Custom agents

Urani's first MEV agent template. It listens for batches, parses them, checks for P2P matches, and spins threads for best quotes through arbitrage in different AMMs.

A command-line interface to generate textual and conversational datasets with LLMs.

AI ChatBot using Python Tensorflow and Natural Language Processing (NLP) along side TFLearn

AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification.

OpenClaw Android Setup Guide Transform any old Android device into a 24/7 AI agent running locally. This guide provides step-by-step instructions for installing and running OpenClaw on Android using Termux and Ubuntu (proot), no PC or cloud server required. What You'll Get Fully local AI agent running on Android 10+ Web-based dashboard accessible

Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.

Lightweight, flexible Spec-Driven Development (SDD) for modern AI-powered development

MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

🪞 Make your agents recursively self-improve

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

AI 塔罗占卜 Agent Skill — 78 牌完整牌义、6 种牌阵、牌间关系理论体系、真随机抽牌脚本

Self-evolving memory palace for AI agents — persistent memory with automatic learning, knowledge graph, and multi-agent support

Hire a private AI tutor for anything — it reads how you actually learn and teaches the next lesson just for you. Bloom's 2-Sigma research as a Claude Code skill + self-hostable web app · 中文优先 苏格拉底式 AI 家教

Multi-agents collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for diverse perspectives

AegisOps企业信息系统智能运维平台：自动巡检、Agent 故障排查、证据工单与审批处置。LangGraph · Deep Agents · MCP；附可复现实测记录。

637 motion techniques for AI video, infographics and scroll decks — rendered clips, recipes, routes and an agent skill (ko/en)

Talk to Claude Code and Codex agents from an Apple Watch and an iPhone. Each agent is a character on the watch.

837 CLI commands. Multi-operator C2. 153 MCP tools for AI agents. The First OSS C2 with Linux native c BOF support + built-in YARA/Nuclei marketplaces.

A data-driven, fast driving simulator for multi-agent coordination under partial observability.

Agentic AI EDR for developer workstations and autonomous agent swarms. Build Swarm Detection & Response platforms with Clawdstrike.

Lightweight, high-performance cross-platform desktop app to browse, sync, and manage AI agent skills across Claude Code, Cursor, Gemini CLI, Copilot, and more.（轻量高性能的跨平台 AI Agent Skills 管理工具）

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

The agentic video editing framework

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.

2026 年编程导航 AI 编程实战新项目，基于 Vue 3 + FastAPI + yt-dlp + DeepSeek + Stripe 的 AI 万能视频下载总结器，支持 1800+ 平台视频下载、AI 视频总结摘要、思维导图生成、AI 问答、字幕导出、Stripe 国际支付。覆盖 SSE 流式传输、JWT 认证、SEO/GEO 优化。用一套教程掌握 AI 编程全流程，从需求分析到商业变现，不到一周学完，给你的简历增加竞争力

MCP-based Computer Use service for Qwen Code and any AI agent — controls macOS, Linux, and Windows via accessibility APIs.

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

PoC memory injection detection agent based on ETW, for offensive and defensive research purposes

Prompt Buddy is a free Microsoft Teams Power App using Dataverse for Teams. It is a space where your team can share their favourite AI prompts and upvote prompts from others. It is preloaded with Copilot categories but others can be added.

Achieve arbitrary kernel read/writes/function calling in Hypervisor-Protected Code Integrity (HVCI) protected environments calling without admin permissions or kernel drivers.

ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.

Harness for running and evaluating AI agents against RL environments

Agentic-AI CyberSecurity Arsenal || 33 real tools, runs 100% locally and 100% Free

Building Software for AI Agent.

🦊 内置 AI 逆向 Agent 的 Firefox — 通用 JS/JSVMP/WASM/签名逆向工作站，SpiderMonkey 引擎层非侵入 trace，把加密参数从黑盒还原成不依赖浏览器的纯算法

Task management system for humans and agents in Obsidian.

[RA-Letter 2022] Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards

Git-native, evidence-backed domain semantic layer for AI agents and human maintainers.

