Custom agents

The AI security agent guards your code.

🔥 构建高质量的大型语言模型Prompt，让AI替你打工。Building a rich, high-quality prompt for an Large Language Model (LLM)

Claude Code tmux orchestration — spawn full AI sessions as parallel workers with heartbeat monitoring and file-based coordination

Benchmarking LLM agents on real-world hardware bug repair tasks

EFF-Monitoring是一款以内置 Agent 为核心的安全运营协作平台。平台围绕安全事件全生命周期，提供日志解析、资产关联、AI研判、处置流转、经验沉淀与报告输出等能力，通过证据驱动的分析与协同机制，帮助安全团队快速看懂告警、定位风险、联动上下游、提升处置效率。

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland -- 30 tools for virtual and live sessions

Agent Skill for Git workflow best practices - branching, commits, PR workflows | Claude Code compatible

Dart framework for stateful AI agents: tool use, skills, sub-agent delegation, planning, streaming, evals, and multi-provider LLM support.

HumanizerAI Agent Skills for Claude Code and Codex - AI detection and text humanization

Unified web search + content extraction extension for pi with 19 backends. Auto-fallback, RRF combine mode, targeted combine, pluggable web_read (Jina/Sofya/Firecrawl/Exa), and env/shell credential resolution.

Open protocol for AI agent accountability. Cryptographic identity, delegation that can only narrow, gateway enforcement, signed receipts for every action. TypeScript reference, Apache-2.0.

Zooid is an open-source, self-hostable chat app for collaborating with AI agents alongside your team.

Talk to your self-hosted Actual Budget from any MCP client: a remote HTTP server for LibreChat/LobeChat or a local stdio process for Claude Desktop, with 71 tools for transactions, budgets, rules, and bank sync. No Docker needed for local use.

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

A family of small protocols for the perceptual side of designer-agent collaboration.

Coral is an open-source, local-first session bridge that lets AI agents borrow a user's already-authenticated browser sessions on a per-site, per-action, fully audited basis.

Track brand mentions across Perplexity, ChatGPT, Claude & Gemini AI search inside any MCP agent. GEO scoring, share of voice, citations, competitors.

AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL, IFC, secret scanning, and audit logging.

Personal Hermes agent with Emblem Vault crypto integration.

Data Curation Tool is a local-first dataset curation, tagging, model-management, downloader, 3D generation, media metadata, and tool-orchestration application. The current documentation set is stored in docs/wiki/

Code repository for Manning's Build an AI Agent From Scratch

专注于crypto策略交易的AI Agent

AI Agent Skills for content creators — install via npx skills add

Open-source runtime attribution and context observability for data access by AI agents and applications

一款集成了ReAct，Plan-and-Execute和Multi-Agent的coding agent

VS Code-style typewriter animation video skill for AI agents (agentskills.io format)

Interactive visual analytics for Claude Code sessions, costs, context usage, and agent workflows

filesystem as an agent framework based on LangGraph. Built for python users

A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

自用/精选的 Claude Code / Codex 技能：内容创作、客服、市场调研、SEO、Agent 工作流循环、Grok X 实时抓取与评审工具

SWARM: System-Wide Assessment of Risk in Multi-agent systems

Autonomous agents proving theorems in Lean 4 - SETI@Home but for maths proofs using LLMs. Git is the queue, the kernel is the gate, no sorry survives.

Agentic practices knowledge base + supporting software toolkit

A persistent, multi-agent Model Context Protocol (MCP) server. Continuum gives AI coding agents — Claude Code, OpenCode, Codex, Gemini CLI — a shared, live view of a codebase and a memory that survives across agents and sessions.

Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid search, full-text search, indexing, RBAC, and common patterns like RAG

Claude Code Research Harness Workflow turns Claude Code from a general coding agent into a controlled empirical research collaborator | by 朱晨 | 遗传社科研究

Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.

Kraivor is an AI-powered system that analyzes real-world codebases and simulates how they behave under production stress, failures, and scaling conditions.

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.

Drop-in visual editor for React that talks to AI agents

本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。

可执行、可复核的缠论(缠中说禅) AI Agent Skill —— 先定级别·先认结构·先写失效点。研究/学习用途,不荐股。An operational 缠论 (Chan Theory) Skill for AI agents; research only.

The Ultimate AI Compute Gateway ( Router ) | A high-performance, stateless-to-stateful LLM compute gateway in Go. Features multi-model pooling, zero-dependency local RAG with muti-users support, session memory stack injection, and cascading optimal routing for Morden Agent compatible endpoints.

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

A modern Internet Library and curated directory of websites to discover AI tools, movie streaming, live TV, anime, games, developer resources, learning platforms, and thousands of useful websites.

