Custom agents

把实现计划派发给另一个 AI 执行，你只负责审——纯 CLI 的协调者/executor 两角色协作工具（opencode / Claude Code / grok / codex，支持远程开发机）

Your Claude, Codex, Cursor, and OpenCode skills pile up across 4+ config folders with no way to see or manage them. Skill Manager is the one desktop app that shows you all of it — enable, disable, edit, and delete skills from a single dashboard.

Replay real agent traces through cheaper models to prove which swaps are safe.

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

An autonomous AI Content Creator Agent for Instagram that discovers trending AI news, drafts engaging multi-slide posts, and generates photorealistic visuals using NVIDIA NIM (Mistral Large 3 and Stable Diffusion XL).

Action guardrails for AI coding agents — native Claude Code enforcement, MCP integrations, and Git/CI checks.

Open-source Python implementation of a Claude-Code-like agent (Gemini CLI, Codex, Copilot...). Usable in CLI, GUI, or as a python library to build upon. Works with any LiteLLM compatible API key, and several local model providers (vLLM, SGLang, Ollama).

Free universal agent skills for federal contracting: SOW/PWS builder, three IGCE builders (FFP, LH/T&M, cost-reimbursement), OT project description, and OT cost analysis. Portable SKILL.md format, runs on Claude, Codex, Gemini, Copilot, Grok, Cursor, DeepSeek Harness, opencode, and LibreChat. For GS-1102s and small businesses.

MVP Engine - The Next-Generation Framework for Multimodal Model Training with Agents

Use the Antigravity desktop app from your phone. One binary that serves Antigravity's own web UI to your devices, behind a password.

A work journal your coding agents write to. Evidence required.

CLI for Local Isolated Environments for Coding Agents

AI-native semantic arbitrage research for prediction markets.

A community-driven catalogue of 150+ reusable AI agent skills for Claude Code , Antigravity, Cursor Ai , kimi , deepseek ,Mimo — code review, security auditing, architecture review, and more. Install any skill with one npx command.

Extensions, tools, and integrations for the pi coding agent.

Interactive demo of a SOTA agentic OCR document approval flow

Catch and fix AI-written patchwork code before it ships, in any language or stack.

A practical learning series on building, grounding, extending, and evaluating AI agents for Microsoft 365 Copilot

Spec-driven development plugin for Claude Code. SpecManager gives you an agile AI team that takes a feature from interview → PRD → Architecture → Design → Plan → Build → Walkthrough.

Self-hosted game den where AI players pull up a chair — 大富翁/大富豪/斗地主/炸金花/UNO with Claude at the table. 一套 AI 牌友同桌打牌的自托管家庭牌窝。

MCP-сервер внутри 1C:EDT: дает AI-агентам семантический доступ к проекту - код BSL, метаданные, валидация и живая отладка

The AI agent-native systems programming language: Meaning in. Verified machine code out. All target OS, memory managed through Ownership & fully interoperable with existing ecosystems & object-oriented AI Agents with payment capability.

Codes for the paper "AoI Aware Radio Resource Management of Autonomous Platoons via Multi Agent Reinforcement Learning"

[ICML 2026] GUIEvalKit: Open-source Evaluation Toolkit for GUI Agents

Turns a vague feature request into a structured spec, technical plan, and task breakdown for AI coding agents — generates first, flags assumptions inline.

DeepSeek Harness auth插件

流镜 Flowglass — DeepSeek Harness session flowgraph，实时可视化消息、工具组、子代理分支与步骤详情。

基于 Claude Code agent 的 PPT 生成 Web 服务，每个生成任务跑在独立 Docker 容器里，跑完自毁，产物可下载

Protect .env secrets from AI coding assistants. Your phone is the key — iPhone Face ID or Google passkey. We also support Windows Hello.

DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidence, declared-vs-detected reconciliation, cross-profile version drift, and a diff of what changed since the last scan.

Deep research skill for pi — structured search, reflection, and analysis.

Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.

