AI Agent Tools

The agent that grows with you

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

AI that sees your screen, listens to your conversations and tells you what to do

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

Web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

Framework for building AI-powered applications and agents with TypeScript.

Autonomous agents for everyone

Personal AI assistant with memory and proactive reach-outs.

IDE for building with coding agents.

The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

Git workflow tool that captures AI agent sessions and indexes them alongside commits.

The open source coding agent.

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

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

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

Open-source infrastructure for computer-use agents, with sandboxes, SDKs, and benchmarks.

Orchestrate coding agents remotely from your phone, desktop and CLI

Open-source React and TypeScript library for building AI chat interfaces.

🙌 OpenHands: AI-Driven Development

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, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Tool for managing multiple coding agents from web or TUI.

Open-source control plane for managing AI agents, tools, and usage.

Open-source agentic development environment for running multiple coding agents in parallel.

CLI to control iOS and Android devices for AI agents

The agent engineering platform

Build, run, manage agentic software at scale.

A lightweight, powerful framework for multi-agent workflows

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Teams-first Multi-agent orchestration for Claude Code

Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Open Source framework for voice and multimodal conversational AI

Open-source backend platform for agentic coding with database, auth, storage, compute, hosting, and AI gateway components.

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

Persistent autonomous terminal agent with local tools and web browsing.

Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord

Platform for running and managing MCP servers.

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

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

MCP Toolbox for Databases is an open source MCP server for databases.

Smart Model Routing for Personal AI Agents. Cut Costs up to 70% 🦞👧🦚

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

Agentic proxy for AI agents and MCP servers.

Persistent personal agent server with multi-provider LLM support.

A unified TypeScript SDK for building chat bots across Slack, Microsoft Teams, Google Chat, Discord, and more.

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

An open-source alternative to Claude Cowork built for teams, powered by opencode

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

Chat with your data - with memory, rules, and observability built in. Deploy in 2 minutes

Opinionated open-source stack for AI agent automation with tools, services, CLI, and API components.

Agent framework for collaboration between AI agents.

Spec-driven development for AI coding assistants.

Universal memory layer for AI Agents

Local AI anywhere, for everyone - LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

Zoo Code gives you a whole dev team of AI agents in your code editor.

A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.

Open-source AI coworker, with memory

Desktop app for isolated, parallel agentic development.

Open-source agent operating system written in Rust.

Open-source gateway that proxies requests, injects credentials, and wraps REST APIs as MCP tools.

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Private AI platform for agents, assistants, and enterprise search.

Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

Native terminal emulator with a built-in AI harness.

Open-source platform layer for AI agents in production.

Native AI gateway and LLM proxy built in Rust.

An open-source AI agent that brings the power of Gemini directly into your terminal.

AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Single interface for working with LLM providers.

Ghost in your shell.

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.

SPEC-first agentic development kit for Claude Code with agents, skills, and quality gates.

Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.

AI development platform with cloud development environments and model support.

Open source no-code MCP server for AI-native API access.

Markdown-first long-term memory infrastructure for AI agents.

LlamaIndex is the leading document agent and OCR platform

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

Local knowledge graph for code review and codebase understanding.

Office suite built for AI agents to read, edit, and automate documents and spreadsheets.

Self-evolving daemon that compresses large repos into concise agent context.

Self-hosted orchestration layer for autonomous AI agent teams with shared memory, heartbeat scheduling, vault-first secrets, and task delegation.

Open-source AI platform for enterprises that cannot send data to the cloud.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Personal AI sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels.

AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

Framework for building multi-agent LLM applications.

AI agent that can spend USDC autonomously to complete work.

Enterprise-grade agentic workflow platform for building super agents.

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Shared memory for coding agents.

Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.

Plan-first AI workflow plugin with task tracking and worker subagents.

Operational layer for coding agents with memory, validation, and feedback loops.

Universal CLI hub and AI-native runtime for websites, Electron apps, and local tools.

Governed CLI framework for deterministic, auditable AI agent workflows.

Multi-agent system framework for complex tasks.

Secure runtime for autonomous AI agents.

End-to-end voice AI orchestration platform for real-time conversational agents.

The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.

Open-source agent eval platform for real-world tasks and regressions.

Agent-native flight search and booking.

Portable open-source operating system for agents built on WebAssembly and V8 isolates.

Open-source middleware for Claude Code with sharper context and fewer tokens.

Open-source agent harness platform for self-hosted, multi-provider AI agents.

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

Self-evolving AI agent framework with a microkernel architecture.

Native backend for MLX Studio workflows.

Ghost in your shell.

Open-source framework for conversational voice AI agents

Provides the right context to your agents.

⚡️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 ChatGPT, Claude, Llama, Ollama, HuggingFace, etc., chat bot demo: https://ai.casibase.com, admin UI demo: https://ai-admin.casibase.com

Agent data plane that gives AI agents data autonomy.

OpenClaw alternative in your pocket.

Local-first AI agent runtime for workspaces and long-running tasks.