Python SDK for Programmable Multi-Agent Orchestration

unleash the power of behavior trees!

OCPP CP simulator for AI agent testing & CSMS development

Context File System for Agentic AI

Better memory for your AI agents. (Karpathy + Graphify + PCKC)

Expose VS Code language intelligence to AI agents via MCP, with automatic routing across multiple windows

Visualize installed Skills and symlink status across AI agents

An automated AI-powered trading system designed to analyze market data, generate trading signals, and execute trades using configurable strategies.

Analyze any video and produce an .avt (Agentic Video Transcript) file — structured visual descriptions, timestamped transcripts, scene tags, and frame references for AI agent consumption.

A runbook for initializing resumable, verifiable, and auditable project harnesses for AI coding agents.

This is a repo of an ai agent that help you read and understand ableton live documentation

A disciplined, delegation-driven operating system for AI coding agents. npx contractor-kit.

Reflective memory for agents

Agent Team Package Manager for Claude Code

Official code for VoLN: Vision-Only Long-Horizon Navigation—Paradigm, Benchmark, and Method. An embodied AI UAV benchmark and VoLN-MLLM agent bridging VLN and multimodal LLMs across 7,210 episodes, AirSim, and real-world flights.

Agent-native graph orchestration for Codex, Claude, and skill-compatible agents

Tmux-native orchestrator for AI agent sessions. Rust + ratatui.

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Orchestrate Claude, Codex, Pi & other ACP agents in dynamic, durable workflows — survive crashes, pause/resume, and retry, all in TypeScript.

Sample skills and prompt patterns demonstrating how to use the Azure DevOps MCP Server with GitHub Copilot and agent-based workflows

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

Open, structured corpus of US primary law: 2M+ sections of state statutory codes, the US Code, and state constitutions, plus the ingestion pipeline that builds it. Data on Hugging Face (CC BY 4.0); scrapers Apache-2.0. Quarterly snapshots.

Tackle is the runtime layer that lets AI agents operate inside your Laravel application — reading code, executing tools, running tests, and taking action, with safety boundaries enforced at the framework level.

Video-production toolkit for AI agents: Deno + WebGPU + three.js/TSL render engine with VRM character locomotion, simulations, effects, and a full audio pipeline — real-time GPU rendering with minimal CPU

Control a running Godot 4.7 editor and game directly from the terminal. Includes a Go CLI, editor addon, 312 commands, and an MCP server with dynamically generated tool schemas.

DevExpress AI Skills for coding agents (.NET, JS/TS)

KookAI is AI Agent for mobile

CLI for the ClickUp API, optimized for AI agents

Snail AI 企业级 AI Agent 平台 - 让 AI 更智能，让开发更高效

Google Ads CLI and skills for AI agents (and humans)

Lightweight local search engine for AI agents in Rust.

Open agentic prompt-expansion harness for image and video generation, bridging polished demos, public APIs, and deployable workflows.

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

OpenSunstar is a cross-platform native desktop app (Tauri 2 + React) — a local-first, all-in-one platform for AI coding workflow engineering configuration

FreeTop: An enhanced multi-agent AI automation framework inspired by LangManus. Better architecture, testing, and developer experience for complex AI tasks.

Multi-Agent Reinforcement Learning in Graphs

Safe runtime for Claude Code, built to be yours.

Telegram bot для нейронной сети chatGPT

PlugBot connects multiple Dify bots and Telegram in one seamless platform. Easily manage endpoints, API keys, and bot tokens all from a sleek dashboard. Power up your workflows with PlugBot’s unified, intuitive interface.

A drop-in fork of Chatterbot that works on python 3.11 and higher

DEPRECATED: NEW *REAL* SOLUTION COMING VERY, VERY SOON... Complete Multi-Agent Orchestration for Claude Code Enables 24 hour Autonomous Coding

:video_game: Toy environment set for multi-agent reinforcement learning and more

QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate

Web development framework with 17 commands and 5 agents for Claude Code - React, Next.js, Vue, TypeScript

Claude Code plugin that offloads large outputs to filesystem and retrieves when required.

Open runtime + DSL for structured multi-agent systems.

A collection of several Deep Reinforcement Learning techniques (Deep Q Learning, Policy Gradients, ...), gets updated over time.

Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support

Multi-Agent Pickup and Delivery implementation

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

llm-based robot that intervenes only when needed

AI lifecycle platform for classical ML and agentic systems. Versioned, encrypted registries for data, models, experiments, prompts, agents, MCPs, and skills. Pre/deploy/post-deployment patterns. Real-time monitoring and evaluation via Scouter. Rust core, governed by design