Browse all 20,362 AI agents

The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .

A modular Python package for real-time agent message streaming and filtering, designed for LLM/AI agent systems. Provides composable stream filters and streaming utilities for RabbitMQ and more.

Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.

🐝 Dynamic multi-agent collaboration system with emergent roles, cognitive alignment, and deliverable-driven output. Make AI collaborate like an elite consulting team.

An Agent swarm that mimics the closed source one of kimi k2

A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems

Desktop multi-agent orchestrator for the Claude Agent SDK. Command a hierarchy of AI agents — chiefs, specialists, advisors, workers — with CodeGraph code intelligence, Claude-Code-grade context compa

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend

A toolkit for developing AI agents, including agent-debugger: Terminal debugger for LangGraph & LangChain agents. Debug LLM agents with state inspection, tool calls, semantic breakpoints, and Python p

A library of multi-agent teams using Ejentum cognitive harnesses. Drop-in deployable agent teams for code review, evaluation, and more.

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/Open

University project of the Agent Technology module which consists in creating an expert system and a multi-agent system based recommendation system and implementing them in a web application using a RE

MCP tool server for AI coding agents -- encoding-aware file tools, binary analysis, DAP debugger, SSH/SFTP, process memory, and more

Agent Tool Protocol

Collection of resources to help AI agents build better with Sanity.

🏘️ Give your AI agents a life — a pixel-art town where OpenClaw agents live, work, and share moments on social feed.

OpenTelemetry-native, local-first observability for AI agents. DuckDB on disk, Next.js viewer on localhost, no SaaS. Adapters for Anthropic, OpenAI, LangGraph, AutoGen, CrewAI, and Claude Code's nativ

OKX trading MCP server — connect AI agents to spot, swap, futures, options & grid bots via the Model Context Protocol.

Local dashboard for Claude Code, Codex, OpenCode, OpenClaw and Qoder session history, token usage, cost tracking, tool calls and subagent replay.

agent trust Trust Game Demo

Run AI SDK agents in a terminal UI.

agent ui

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Cl

👁️ The visual layer for CLI coding agents. Pipe JSON → interactive native UI → modified JSON back. Like fzf, but for visual decisions.

TypeScript SDK and CLI for building AI agents that autonomously join, listen, and speak in X/Twitter Spaces. Supports multiple LLM providers (OpenAI, Claude, Groq), speech-to-text (Whisper, Deepgram),

⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 | Approve your AI coding agent's risky actions from your Apple Watch, get buzzed when tasks finish

Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.

A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more.

An open standard for multi-agent workflows -- from scripted pipelines to self-organizing teams. Declarative. Runtime-agnostic. Portable.

Engineering workflows for AI coding agents or flesh engineers. It helps absorb silent base-model quality drift.

All your projects in one workspace. Run multiple CLI agents in parallel across different repos. Runs on your hardware, accessed through the desktop app or the browser. Bring your own plans.

Control plane that runs AI coding agents (Codex, Claude Code, Gemini, OpenCode, Grok, Cursor) as disciplined contributors: each task gets an isolated git worktree + Docker Compose stack, profile-drive

HR Configurable Workspace

The open world for autonomous AI agents on Solana Trade. Build. Fight. Earn. Explore. Connect your AI agent to a persistent shared world. Trade real SOL, build structures, form guilds, fight for terri

ICLR 2026: Agent-X Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks

Your AI Agent for Academic Research

Agent Zero AI framework

Provides configurations for agent-initiated messaging capabilities.

Backend server for AGI OS - Awesome Gamer Insight Orchestrating System

A composable AI agent framework for .NET.

Self-hosted private AI agent workspace for local and OpenAI-compatible models. Chat, code, use tools, manage memory/skills, route tools intelligently, and deploy Docker-backed apps from one browser UI

2D to 3D CAD Conversion Using Coding Agent

Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.

Agent4GoMicroservice: A Go-based multi-agent microservice solution. Combines LLM tool-calling, Eino workflow orchestration, and Milvus-powered RAG for cross-domain automation (business tasks + knowled

Open source Node.js AI agent runtime framework for building AI agents and tooling infrastructure.

Open Source AI Agent Framework in Python

Connect AI agents across any network — zero config, encrypted, skill-based routing

AgentAPI is a lightweight Python framework for building agentic AI backends and chatbots with minimal configuration. It provides a plug‑and‑play developer experience for integrating multiple LLM prov

Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.

open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act, le

Official Implementation for the Paper [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://arxiv.org/abs/2602.03955)

AgentAz™ — an open, design-time governance specification for AI agents, with 60 reference blueprints. Documents each agent's Trust Level, worst-case action, and boundaries.

AI native API/MCP framework for the agent era. Built with agents, for agents.

Examples to demonstrate configuration and usage of basic agents and workflows from Microsoft Agent Framework, supporting thread persistence and structured output.

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Spend control & billing for AI agents. Prevent API bill shock with 3 lines of code. Supports OpenAI, Claude & MCP.

Visualize the process and LLM functions call logs of AI agents development, including multi-agent, autonomous agents environments, etc.

🧠 Brain-inspired cognitive architecture plugin for AI agents — persistent memory, evolving personality, neurochemistry-driven mood, learning from mistakes. Fully local on OpenClaw.

Make any API agent-ready in 30 seconds. The open-source bridge between APIs and AI agents.