Custom agents

AI agent for After Effects — bring your own API key and endpoint

Create and improve AI agents that get better over time with automatic optimization and continuous learning

Syncode — an adapter-based CLI for syncing AI agent configs across repos

Turn your files into a memory filesystem for AI agents.

🧠 ESC Skills — Coleção de skills para agentes AI focadas em desenvolvimento web, DevOps, design, SEO, performance e arquitetura.

General Agent Benchmark for OpenClaw, made by Qwen Team, Alibaba Group.

Training and inference code for "Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning"

OS for Agents: 130+ Agentic Skills, Gemini Protocols, and Autonomous Workflows. (Antigravity System)

Multi-Agent Determinantal Q-Learning

🗺️ The Definitive Map & Launchpad for the Agentic Economy - From Zero to Production in 5 Minutes

Elastic APM Android Agent

SKALE Interchain Messaging Agent

The OpenSVC node agent

A home for your agents skills. Create, manage, share skills between agents easily.

Mail.ru Agent protocol plugin for Pidgin IM

Library-friendly Agents

Web status monitor for FreeSWITCH's mod_callcenter queues and agents

Scriptable KVM/QEMU guest agent implemented in Python

Skills for coding agents

The Microsoft Agent 365 DevTools CLI is a command-line interface tool designed to streamline the development, deployment, and management of Microsoft Agent 365 applications.

Double Q-learning reinforcement learning agent on NES Super Mario Bros

Agent Skill for working with Jujutsu VCS

Chatbot framework

Dialoqbase Lite is a Chrome extension that offers a web-based UI and a side panel, Copilot, designed specifically for almost all AI providers

Common AI Agent written with Go. Supports MCP, RAG, A2A, AI Memory

DevOps, Cloud Native, Hybrid Cloud, Open Source, AI, industry news, culture, and the ‘ish between.

Open-source AI chat app powered by Apple Foundation Models. Runs in any browser. Self-hosted. Private. No cloud.

Agent FM - Tune in and stay in the loop with your agents 🎧

LLM-powered assistant for first-time dads, fine-tuned on real parenting discussions using Mistral 7B

Codify enables data scientists to perform all the tedious and time-consuming tasks such as EDA (exploratory data analysis), data cleaning, data pre-processing, data visualization, modeling, and evaluation in the data-science life cycle, by only conveying the logic of the task in natural language (English) and the system will automatically give out all the relevant python code snippets.

An AI assistant building SDK in python

Streamlined Slack Web API client for TypeScript

A Story Format for Twine that let's you turn a branching narrative into an interactive chat story

AI agents for the bavarian card game Schafkopf trained with reinforcement learning

Claude Multi-Agent: Iterative Sub-Agent Orchestration System - Transform single-threaded AI assistance into a distributed, self-coordinating agent network capable of handling tasks of arbitrary complexity and scale.

Secure access to private services for developers and AI agents.

Low code framework to build and launch a crew of AI agents with shared state. See docs https://axcrew.dev

"When to Switch" Implementation: Addressing the PO-MAPF challenge with RePlan & EPOM policies. This repo includes search-based re-planning, reinforcement learning techniques, and three mixed policies for pathfinding in partially observable multi-agent environments. 🤖🛤️

A Continual Learning Framework for Production LLM Agents

Multi-agent reinforcement learning programs based on Game theory

Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding (IJCAI-19)

Network generation for paper Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks.

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels. (CVPR2025)

Build your genius agent🤔

Paul Graham AI Agent powered by Nia API. Ask questions about startups, writing, technology, and life — grounded in 120+ essays.

ToolFuzz is a fuzzing framework designed to test your LLM Agent tools.

Unit tests for plain text - LLM as a copy editor

🚀 LLM-I: Transform LLMs into natural interleaved multimodal creators! ✨ Tool-use framework supporting image search, generation, code execution & editing

AI agents + toolkits for scientific knowledge

A professional web application that democratizes database querying by converting plain English questions into executable SQL queries. No SQL knowledge required! Built with a sophisticated multi-agent architecture that analyzes schemas, generates queries, and provides clear explanations—all powered by local LLMs via Ollama.

