Custom agents

Official implementation of the paper "Learning and Planning Multi-Agent Tasks via a MoE-based World Model"

Strava for Claude Code / Codex. CLI to track your AI coding output tokens, spend, and streaks. Compete on a global leaderboard and see what your friends are building. Make every agentic coding session count.

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.

一个常驻桌面的 AI 小伙伴。悬浮球形态，轻量不打扰，支持对话、文件处理与轻记录，具备 Agent Loop 与按天记忆能力。Electron + TypeScript 构建，支持 macOS & Windows。

Mobile app for managing Codex, Claude Code, and soon Gemini on remote servers through a chat-style interface with terminal, diff viewer and file browser

Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.

Debug-only in-app MCP server for iOS/macOS/Android/Flutter/ReactNative. Gives LLM agents Playwright-like control over native apps — UI, state, navigation, and diagnostics over the local network.

Expert SurrealDB 3 skill for AI coding agents (Claude, Codex, Amp, Gemini CLI, Copilot, Cursor). SurrealQL, multi-model data modeling, graph queries, vector search, WASM extensions, and full ecosystem.

Project setup generator for Claude Code. Pick framework + workflow, get a fully configured project - CLAUDE.md, hooks, agents, commands, skills, plugins, memory.

CheckmateC2 is a custom agent and listener for the Havoc Framework (made by @Cracked5pider) that communicates entirely through Chess.com game collections and analysis boards using Base5 and FEN for data encoding.

Cross-platform C SDK for Model Context Protocol (MCP), in modern🚀 C23.

Production-ready Claude Code 2.0 setup for autonomous development

The Marketing Swarm Template is a powerful, easy-to-use framework built on top of Swarms for creating multi-platform marketing content using AI agents.

[ICLR 2026] Official code for [EdiVal-Agent Automated, object-centric evaluation for multi-turn instruction-based image editing]

إطار مفتوح المصدر لتكييف مساعدات الذكاء الاصطناعي وسير العمل القانوني مع البيئة القانونية السعودية. Open-source framework for adapting AI assistants and legal workflows to the Saudi Arabian legal environment.

This repo contains my coursework, assignments for IBM RAG and Agentic AI Professional Certificate on Coursera

Starter project for the Build your first declarative agent for Microsoft 365 Copilot by using Visual Studio Code learn module

Architecture rules next to the code, checked on every change.

Production Claude Code skills for n8n from a Verified Creator's 100+ workflows

🤖 The missing WeChat Bot SDK for Node.js — Official iLink Bot API. Zero deps. Full TypeScript. Send/receive text, images, videos, files, voice.

RiskLab (ACL 2026 Demo): A Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems

A vibe coded final fantasy tactics inspired game using Codex, Claude Code and Agent Skills

Full-stack LangGraph real-estate agent for lead intake, property search, Google Calendar scheduling, chat, SMS, and voice workflows

The software suite for creating your waifu and the world where your waifu lives.💕

OSINT Agentic Framework

AutoAdapt: An Automated Domain Adaptation Framework for Large Language Models

飞书 MCP 配置指南 - 让 AI 读写飞书文档、多维表格、知识库 | Feishu/Lark MCP for openclaw, Cursor, Claude Desktop

Production ready Personal AI Agent Platform using Claude Code CLI. Focused on productivity, reliability and security at it's core

Mastering Spring Boot from fundamentals to production — REST APIs, Security, JPA, Microservices, Kafka, Docker, Kubernetes, CI/CD, and AI-powered backend development.

Ultimate Telegram Bot API MCP server — full v9.6 coverage, meta-mode, rate limiting, circuit breaker. TypeScript.

IMAP/SMTP email for AI agents -- read, send, organize folders, and manage attachments across multiple accounts, with auto-discovery.

Telegram MCP server (MTProto). Connect Claude, Cursor, Claude Code, VS Code, Codex, Cline, Windsurf to a real Telegram account — read/search/send messages, moderate channels, manage stories/contacts/folders, transcribe voice, and call any raw MTProto method. Browser-based sign-in. 100+ tools.

Cryochamber for your AI agents, for scheduling long running tasks

Dippin: a DSL for authoring AI pipeline workflows

Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

MinerU Training Camp course materials and tutorials

Free, fully local, easy to use Ai agent/character platform with built in neuroscience inspired persistent memory, moods powered by simulated neurochemistry, and visual memory graphs. Ollama, Sillytavern, Api, Huggingface and locally download GGUF file compatibility. Check ReadME for more details

简悦 Andrej Karpathy LLM Wiki 方案

MCP server giving AI agents full debugger control over running Java applications — inspect state, set breakpoints, evaluate expressions, and mutate values at runtime via JDWP/JDI

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supervisor, creates, runs, answers & reviews tasks on its own. Bash, computer use, vision, semantic search. No cloud, no API keys, no subscription, zero telemetry — your code and your ideas never leave your Mac.

ontorag cli and core library

Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.

对话即创作 · AI Agent 驱动的小说写作工作台 ｜ Chat to create — an AI-agent-driven novel-writing workbench

Meshy: The leading AI 3D Content Generator. This serves as a central hub for Meshy tutorials, workflows, and best practices.

End-to-end educational RAG system: dual-engine retrieval (BM25 + BGE-M3 hybrid vector search), adaptive query strategies (HyDE/sub-query/backtracking), BERT intent classification, BGE-Reranker precision ranking, Chinese-optimized text splitting, and FastAPI SSE streaming — from documents to real-time answers.

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.

LLM reliability layer -keeps agents alive with smart routing, context compaction, and local fallback

MCP server for Home Assistant: give each AI agent its own token, scoped to only what you allow, with per-entity safety, full audit, and instant revoke.