The AI engineer roadmap for agent builders: a staged path with runnable labs to build a coding agent from scratch - by AI Builder Club

Feature rich AI driven v2 v3 roleplay character card editor

The Graph Search Engine for Your Knowledge Base

Official plugins (Ghosts) for Cindy — source, review standards, and auto-publish to the plugin marketplace · Cindy 官方插件源码仓：欢迎提交你的插件，合入即自动上架插件市场

mahmud-fca is a Facebook Chat API modified with bug fixes, stability improvements, and extra features for Facebook Messenger bots.

3D code dependency graph generator with built-in LLM agent. Language-agnostic (Python, TypeScript, Rust, Go, Java, C/C++, C#, Ruby, Kotlin, Swift, PHP, Lua). Coupling depth analysis, constraint gating, real-time file watching. Tauri 2 + Three.js + Rust engine.跨语言代码依赖拓扑图生成器 · 14 门语言统一 IR · 3D 全息星图 · 内置 AI Agent 双向联动 · 四级耦合诊断 · 桌面应用 / CLI 双模

A local open-source Frieren desktop companion for monitoring local and remote Pi, Codex, Claude Code and Cursor sessions.

Measure what a website serves to machine readers. Fetches any page as several honest identities, including a cryptographically signed agent, and reports what each one received.

AI-agent skill for building Lark (Feishu) slides via the lark-cli: 51-page template library, brand design tokens, XML generation workflow, and automated layout review. Built for agents, reusable anywhere.

A Codex skill for durable project memory across context compaction

Verify the context you feed your AI agents, against the web or your own documents.

Intent-based Python project scaffolding. 8 project types, non-interactive mode for AI agents, AGENTS.md generation, and built-in health checks.

Download the bootstrap agent and workshops skills to start building your very own company OS

Turn pets, selfies, characters, or anything into a full set of AI chat stickers.

Curated copy-paste Grok Bot profiles, skills, and team templates.

AI Agent 开源书单/教程合集 | Awesome list of LLM Agent books & courses

Claude Code plugins: Ghostty terminal notifications and permission auto-handling

A comprehensive collection of prompts, templates, tools, and frameworks for Product Managers working with AI/ML products.

AGI CLI ~ a meta-harness for building Agent Factories

牛火山企业智能体平台是一套基于 Java 21、AgentScope Java、RuoYi-Vue-Plus 与 SoybeanAdmin 构建的企业级通用智能体平台工程实践。平台以任务驱动、数字员工、工作空间和业务接入为核心，提供多 Agent 协作、Skill/MCP 集成、模型管理、知识库、数据源、Browser 与 Sandbox 执行环境，并覆盖权限控制、风险审批、审计追踪和 Token 用量分析，面向企业私有化部署与智能化业务落地。

A self-improving weather forecasting & trading agent, in public.

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.

Zeltrin (formerly known as SOP, Scalable Objects Persistence)

A multi-device environment for evaluating intelligent vehicle interaction across connected cockpit systems

A multi-user OpenClaw deployment with isolated workspaces and configurable model backends

Joltrin (formerly known as SOP, Scalable Objects Persistence)

Run OpenClaw, Hermes and your own agents in microsandbox microVMs. One reviewable TOML role sets image, allowed domains and host-bound secrets. No daemon.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST API.

Automate on-chain events and actions reliably and securely. Build Workflows in minutes without the need for infrastructure, code or wallet management. Get instant alerts and never miss what matters.

Research Agent for the Open Web

Local-first, model-agnostic LLM agent-harness research. Restart planned after a hiatus; existing code and historical claims await revalidation. MIT.

DeepSeek Harness 免安装便携版（Windows）：官方 npm 包 + 内置 Node.js，双击 exe 即用，拷贝到任意 64 位 Windows 电脑独立运行

P2P — Prompt to Prompt: a prompt that writes prompts. Claude plugin; file edition for other models in releases.

Observability and control plane for AI agents.

