Custom agents

Use Reinforcement Learning to train an autonomous driving agent in CARLA Simulator

Generate "Rules for AI". Quickly ✨

Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests

platform engineering framework for the agentic age

An AI agent that brings Augment Code's power to the terminal.

Revornix is an open-source, local-first AI information/markdown workspace. It helps you collect fragmented inputs, turn them into structured knowledge, generate reports with images and podcast audio, and deliver the output through automated notifications.

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

Web Testing AI Agent - Write your specs, it does the rest

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

OpenCode/Claude Code 技能库 。特色技能：视频生成、图片生成、AI Agent 互联、智能问数等等各场景，持续开发更新中

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first

使用社交软件聊天记录结合向量数据库让AI更好的扮演对方的角色，在不微调模型的情况下可以达到可观的效果。把曾经的美好，续成往后的陪伴。

Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.

SeClaw provides a practical foundation for measuring, diagnosing, and comparing security failures in autonomous LLM agents.

Meet Coco. A superintelligent agent framework powered by an advisory board of 389 world-class minds. Scale your AI assistant into a complete engineering department with 142 skills, 277 commands, and persistent state. Universal compatibility. Local privacy. Free and open source.

Apple's official Agent Skills exported from Xcode 27 — SwiftUI, UIKit modernization, Swift Testing, C bounds-safety, and security hardening for AI coding agents.

800+ pure-markdown skills for autonomous AI research. Non-linear orchestration with backtracking, 4-layer military hierarchy (Campaign → Strategy → Tactic → SOP), 5 MCP integrations. The AI is the researcher — you set the direction.

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

Run a team of local coding agents in your terminal. Launch multiple Claude Code, Codex or Gemini agents, switch between them, review their changes and add comments, and push PRs all from one streamlined terminal UI. An exercise to push how fast development can happen with multiple parallel agents. Mostly vibe-coded

A browser coding agent interface for selecting elements and sending instructions directly to Claude Code.

Benchmarking Agentic LLM and VLM Reasoning On Games

Ticket-Driven Automated Software Engineering. OpenASE is an all-in-one platform that turns tickets into working code — AI agents automatically pick up tickets, execute workflows on your machines, and deliver results with full traceability.

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans and LLM agents edit through the same JSON command protocol.

Run AI coding agents in parallel, one git worktree each. Desktop, web, and CLI.

A chatbot for banking that uses the Watson Assistant, Discovery, Natural Language Understanding and Tone Analyzer services.

Empower Your Dev Ecosystem with AI Agents, Automate with Your AI Copilot, Elevate Your Code.

An open-source Vibe platform similar to Claude Cowork / Manus / Openclaw, with professional rich image document generation.

:loudspeaker: Ptt 文章通知機器人！Notify Ptt Article in Realtime

AI Agent OS with visible workflow, real execution, and a 3D office shell. From one sentence to full task lifecycle — plan, run, review, replay

a chatbot based on sklearn where you can give a symptom and it will ask you questions and will tell you the details and give some advice.

ai-chat-app-with-agents-getstream

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

🧠 AI Agent Skills Repository - A curated collection of specialized skills for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf). Created by Yuval Avidani using GitHub Copilot via VS Code Insiders.

Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.

An open protocol for discovering A2A-capable AI agents on local networks — the discovery & trust bootstrap layer beneath A2A (mDNS/DNS-SD, well-known endpoints, signed AgentCards).

Implementation of statistical models to analyze time lagged conversions

(AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions

[AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".

Repo to accompany Jon Krohn and Ed Donner's workshop on Agentic AI in Action at ODSC East

A comprehensive statusline dashboard for Claude Code — session info, quota bars, agent tracker, MCP health, message history, and more.

tmux-native dashboard for managing Claude Code agents

qKnow is an open-source agent platform for enterprise knowledge intelligence and industry AI. It provides knowledge graphs, RAG, and bot building, encapsulating industry AI into standardized modules for rapid deployment. Supporting unified integration of documents and data, it helps enterprises quickly build knowledge hubs and AI solutions.

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.

Operational framework and patterns for high-quality, AI-assisted software development. This repository provides a single canonical guide for AGENTS.md and a lightweight workflow for repeatable, auditable, and architecture-first delivery.