Cockpit web UI for the omp (oh-my-pi) coding agent. Multi-session chat, kanban, cron routines, inbox, Telegram bridge, plugin marketplace.

Interactive web-based digital logic circuit designer & simulator with AI-powered features.

PicoClaw is an ultra-lightweight, open-source AI agent framework designed to run on resource-constrained hardware (like $10 RISC-V boards or old Android phones).

Dataset for Training and Evaluating LLM-Based SOC Agents

Lightweight personal assistant on telegram / discord based on Pi Agent

为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好。 | Born to burn tokens — they get cheaper, quality stays scarce. A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best. Claude Code-style, any model, team-ready.

One registry, every agent. Browse and share skills across Claude Code, Cursor, Codex, and more.

基于强化学习的 LLM Agent 长链路决策优化系统

Your full-service AI agency. 8 teams, 113+ agents, 9 workflows. Clone it, open in Claude Code, say "onboard" — zero setup, zero API keys, just results. v2: Research team, credit-saving guide.

A control plane for long-running agent loops: agents prompting agents on Pi, run history in Neon, a React dashboard, deployable with Retool.

AI-assisted coding setup that helps you spend less time re-explaining context, and more time shipping with better output. Includes a custom spec kit, memory, agent and skill framework.

A centralized analytics dashboard for enterprise GitHub Copilot adoption. Visualize usage metrics, license allocation, premium request consumption, and AI model activity — all sourced from the GitHub Copilot Usage Metrics API.

Reading copilot for Zotero powered by the DeepSeek API and scoped to your local papers, PDFs, and collections.

Self-hosted control plane for long-lived AI coding agents — structured ACP timelines, multi-agent team workflows, and remote execution nodes in one surface.

CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control

Filesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups.

基于 Claude Agent Skills 构建的内容创作助手，支持用户需求澄清、深度研究、配图、AI 痕迹优化、多平台风格等功能，一键生成高质量文章

Official implementation of LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Claude agent skill: Score any video ad with an AI expert panel. 8-dimension rubric + 3 specialist personas.

Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.

Skills and guides to build autonomous AI agents across internal company functions

Windows 本地/局域网 AI 助手：Web 对话、多用户与角色权限、团队文件工作区。Python 3.12 一键部署，依赖包已含（Git LFS）。

My collection of Claude Code, Codex and OMP Agent Skills for web and iOS Development

Turn slide screenshots and generated images into editable PowerPoint decks with visual-layer splitting, OCR evidence, and QA.

Cairn — an AI that walks your system and leaves a trail of tests: UI, API, unit, docs.

Convert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.

Official Porkbun MCP server — exposes the Porkbun v3 API as native tools for Claude Desktop, Cursor, and other AI agents. Idempotency-safe writes, full domain lifecycle.

Evidence-driven stock market analysis CLI for A/HK/US/JP/KR stocks, funds, and portfolios.

Cybara - Your agents. Your tools. Your runtime. Harness the power of AI

Desktop R&D AI-agent

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

A curated map of modern X-Ops: AI Ops, LLM/Agent Observability, Platform Engineering, GitOps, DataOps, FinOps, DevSecOps, and production-grade open-source operations tooling.面向现代 X-Ops 的开源工具地图：覆盖 AI Ops、LLM/Agent 可观测性、平台工程、GitOps、DataOps、FinOps、DevSecOps，以及生产级运维工具链。

🗞️ AI 驱动的每日资讯采集与智能推送平台 — 将 RSS / GitHub Trending / AI 搜索汇聚为个性化日报，推送至飞书、企微、公众号、小红书、钉钉等平台。

Tmux manager for running, monitoring, saving, restoring, and looping Codex, Claude, Gemini, and custom agent CLIs.

Anvil — agent-native multi-genre game engine for AI coding agents

Live DevTools for your running React + TanStack app — driven from the terminal by your AI agent, through one CLI

Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.

Reusable agent skills for end-to-end software delivery, from requirements and implementation to review, testing, and release.

AI makes users productive — but also cognitively lazy. Lucid detects cognitive dependency in real-time and adapts AI responses to keep users thinking. Drop-in SDK: zero latency, any LLM provider, research-backed.

Self-hosted web UI for running Claude Code agents (with optional Codex support). Multi-session chat, voice, skills, social media, telephony.

ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning (AAMAS 2026)

MCP server that extracts, chunks, embeds and stores PDF documents into a pgvector database for semantic search and RAG pipelines.

Research Agent for multi-hop reasoning QA — 3rd place🥉 in 2026 Alibaba Cloud Data+AI Global Competition

Audit, clean, and harden a WordPress site end to end, with an AI agent (Claude/Cursor/Codex/MCP or SSH). Detects & removes hidden malware — cloaking, backdoors, database injection — scores your security posture, and hardens safely. Free, open-source (AGPL-3.0).

Multi-pane ChatGPT workspace Chrome extension with side-by-side chats, lazy panes, prompt queue, goal agent, and Telegram bridge.

本仓库记录了一套以 Obsidian 为知识库核心、以 Claude/Codex/Gemini 等 AI Agent 为分析引擎的研究工作流，适合需要大量阅读文献/资料、整理学习笔记、复现模型/实证的学生党、研究者、工作人员等。

A curated library of 137 production-grade skills for Claude and other AI coding agents.

Control AI Coding Agents From Your Phone

Data Wiki turns data into portable knowledge bundles following Open Knowledge Format (OKF) and serves them to AI agents over the Model Context Protocol (MCP).

A new kind of IDE for agentic engineering

GUI + MCP control plane for your local dev servers. Humans click, agents automate the same daemon.

An agentic Orchestration Setup named after the Greek God of Creation. One Slash command, scans your project, or plan, sets up all the necessary agents + Workflows + MCP tools + claude.md + Documentation Structure. Can be reused to update everything within the project to maintain Proper Context