Plug and play AI agents for any domain

Open source alternative to LangGraph Platform (now LangSmith Deployments) - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.

Your Friendly Open-Source Gen-AI Platform

Extended Ralph loop for autonomous AI-driven plan execution.

Local-first AI operator platform for governed, auditable workflows.

Spec-first AI development with specs, plans, tasks, and autonomous builds.

An open-source AI assistant framework with skills and agent architecture

An autonomous agent that conducts deep research on any data using any LLM providers

Your easy to use, always-on AI workforce 👾

3D AI agent platform for the browser with embeddable web components, memory, tool use, and MCP support.

Open-source AI agent platform for building, deploying, and managing AI teammates.

Self-hosted autonomous agent OS for consumer hardware.

Open source cowork desktop for productivity.

AI Coding Agent Orchestrator — loops until done

Self-hosted open-source AI gateway for LLM providers, databases, and files with RAG and guardrails.

open-source agentic AI data assistant for the next generation of AI + Data products.

Keyboard-first menubar app to monitor and jump between AI coding sessions.

LSP-powered code intelligence for AI agents. Speculative execution, blast-radius analysis, and enforced multi-step workflows. 50 tools, 20 skills, 30 languages.

Agent dashboard hub for monitoring and controlling AI coding agents.

Grounded Docs MCP server for documentation retrieval.

Self-hosted AI agent platform for running enterprise-ready agents locally.

Bionic is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

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 20+ tools, 100+ models via OpenRouter, MCP, and Ollama. Free, MIT-licensed, no telemetry.

Agentic SDLC with local LLMs.

Multi-AI-role collaboration and planning orchestration.

Local-first AI execution runtime for secure automation and tool use.

Biomedical Model Context Protocol server for healthcare data integration.

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

Intelligent automation and multi-agent orchestration for Claude Code

An AI prompt optimizer for writing better prompts and getting better AI results.

AI coding agent platform for shipping features faster.

The context development platform. Store, enrich, and retrieve structured knowledge with graph-native infrastructure, semantic retrieval, and portable context cores.

MCP server for Proton Mail with permission-gated agentic email access via Proton Bridge.

Open-source troubleshooting atlas for RAG, agents, and AI workflows.

Open-source AI agent orchestration platform for autonomous multi-agent systems.

Terminal-first AI coding agent with observable runs and daemon support.

An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack

Open-source dashboard for managing autonomous AI agents in real time.

Dashboard for running and coordinating multiple AI CLI agents.

Universal MCP gateway for AI agents.

Open-source MCP server connecting Telegram to AI assistants.

Lightweight coding agent for orchestrating work through multi-agent collaboration.

Tool for giving AI agents real USDC wallets on Base L2.

AgentNetworkProtocol(ANP) is an open source protocol for agent communication. Our vision is to define how agents connect with each other, building an open, secure, and efficient collaboration network for billions of intelligent agents.

Context management for the agentic engineering era.

Open-source TypeScript framework for building AI workflows and agents.

Build autonomous AI agents with adaptive intelligence and emergent behaviors.

Declarative governance framework for AI-augmented software development lifecycles.

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

Portable configuration layer for AI agents and coding workflows.

Agent framework built on Claude Code and Obsidian for coordination, automation, project management, and cross-chat memory.

Open-source AI collaboration suite and multi-agent automation platform.

Semantic code search MCP server for AI agents.

Automatos AI: Open-source platform for advanced context engineering and multi-agent orchestration in enterprise automation. Built on frontier research in RAG, vector embeddings, cognitive tools, emergent symbols, and neu

Persistent codebase memory for AI coding agents.

Remote MCP server connecting Jira and Confluence to LLMs and agent platforms.

AI-powered ServiceNow development platform with MCP tools and model support.

Prompt development and orchestration system powered by Supabase and n8n.

AI assistant for trades, focused on contractors and field work.

Autonomous agent framework for Elixir built for distributed, autonomous behavior and dynamic workflows.

Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

Open-source session management platform for Claude Code.

A .NET library to build AI agents with 30+ built-in connectors.

Open-source platform connecting AI assistants to government open data.

The protocol + runtime for agentic work. Deploy agents, workflows, and scripts as MCP, API, web, or CLI — production-grade, in 30 seconds. Open source.

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode

Semantic code search engine.

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Giselle: AI App Builder. Open Source.

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

Open-source self-hosted cloud agent cluster for collaborative AI agents.

TypeScript framework for building AI agents with LangChain, Vercel AI, and native integrations.

Self-improving agents through iterations.

Open-source voice AI evaluation platform for testing and comparing voice agents.

Open-source AI workforce platform with tasks, tools, browsers, and email.

Hexabot v3 is an automation platform with first-class AI capabilities, combining workflows, actions, and conversational channels in one runtime.

Captures your web app's complete development timeline: server logs, browser events, console messages, network requests, and more.

Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, and semantic search.

Monitor and control multiple AI agents running in parallel.

Compact AI agent for GitHub issues and command-line coding tasks.

