Browse all 21,375 AI agents

One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and deliver

The self-improving all channels AI agent. Self-healing. Fully autonomous. Single Rust binary.

Opendata.cat MCP Server - Servidor MCP (Model Context Protocol) per interactuar amb les dades obertes públiques de diferents organismes Catalunya. Creat per Opendata.cat

Rust-native MCP server for Office document processing (Excel, Word, PowerPoint). Sub-millisecond, local-first, open source.

Your Open Autonomous Android Agent — A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate r

Give your AI agent accurate economic data. 330K indicators from FRED, World Bank, IMF, Eurostat & more. MCP server + web UI.

A Model Context Protocol (MCP) Server to assist you on various openEHR related tasks and APIs

An event-sourced knowledge runtime for coding agents.

A flexible framework for AI agents that separates workflow logic from search strategy. Based on https://arxiv.org/pdf/2512.03571 Also read https://asari.ai/blog/encompass

Self-hosted multi-user AI assistant with agents, memory, scheduler, and a built-in dashboard. Works with Claude, OpenAI, Ollama, LM Studio, and more.

OpenEvidence MCP: open-source browser-session MCP server for human and AI-agent medical workflows

OpenExCard - Open Agent Execution Cards: A workflow framework for AI agents

Open-source Agent Operating System

A Swift framework for Final Cut Pro FCPXML processing built with AI agents

😼 OpenFelix — Voice-first AI agent for macOS. Runs local LLMs on Apple Silicon via MLX. Supports all OpenClaw skills. Claude, GPT, or fully offline.

One-stop quant-trading AI agent — research · strategy · backtest · paper trade from one prompt. Works in Claude Code, Cursor, and 20+ AI agents via MCP. 60-second install with auto Skill registration.

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, call-level, no model on the hot path

LLM-powered OpenFOAM MCP server for intelligent CFD education with Socratic questioning and expert error resolution

Multi-agent orchestration framework for AI applications - build, deploy, and manage AI agents across the full lifecycle with Forge, Conveyor, Shield, and Watchtower modules

OpenFused is a shared memory and messaging layer for AI agents, built on plain files. It gives agents persistent context, signed mail, and peer sync without locking them into a proprietary runtime.

A framework-agnostic, git-native standard for defining AI agents

Drop-in OpenAI-compatible API gateway for Qwen AI models. Use your Qwen account (chat.qwen.ai) as a free AI API provider in any OpenAI-compatible client — Cursor, Continue.dev, Claude Code, VS Code Co

Open-Source Generative UI Framework

A persistent, daemon-based multi-agent system that leverages opencode to automatically discover, plan, implement, and review code changes across a codebase.

Build organizations of OpenClaw agents that coordinate work across Codex, Claude Code, Cursor, OpenCode, and more 🐐 🐐 🐐

Hire a phone to do your growth work: An open-source AI mobile operator that automates Android apps for growth, research, social media, and long-running phone-based workflows.

OpenHarness is a long-term, fully autonomous AI agent execution framework for OpenClaw built on the concept of Harness Engineering. It enables your AI to work tirelessly for you 24/7 with just a singl

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.

OpenHuskyAgent

OpenTelemetry Instrumentation for AI Observability

💼 One MCP server to search job boards and company career sites

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

MCP server for University Learning Management System (KLAS).

Framework-agnostic Lossless Context Management SDK for AI agents. Unbounded memory, bounded context. LangGraph · CrewAI · AutoGen · Google ADK

Secure autonomous AI agent framework. Build an AI team by describing what you want. Run entire departments with agents that can do everything a human can do.

Lightweight AI agent runtime for Raspberry Pi and homelabs, built around deterministic skills and local LLMs.

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers,

Open, self-hosted runtime for real-time voice agents — a Rust recreation of ChatGPT's Advanced Voice Mode (GPT-Live), model-neutral

The League of Agents (OpenLOA): An extensible orchestration framework for creating personalized AI agents with modular tools and custom interfaces. (智能体联盟 (OpenLOA)：一个可扩展的编排框架，用于通过模块化工具和自定义界面创建个性化 AI

OpenLoop is a universal loop engineering framework for AI agents, enabling play-test-fix-verify-improve cycles with logs, heartbeats, baselines, guardrails, and auditable stop conditions.

openlore provides persistent architectural memory for AI coding agents by turning codebases into queryable knowledge graphs featuring static analysis, living specs, automated drift detection, and grap

AI agent framework, written from scratch (not based on openclaw), focused on stripping it down to the bare necessities, optimizing token count, reducing security risks. modular so you can enable only

AI coding toolbar for any web app — run npx openmagic, select any element, describe a change, review the diff, and it edits your real source code (verified & self-correcting). Visual element editor +

Lightweight multi-platform AI agent chat framework. Connect multiple LLMs to Feishu/WeCom/QQ with composable tools, long-term memory, scheduling & browser automation. | 轻量级多平台 AI Agent 聊天框架，连接多个 LLM

OpenManus Go is a Go language rewrite of OpenManus, supporting multi-agent systems, tool calling, flow control, and secure sandboxing.

Open, self-hostable organization-of-record for AI agents — the accountable layer above any framework. Autonomy is earned, not assumed.

OpenMAS is an open source multi-agent simulator based in Matlab for the simulation of decentralized intelligent systems defined by arbitrary behaviours and dynamics.

Turn any openapi file into an mcp server, with just the tools you need.

All in one vscode plugin for mcp developer

A content-creation agent runtime for reproducible multimodal production — projects, workflows, skills, provenance.

🧠 AI Agent Memory Management Framework - Dual-layer memory architecture with smart classification and automatic extraction

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team colla

OpenMolt lets you build programmatic AI agents in Node.js that think, plan, and act using tools, integrations, and memory — directly from your codebase.

World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.

Interactive CLI/TUI for OpenNext.js + Cloudflare Workers. Automated setup, deployment, validation, and MCP server for AI-assisted development.

A notebook app built with Rust + Flutter and AI tech stacks. Support semantic search, mcp, importing webpages and more.

你的 IT 工作助手，自主进化、伴你成长，专为中国团队打造的开源Agent

A personal AI workforce that runs on one Resident. It handles what it can, delegates the rest to Workers, and a System Governor makes the whole thing smarter over time — without trusting self-report.