Browse all 22,308 AI agents

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semantic layer. 20/20 on an 80-table Spider run. Built-in tracing

[ESWC '24] This repo is official implementation for the paper "Towards Harnessing Large Language Models as Autonomous Agents for Semantic Triple Extraction from Unstructured Text"

基于 UbD 逆向设计的教材写作 skill 组合（支持 Claude Code / Codex CLI）：教学定位 → 五件套 gate → 章节树 gate → 逐章写作，例题真算验证、中断可续写，面向数学/物理/计算机等 STEM 学科成体系教材写作

Access OpenAI's ChatGPT and Dall-E 2 through text messaging

🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing

Telegram channel and group reader MCP Server

Telegram user console client and archiver

This is the official implementation of [AAAI'25 Oral] accepted paper: Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems.

Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.

67 hand-picked Thai-language Claude Skills for working professionals and students 🇹🇭 · Free, open source

Autonomous AI agent for Home Assistant with multi-model routing, persistent memory, and an OpenAI-compatible API

Open-source agent harness platform. Native Rust, multi-provider, runs on your own machine. Sovereign by design.

The 3rd Eye is a modular OSINT (Open Source Intelligence) framework built on an agent-based, graph-driven architecture. It automates public information discovery, identity correlation, and exposure a

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

AI Engineer capstones progressing from optimization and deep learning to transformers and a final agentic MCP-based incident command system with telemetry and replay.

The Architect — A Claude Code meta-agent that designs complete software blueprints. Describe what you want to build, get a self-contained .md file that Claude Code can build autonomously.

The Blog Agent

multi-agent AI framework for VScode copilot with semantic memory and gemini-CLI baked in

Neurosymbolic AI agent framework - LLM + Prolog reasoning for small models. Single binary, runs offline or cloud-ready. Python & Rust.

The orchestration layer that turns Claude Code, OpenCode, and other AI coding CLIs into autonomous engineers — driving real work from task intake to merged pull request, with humans in the loop only w

Multi-Agent Code Evolution Platform — 4 LLMs compete, evolve, and breed code through a JIT compiler judge

Autonomous AI programming. Stop babysitting your coding agents. You make the important decisions; AI does the rest.

A local, provider-neutral runtime for governed software agent loops.

Toolkit for managing i18n in any framework

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes c

P2PCLAW Research White Paper Series II — 16x16 chess-grid autonomous research agent with evolutionary memory and self-improving capabilities.

⚔ 18,142+ AI agent skills from 307+ GitHub repos across 14 frameworks (Claude Code, Cursor, Cline, Roo, Aider, OpenHands, Codex, Continue, Goose, Copilot, AutoGen, CrewAI, LangGraph, Antigravity). Org

a newsstand skill that gives agents API access to the current main headlines of many newspapers across 20 countries.

The RepSignal Agent delivers AI-driven insights for pre-call planning, account strategy, and territory optimization—helping reps boost productivity, drive strategic growth, and stay efficient on-the-g

Multi Agent AI tutoring system - Content generator, question setter, feedback evaluator

Org-aligned multi-agent orchestration framework with roles, stages, human gates and autonomous execution

How it works

This n8n workflow revolutionizes Instagram content creation by automating everything from idea input to publishing high-quality, AI-generated posts with realistic images or infographics. Whether you'r

An advanced Digital Worker framework for AI agent-driven research and process automations.

Claude Mythos Engine 2026: AI Sub-Agent Framework for Epic Interactive Storytelling

Trusted context for AI agents

TheNZT is a powerful multi-agent finance query processing system designed to process and respond to finance-related queries efficiently. Leveraging advanced LLM multi-agent collaboration, it provides

TheraBot is a SaaS-based AI mental health companion that offers empathetic chatbot support, therapist booking (chat/audio/video), and AI-powered patient health summaries using agents to assist therapi

The Mindset Your AI Is Missing Like hiring an entire team. Except it's free. 67 specialists across 12 professional fields — security auditor, business strategist, project manager, database architect,

把定性投资判断变成可回测对象

Autonomous closed-loop IoT visual monitoring: an LLM agent turns plain-English goals into capture schedules, sends them over MQTT to a bare-metal STM32U5, and analyzes frames with cloud and self-hoste

500+ curated tools, resources, and agencies for builders and creators. With MCP server for AI coding agents.

Drive any agent against any W3C WoT Thing from its description. No per-integration server.

MCP server for Things 3 with read/write support for tasks, projects, areas and tags.

🐉 ThingsBrain 是基于 Dante Cloud 企业级能力构建的，一款兼容阿里云物联网平台标准、支持 MQTT 动态认证与 OAuth2.1 安全体系的高扩展性物联网平台。具备多协议、多存储可插拔架构，为万物互联与 AI 融合提供高可靠、高安全的一站式物联网应用基座。也是 Dante Cloud 全栈能力的最佳价值兑现应用场景。🔝🔝 点个star 持续关注更新！

A minimal, opinionated agent harness — focused scope, straightforward code, easy to fork

Evidence-graded, agent-executable thinking-method skills - 56 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 56 frameworks + 4 tools + 9 recipes for

编程笔记、 AI 学习、观影指南、读书笔记、生活感悟、游戏记录

一个基于思维导图的智能思考辅助系统

Vibe code with pi in a lightweight, real IDE - The Vibe You Need

Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and cost tracking across OpenAI, Anthropic, Gemini, and self-hosted LLMs.

Install once, talk to your agent. ThinkWiki turns documents and notes into a local Markdown wiki with inbox review, content knowledge graph, and browsable HTML workspace.

A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.

Third-party Risk Management Advanced brings generative AI capabilities to streamline and automate risk management processes.

An automated end-to-end phishing process to reduce the manual labor, time to contain, and resolve phishing incidents

Automated Order Management: Eliminate lengthy, complex, and manual order fulfillment for technology industries and service providers. Automate and simplify the intake, validation, and enrichment of th

Combine the power of DevOps and AIOps to simplify and enhance application management

This riddle describes a difficult readlock problem in a multi-agent system. Enjoy the riddle ;)

AI influencer Alice lets her followers vote to choose her daily Instagram posts