API gateway for purpose-based authorization for AI agents. Human approval for tasks, AI-native enforcement for agents.

Vite plugin to help LLMs to interact with your React App

Sleek, Fast and Token Efficient AI Coding Agent

Agentic RL最详细入门

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

A distributed Spark/Scala implementation of the isolation forest and extended isolation forest algorithms for unsupervised outlier detection, featuring support for scalable training and ONNX export for easy cross-platform inference.

[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

A modular framework for building intelligent AI agents powered by Claude, with rule-based workflows, skill management, and clean JS, TS architecture.

Repository for the book GPT-Agents, published by Manning Publications

Prompts for performing tests on your Kali Linux using Gemini-cli, ChatGPT, DeepSeek, CursorAI, Claude Code, and Copilot.

AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.

A lightweight monitoring agent that detects anomalies, auto-diagnoses root causes with AI, and lets you troubleshoot interactively via chat

AI mock interview coach for FAANG, Big Tech, and startup job seekers. Generate personalized interview questions from JD + resume.

Agent multiplexer with map-charting capabilities

A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时：快速开发、验证和恢复复杂 AI 工作流，并将其稳定交付为服务。

CodeAct Agent SDK with an AST-based code execution engine, enabling stop/start workflows, tool-level state management, and enhanced observability.

Русскоязычный генеративный чатбот с профилем и фактами

:fire: One Slack = Multiple AI Coding Agents :fire: Code anywhere from anything. Connect Claude Code, Codex, and OpenCode to Slack. Work from your phone. Monitor agent progress. Switch agents by renaming channels.

Complex Reasoning Rag System, Agentic Rag System

Codebase for paper: RoCo: Dialectic Multi-Robot Collaboration with Large Language Models

🤖 A Multipurpose Discord Bot with a Music System & Utility commands used by 200K+ users!

A textual adventure game

Knowledge Management for Humans and Agents

Asking yours data in a natural language way through pre-modeling (data models and semantic models).

🤖 An open-source AI assistant answering questions using your docs

[ICML-2026] Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"

[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Undetected Playwright for Android. Real Android device in Docker (Redroid), driven via CDP with OS-level stealth. While every other antidetect browser runs desktop Chromium, DAMRU is Android-native, built for web scraping, AI agents & fingerprinting research.

An agentic operating system where the kernel is controlled directly by Claude

Prototype SDK for RAG development.

A framework for agentic workflow creation and deployment

A chain-agnostic, secure delegation framework enabling AI Agents to perform autonomous, permissioned on-chain actions across Web3 ecosystems.

Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company.

A true AI agent for pixel-perfect web cloning. Multi-agent architecture built on Claude Agent SDK with 40+ specialized tools. Clones from CSS & structured blocks—not screenshots—enabling perfect reproduction where single-model tools like Cursor/Claude Code fail.

A collection of skills for AI coding agents from Semgrep

Agentic LaTeX Writer - Local-first editor for AI-assisted academic writing

A viewer for reviewing local code changes in small individual chapters. Works with any AI agent.

Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.

Your proactive personal AI assistant & companion for daily productivity 🌎

Agentic OSINT toolkit. Autonomous identity triangulation, 6-dimension cognitive profiling, breach analysis. CLI-first. 30+ platforms. 5 languages.

InstSci: academic paper retrieval with Open Access fallback and browser-backed institutional access for AI agents and CLI workflows.

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web applications.

Turn local files into searchable context for AI agents.

🌊 Simple, event-driven and stream oriented workflow for TypeScript

用微信聊天记录训练一个你专属的聊天机器人

Aqua, a cli message tool for AI agents

A library of shared system prompts for creating customized educational GPT agents.

Problem solving by engaging multiple AI agents in conversation with each other and the user.

Various things I had to figure out recently to make things work better...

基于ragflow二次开发的后台管理系统，可以独立运行，支持批量管理知识库、聊天、智能体、用户等，解决ragflow在后台管理上的痛点。

Distill a teammate into an AI Skill. Auto-collect Slack/Teams/GitHub data, generate Work Skill + 5-layer Persona, with continuous evolution. Powered by MyClaw.ai. Works with Claude Code, OpenClaw, and any AgentSkills-compatible agent.