Memory and workflows for Claude Code across sessions.

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval.

AI agent memory.

Client for OpenClaw that connects the local claw workspace.

Query Engine for AI Analytics: Build self-reasoning agents across all your live data

A shell-first terminal where an AI agent is one keystroke away.

CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

Workflows and skills for people and agents collaborating on open-source software.

AI-powered app to chat with public GitHub repositories and developer profiles.

Universal memory layer for AI agents.

TypeScript MCP framework for AI agents.

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

Agent OS for building private vertical general-purpose agents.

ChatOllama is an open source agentic app for running AI agents across local and hosted models.

Open-source local workbench for multi-agent software development.

Open-source AI agentic harness for property management operations.

Open-source AI chat platform with multi-provider support, voice calls, WhatsApp integration, and video chat.

Platform for enabling long horizon workflow automation using teams of AI assistants.

Security-first platform for AI agents.

Open-source multi-agent platform for coordinated software engineering workflows.

Installable autonomous AI CEO platform with strategy, skills, and overnight autonomy.

Agent gateway for external tools.

SQL query engine for querying apps, APIs, files, and SaaS data sources.

Autonomous multi-agent AI platform with DAG execution and workflow scheduling.

Spec-first, TDD-enforced development pipeline for Claude Code.

One interface for your whole data stack, with built-in safeguards and a simpler workflow for your team. Written in Rust.

Enterprise search, semantic navigation, and chatbot platform.

Extendable code review and QA agent.

Workspace-first multi-agent coordination platform with specs, kanban orchestration, and MCP integration.

superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.

Open-source multi-agent AI workforce platform with collaborative agents.

Production-ready AI Agent Workflow System for Claude Code.

Deploy serverless AI workflows at scale. Firebase for AI agents

Open-source agentic build system for generating and verifying code.

⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI

Self-hosted AI agent that thinks, acts, and improves itself.

Orchestration layer for AI coding agents.

Browser-based AI agent platform for professionals and small business owners.

Production-ready MCP server framework for AI agent infrastructure.

Self-hosted personal AI agent platform with a desktop installer and multi-agent features.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.

AI agent development platform with knowledge and workflow features.

Open-source code review platform.

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

Workflow automation platform connecting apps, services, and APIs.

AI-first search and answer engine for workplaces.

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

Index and search Claude Code sessions for quick retrieval of solutions and insights.

Enhance agent memory with smart categorization, automatic extraction, and multi-IDE support.

Continuous personality for your agents.

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

LLM Frontend for Power Users.

Memory operating system for AI agents with persistent memory and semantic search.

An open-source AI assistant answering questions using your docs

A bio-inspired cognitive memory engine - a new paradigm for Graph RAG.

Desktop client for harnessing Claude Code, Codex, and other agent runtimes.

A privacy-first AI assistant that works seamlessly during meetings.

Fetch source code for npm packages to give AI coding agents deeper context

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Open-source AI cloud platform for self-hosted infrastructure management and multi-agent orchestration.

Local-first autonomous agent operating system with MCP tools and memory.

Open-source alternative to coding agent desktops and agentic software workspaces.

AI computer use powered by open source LLMs and a desktop sandbox.

Agent orchestration dashboard - Kanban UI for any work tracker and any agent runtime.

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Open-source self-hosted AI workforce with meeting-to-work execution.

Security-first platform for AI agents.

Open-source Agent Team framework for Claude Code, built for solopreneurs. One command spins up the whole agent team — all working in perfect sync.

Open-source agent platform.

Local-first desktop agent runtime for turning business goals into executable and auditable workflows.

Open-source brain viewer and project management for AI agents.

A visual playground for agentic workflows: Iterate over your agents 10x faster

Open Source Library for Automated Optimization of AI Agent Workflows

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Open source platform for task-driven autonomous AI agents.

Local-first AI workspace with agents, docs, email, calendar, and terminal.

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Open source operating system for AI-powered businesses.

Browse the MCP registry and install servers into Cursor, Claude Code, and VS Code.

Visual feedback tool for agents.

Open-source agent matrix runtime for running human-in-the-loop agents.

Open-source persistent operator runtime with scheduling and retrieval.

Modular cloud-native AI agent platform designed for extensibility and automation.

Platform for deploying fleets of AI agents on local machines.

Desktop client that bridges agents to chat platforms.

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.

Open-source workspace for autonomous AI teams.

Remote MCP server for any GitHub project.

Sovereign, self-hosted memory layer for AI applications.

Open-source Claude Code alternative and agent framework.

Open-source MCP server connecting legal document management systems to AI assistants.

Scaffold a Claude AI agent that pays per API call with USDC.

Open-source platform for building and running AI employees with a single prompt.

A private, open-source, on-device AI assistant.

Open-source document chat platform with semantic search and RAG.

Open-source MCP server for independent consultants with proposals, invoices, and time tracking.

Visual AI agent builder and deployable runtime stack.

Open-source AI agent command center for Claude Code agent teams.