内嵌式 AI Agent 桌面应用——自动识别 AI 回复中的命令和工具调用并在本地执行

Agent-native trading terminal built on DeepSeek Harness. Crypto, US, CN and HK in one three-column GUI, 19+ hot-swappable connectors, dry-run by default with human approval on every live order. BYOK, no data redistribution.

One open-source modeler for structures, heat and fluids, built from scratch in pure Rust: parametric part in, verified results out. Automatic all-hex and tet meshing, our own nonlinear implicit and explicit FEA, heat transfer and lattice Boltzmann CFD — every result checked against theory. For engineers and AI agents alike. Free, forever.

WeChatAuto.SDK 是一款面向 AI 的微信RPA自动化SDK，为Harness/Agent提供操作微信的能力,适合于做为微信Agent的底座使用

Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"

Open-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost OR host on a cluster via Tailscale OR connect to app.49agents.com (coming soon)

Build, evaluate and observe LLM apps

The original Tiny Claw as your personal autonomous AI companion. 🐜

AI Native IDE for reverse engineering

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭代的知识体系。

把文章、案例或笔记排成 3:4 小红书图文 | 1080×1440 | 20 个母版 | 浅色 / 深色 | Claude Code Skill

Messenger automation CLI & SDK for AI agents

POC AI based Compiler, for converting english based markdown specs, into functional code

Nosana Builders' Challenge: Agent 101

FireAct: Toward Language Agent Fine-tuning

AI auto-completion plugin for Monaco Editor, inspired by GitHub Copilot.

Lightweight agent orchestration dev tool that lives in your repo

Codev helps humans and agents co-develop both the context and the code of the project.

Cloud native zero trust security for AI agents run environments

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

Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

本地优先的微信内容情报库：同步公众号文章，保存精选评论和互动数据，供 Codex/Claude Code 做内容研究。

梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用

Pithagoras — hosted web UI for the pi coding agent. Give it a task, close the browser, come back when it's done.

The first self-evolving open-source Agent OS, connecting your team, AI agents, devices, and compute

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

OSS trading workspace with your favorite agents

Our agent harness: Skills, plugins, hooks, and utilities to improve the quality of your agent.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

AI Talks - ChatGPT Assistant via Streamlit

MoFA - Modular Framework for Agents. Modular, Compositional and Programmable.

AI-native data platform: 60+ connectors, dlt-based ETL, DAG scheduling, per-source RAG knowledge bases, and sandboxed AI agents that query, chart, and analyze your data.

Sandboxed AI agent orchestration platform

X-ray vision for AI agent sessions — a transparent HTTP proxy and dashboard for Claude Code

A curated awesome list of agent harnesses, agent frameworks, workflow frameworks, and emerging agent protocols.

AI coding agent for long-running work — high quality at low or even zero cost.

Free offline AI assistant for Windows — reads your screen, hears your question, speaks the answer. No API key, runs locally with Ollama.

YoLuster Shorts 釉光影：An independently developed AI short-drama creation workspace — from initial ideas to storyboard scripts, images, videos, and reusable asset management. Provides a Docker-based local demo package.

TikTok e-commerce video generation, replication, and analysis SKILL

Durable AI agents for Apple platforms: pi-durable on JavaScriptCore with a Swift API

Mentis: A powerful multi-agent orchestration framework built on LangGraph.

Pytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”

A Minecraft coremod / Java Agent aiming to patch serious security vulnerabilities found in many different mods

Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents"

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Technical overview of the Model Context Protocol, current to the 2026-07-28 spec.

Official code for article "LLMLight: Large Language Models as Traffic Signal Control Agents".

🔍 Source code leak? Production code? 13 chapters breaking down Claude Code's production-grade architecture layer by layer — the most visual + agent simulator + source code analysis

[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

Threat Designer is a GenerativeAI application designed to automate and streamline the threat modeling process for secure system design.

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.

Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 categories. 11 security domains, 60+ secret patterns, parallel subagent analysis, professional report generation. Built by tododeia.com

World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.

Private voice keyboard, agent, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.

Open-source AI customer support system. AI-first support, human-ready operations.

The TypeScript framework for building modular agents around an immutable event log.

The open-source SDK for creating AI plugins and actions

An agent-based simulation of corona and other viruses in python