Custom agents

A Graph-Centric Framework for Orchestrating Multi-Agent Systems with Vibe Graphing.

VICE is a security auditing CLI tool that finds vulnerabilities in your web applications.

Build digital human beings — autonomous, collaborative, and socially intelligent agents. FNzgGxU31RWiDgLr3GvxxSa42nRntvZNSG6aBMQ1pump

A wearable terminal to dispatch tasks to your own AI agents — Claude Code, OpenClaw, Codex. Tap, speak, dispatch. The first hardware built for OpenClaw. Open source (MIT).

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

Event-sourced graph runtime for durable and stateful agents

Kolo is a text-based Python debugger for AI agents. Capture every executed function call, return value, local variable, HTTP request, and more in greppable trace files.

im busy building ai agents so why not let an ai talk to my girlfriend? (i am single)

⚡ High-performance job queue for Bun. SQLite persistence, DLQ, cron jobs, S3 backups. Built for AI agents and automation

The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.

Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.

[ICME 2026] Official implementation of Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations

ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

The TypeScript framework for agents & workflows with react-like components. Lightning fast dev loop. Easy to learn. Easy to extend.

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

A dead-simple API to build LLM-powered apps

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

The LLM abstraction layer for modern AI agent applications.

Hack Together: RAG Hack | Register, Learn, Hack

Agentic Development skills behind the JS Mastery workflow

Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Access your terminal and your AI agent from any device — phone, tablet, desktop.

AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor.

Survey on LLM Agents (Published on CoLing 2025)

LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agent–driven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.

An experiment to give an autonomous GPT agent access to a browser and have it accomplish tasks

Mac compatible Ollama Voice

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

Multi-device terminal server for AI coding agents. Server-side VTE, session persistence, file browser, web preview, plugin system. Self-hosted.

MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.

The open-source, self-hosted video conferencing software. Scalable, customizable, and with a powerful AI Meeting Agent.

Agentic skills framework for Godot 4.x. Domain-specific skills for AI coding agents (Claude Code, Copilot, Antigravity, Cursor)

MARVIS-Agent: all-purpose credit risk agent for model development, validation, data processing, feature engineering, and strategy workflows.

Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

An open SDK for agentic payments. Let AI agents make payments, hold funds, and move money across chains with policy enforcement and human approval built in.

Production-ready MVP for securely chatting with your documents using pgvector

Data-Driven Evaluation for LLM-Powered Applications

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete

Permanent memory for AI agents. Single binary, zero dependencies, MCP native.

Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault proxy.

🕵️‍♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.

首个中医大语言模型——“仲景”。受古代中医学巨匠张仲景深邃智慧启迪，专为传统中医领域打造的预训练大语言模型。 The first-ever Traditional Chinese Medicine large language model - "CMLM-ZhongJing". Inspired by the profound wisdom of the ancient Chinese medical master Zhang Zhongjing, it is a pre-trained large language model designed specifically for the field of Traditional Chinese Medicine.

TapCanvas — 无限画布 ❌，沉浸式画布 ✅。线上版功能基本对齐TOP级别。agents-cli 智能体蒸馏自 Claude code + codex + hermes-agent。 可使用 cli 工具直接调试 & 调用画布全部功能。

MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime dependency beyond a POSIX shell.

Self-hosted Lovable/v0 alternative. Realtime database & storage included.

Empower the Shell to think. Evolve Operations.

A project implementing various agentic RL based on the Slime post-training framework

DeepAgent Code: AI coding agent with persistent memory and control plane

Exact structure out of any language model completion.

Bring Claude's Artifacts feature to ChatGPT

A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.

AI-native OpenTelemetry APM with multi-agent root-cause analysis across traces, metrics, and service topology

The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.

Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents

💡 Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the development of technology.

Keep your AI coding agents around. Launch Claude Code, Codex CLI, Gemini CLI, Pi Agent, and more from one place — side by side, connected, reachable, and ready to work across web, mobile, and messaging.

agent q - oss advanced reasoning and learning for autonomous ai agents

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

🧠 AI-powered Personalized Exam System: Integrating OpenPangu LLM, Knowledge Graph RAG, and BKT algorithm for adaptive question generation and recommendation. 基于LLM与知识图谱的智能个性化出题系统。

A command-line interface tool for serving LLM using vLLM.

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode

An AI workflow skill pack for research, competitions, and innovation projects.

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.

Info about many of my Terraform, AWS, DevOps, and AI (tada!) projects.

Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.

A Gym for Agentic LLMs

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 284 commands, 244 MCP tools, change-safety gates, audit evidence, zero API keys.

Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)

[ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.

Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks

Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.

Real-time decoded feed of AI agent actions — monitor multiple Claude Code & Codex sessions, see exactly what each agent is doing, and coordinate swarms efficiently

A Trusted Human-Multi-Agent Reinforcement Learning Interaction Framework

Self-hosted web search skill for AI agents (OpenClaw/Claude Code/Antigravity) via SearxNG

AI-powered IDE for novel writing — local LLM + RAG, privacy-first, BYOK. For web fiction authors and creative writers.

Auditable workspaces for AI coding agents: sandboxed worktrees, programmable multi-agent orchestration, automated security checks, up to 95% less token waste, and persistent memory.

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类

Video Search and Streaming Agent 🕵️‍♂️

A precise user agent parser and device detector written in TypeScript

Task management, but AI agents do your tasks. Self-host on Cloudflare.

SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

Install agent skills from npm

Autonomous GPU Kernel Generation & Optimization via Deep Agents

Open-source agent skills for generating editorial-style information cards from natural-language input.