A2A Mastra Demo - Multi-Agent System with Amazon Bedrock

NeurIPS 2023 paper: De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.

Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.

Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies among Large Language Models (LLMs) in a resource-sharing economic scenario. Our experiment extends the classic PGG with a punishment phase, allowing players to penalize free-riders or retaliate against others.

Command Line telepathy. An Autonomous Al Agent for your Terminal that turns intent into Execution (Windows/Linux/Mac)

基于知识库的测试用例生成工具

A powerful integration that combines Browserbase's Stagehand with Mastra for advanced web automation, scraping, and AI-powered web interactions. Features include web navigation, element observation, action execution, data extraction, and intelligent session management.

Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understand relationships, discover notebooks/jobs, and execute queries - greatly reducing ad-hoc query time.

SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning

Multiple agents with LangGraph and MCP

Z.ai Code Review for GitHub Actions

Multi-strategy RAG system achieving 74% Recall@10 on MultiHop-RAG. Combines RAPTOR hierarchical retrieval, knowledge graphs, HyDE, BM25, and Cohere neural reranking.

Playing with Agents

optimize your documentation through fleets of agents

AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-based AMLP-Analysis for molecular simulations and validation.

A different way of calling the notify function on the ps4 for homebrew development.

A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities. This agent enables Claude to interact with web content, manipulate DOM elements, execute JavaScript, and perform API requests.

TelegramBot Tool to Interact with Google's Gemini AI Chatbot

Minimalist AI agent that fixes itself when things break.

[ICASSP 2026] Agent4Debate is a dynamic multi-agent framework that leverages LLMs to achieve human-level performance in competitive debate by dynamically coordinating specialized agents to mitigate hallucinations and enhance competitiveness.

MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.

Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.

Bitwig Controller Extension that provides an MCP Server for AI Agent control

Claude Code skill for AI video & image generation via agent-media CLI

🤖 AI Toolkit - Standardized setup for Claude Code AI workflows. Nx monorepo with reusable agents, commands, and generators for enhanced AI-assisted development.

Self-evolving context for any coding agent.

Vue and Nuxt best practices for Claude Code and AI agents

workspace-cli is a Rust-based command-line tool designed to provide programmatic access to Google Workspace APIs with structured JSON output optimized for AI agent consumption. Built for speed, efficiency, and deterministic execution.

AI Agent 社招面试题自动采集与整理工具 - 从中文互联网平台搜集近12个月真实面试题，清洗去重后按8大模块分类，生成带解答的 Markdown 题集

Your agents do the work — you keep the knowledge. A local-first dashboard (+ desktop pet) that records and replays your Claude Code, Codex CLI and Cursor sessions: timeline, AI session summaries, analytics — all on your machine.

Open source telegram bot powered by ChatGPT and built with Telegraf. Enhance your Telegram experience with AI-driven conversations, smart automation, and advanced features, including the ability to communicate with ChatGPT via text messages, voice messages, and photos.

GyShell is An Strong AI Agent Powered Terminal, Support SSH connection.

A smart multi-agent system to turn prompts into GitHub PRs

Crawl any website into a single searchable file. Query it forever, offline.

A curated collection of powerful AI tools, maintained by the community. This project welcomes contributions from developers worldwide to help build the most comprehensive AI tools directory.

Agent runtime with full system prompt control. Define agents in markdown, run them in a terminal TUI or multi-user web UI. Powered by the Claude Agent SDK.

Semantic code search plugin for Claude Code using hybrid vector search + BM25. 98% accuracy, 5x faster than grep.

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.

AI Runtime Kernel: a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back.

A Model Context Protocol (MCP) server exposing Lucide icons as resources and tools for LLMs and agentic applications. Built with Bun and the MCP TypeScript SDK.

AI Agent Skills toolkit for automated product introduction video generation with Remotion, Playwright, and edge-tts

AI-powered job search pipeline for AI coding agents

🤖 Your Complete AI Toolkit | 500+ Resources | Trending Tools, Hands-On Guides, Interview Prep & Learning Roadmap | From Beginner to Expert

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

agent framework native in Apple shortcuts, better than Siri

CLI-based multi-agents for Auto-Tuning (e.g. HPC code optimazation loops) supporting Local LLMs