex CLI tasks using OpenClaw to write prompts, approve commands, check results, and interact via terminal or Telegram.
🤖 Build and explore powerful AI agents that solve real-world tasks using tools, memory, and reasoning within a collaborative hub.
🛠️ Discover essential skills and tools for AI coding agents to enhance capabilities and streamline the development of intelligent solutions.
Agentic coding harness with persistent memory and a REPL body. Built on Ori Mnemos. Open source must win.
🔍 Empower data scientists with DeepAnalyze, a tool that leverages large language models for automated data analysis and insights generation.
🛡️ Discover essential tools and resources that leverage AI for enhancing cybersecurity, focusing on modern technologies and their applications in security operations.
Optimize websites for AI search engines with a universal TypeScript engine supporting Next.js, NestJS, WordPress, and Shopify integration.
Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.
A web component based AI agentic chat UI element which can be added in any website to turn it into an agentic app
Agent ReAct framework with cognitive planning engine — five-phase cognitive cycle with nested ReAct loops, dynamic skill acquisition, and interactive user input.
AgentPin agent pinning protocol, part of the Symbiont Agent Trust Stack
🤖 Develop enterprise AI agents with integrated tools for chat, video, image editing, and secure multi-tenant workflows.
🔍 Automate penetration testing with an intelligent agent that organizes security assessments, leveraging local LLMs and Kali Linux for effective exploitation.
🌐 Develop WebGPU-enabled Three.js applications with TSL for advanced shading, materials, and post-processing effects in your projects.
🗓️ Simplify booking with this AI service agent that processes queries, finds local options, and offers immediate slots and notifications.
Provide a local, privacy-focused AI assistant for Telegram that runs fully on your machine without sending data to the cloud.
Enable AI agents to autonomously create, evaluate, and evolve skills across any marketplace without user intervention.
Provide reliable, repository-scoped memory for AI coding agents with code citations, just-in-time verification, and stale-proof data management.
Coordinate AI agents to break down tasks, plan workflows, and delegate coding, design, and testing within OpenCode projects.
🤖 Generate secure, automated repo documentation and pull request checks with a safe-by-default toolchain for coding agents.
📋 Empower AI agents to autonomously manage projects with a filesystem-based Kanban system for efficient task tracking and documentation.
🤖 Enhance customer support with an AI chat platform that delivers intelligent, context-aware responses through a seamless full-stack solution.
🛠 Manage Codex and Claude Code skills on macOS with this SwiftUI app. Browse, import, and delete skills effortlessly while viewing detailed info.
📄 Transform your workflow with persistent markdown files for planning, tracking progress, and storing knowledge like a pro.
🛡️ Enhance code safety with Claude Code Safety Net, a tool designed to identify and mitigate risks in your codebase effectively.
📊 Analyze and visualize Model Context Protocol (MCP) traffic with RETICLE, your Wireshark-like tool for better network insights.
🤖 Orchestrate AI models like GPT and Claude for seamless collaboration in multi-agent development tasks with the Claude Team MCP Server.
⚙️ Simplify your projects with MoLi, a fast and flexible Molang interpreter in Java, designed for easy integration and high performance.
🌟 Track token consumption in real-time with MCP Audit. Diagnose context bloat and unexpected spikes across MCP servers and tools efficiently.
🛠️ Simplify your tasks with MineContext, an open-source AI tool that provides context-aware support for clarity and efficiency in work and study.
💹 Analyze major cryptocurrencies' prices, market caps, and trends using Python and the CoinGecko API for informed investment decisions.
No description
Manage and debug local Model Context Protocol servers with an easy desktop app that auto-discovers and monitors MCP instances.
Track and manage AI personality changes, rules, and memories with full version control and easy reversibility.
Automate the OpenClaw installation on macOS with a native GUI that cuts setup time from 30 minutes to 3 minutes.
Enable autonomous reverse engineering and recompilation of PlayStation 2 games using a structured OS for LLM agents with persistent memory and workflows
Automate local Chrome browsing with isolated profiles, extract content, save pages to Markdown, and run searches using CLI tools and Node.js APIs.
Analyze git code changes to generate structured review reports using flexible AI models and integrated workflows.
Manage and automate tasks in Yandex Tracker using a robust MCP integration for efficient issue tracking and project control.
Simplify AI agent deployment and management with OpenClaw-Turbo’s secure, intuitive interface optimized for Linux and Chinese language support.
Automate shell tasks using a local Ollama model that plans, executes, and fixes commands without cloud or API dependencies.
Audit projects for security, broken hooks, tests, and CI issues across 20+ languages with adaptive scoring and actionable fixes.
Implement Recursive Language Models using Deno and Pyodide to enable scalable, code-driven prompt processing with modular sub-agent calls.
Control autonomous AI agents by enforcing behavior rules to prevent unauthorized actions, improve focus, and boost execution efficiency.
Demonstrate a proof-of-concept exploit for CVE-2026-2441, a high-risk Chrome use-after-free vulnerability in the Blink CSS engine.
An AI agent system that grows your goals from seed to tree. Set a goal — Seedy observes, delegates, and tracks until done.
Rune - Discipline Engineering - Multi-agent engineering orchestration for Claude Code. Plan, work, review, and audit using Agent Teams.
AI-powered self-learning OS with I Ching philosophy | 融合易经哲学的自学型 AI 操作系统