Scheduled tasks for your coding agents, in the terminal. A prompt, a cron line, and a fresh git worktree per run — on Herdr. One YAML file, no store, prebuilt binaries, per-automation model, catch-up after sleep, and a live board.

Your coding agent makes the demo video — a narrated, captioned MP4 from one storyboard.json. Deterministic replay re-renders it in CI (no key, ~$0). Open-source (MIT) alternative to Screen Studio / Clueso / Demosmith.

A minimal coding agent, 400 lines of Rust, built with Rig and Ratatui

Retrieval Augmented Generation and Semantic-search Tools

Demo helpdesk system with AI triage, context enhancements, customized ML model for urgency estimates and autonomous coding assistant to fix bugs. Showcases enterprise patterns to add agentic and ML features to business workflow while keeping control.

AI presentation engine. Describe your deck and the look, it derives a bespoke style and renders polished 1920x1080 HTML slides with real charts, tables and imagery. Agent skill: npx skills add SlideSpeak/slide-design-skill

GPT Image 2.5 Sunburst & Flare toolkit for agents: generation, reference and masked edits, PNG/JPEG/WebP, dry-runs and validated receipts. Experimental ChatGPT/Codex backend.

Open, agent-native CAD; edit code, not click menus, make things. kernelCAD.com

The open-source Agentic Development Environment (ADE) for FPGA/ASIC work

Free, open source REAPER MCP server that lets an AI agent (Claude or any MCP client) drive REAPER: read every plugin and parameter, set FX values, write automation, and measure a mix move before and after. MIT. macOS, Windows, Linux.

MCP server that clones the style of a reference reel onto your footage — analyze, scaffold, render, and self-review with Remotion

A Soul-grounded Minecraft social simulation runtime where Mineflayer actors pursue LifeGoals through evidence-backed action skills and transcript-first verification.

A spec-kit demo showing how to build an LLM Performance Analytics Platform (Spring Boot + React) from scratch using AI-assisted specification, planning, and implementation agents in GitHub Copilot Chat.

Open Agent SDK - A Rust framework for building autonomous AI agents

Autonomous pentesting agent

Programmatic Tool Calling for the pi-coding-agent

🎬 Remotion Video Toolkit — AI agent skill for programmatic video creation with React. Covers animations, rendering, captions, 3D, charts, and more. PRs welcome!

A local, persistent cognitive OS for AI agents. Features continuous background consolidation, curiosity triggers, emotional weighting, and lightning-fast Nomic vector retrieval via a persistent FastAPI brain.

Evidence-governed security compliance verification framework for IoT products, initially validated for ETSI TS 103 701 / EN 303 645. Connects test orchestration, traffic intelligence, traceable evidence, and independent review.

MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis

[KDD 2026] An automatic, extensible Framework to Evaluate User-Proxy Agents for Human-Likeness. 🌟 Star if you like it!

Code for 'SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation'

Agents powered by Copilot-SDK and GitHub Agentic Workflow System

Secure, zero-touch mobile access to every running Oh My Pi session

Grimoire's Tome & The Grim Council. A Prompt Spellbook of /skills. The #1 Coding Wizard 🧙‍♂️📖

AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 15,000+ npm downloads.

The easiest way to self-host projects on your own server. Connect your AI agent and let it deploy, maintain and manage multiple projects on any stack, while keeping your server organized and under control. Easy for anyone, not just sysadmins.

Turn Claude Code into a voice-enabled, multi-channel assistant that runs tasks in parallel

Names your startup, product or side project, then proves you can actually use it. Checks the domain registry, trademark, GitHub, npm, app stores and search. An agent skill for Claude Code, Cursor, Codex and 75 other agents.

Audits a repository for how ready it is for AI coding agents, and returns a prioritized fix backlog with evidence for every finding.

Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own OpenRouter, Vercel AI Gateway, or TypesafeAI token.

The coding agent you don't babysit. Automatic software factory.

Agent skill that turns scripts or fact lists into Vox-style paper-collage explainer videos — narration-first pipeline with AI-generated cutout imagery, limited-frame animation, music, and ffmpeg assembly.