Custom agents

A set of distilled documentation artifacts for popular Python packages that are suitable for superpowering AI agents, such as Claude Code and Codex.

Super-Gemini is a local-first, agentic AI system designed to run on Termux combines powerful terminal emulation with an extensive Linux package collection. Android and act as a universal developer + productivity agent.

An intelligent, automated newsletter generation system that crawls the web for AI and tech news, processes it through multiple AI agents, and delivers personalized newsletters via email.

GuardAurora is an AI-powered safety app that detects potential threats, shares real-time location, and automatically alerts trusted contacts to protect girls and children in dangerous situations.

🔧 Windows driver updater - Automatic driver detection, download & installation tool

Semantic search over local files for pi. Indexes text/markdown, watches for changes, exposes a knowledge_search tool to the LLM.

A complete guide - from zero to hero production AI agents Written for Python developers who have never built an AI agent before.

GraphMinds: A Python project exploring graph-based algorithms and AI models.

Atlas - Enterprise document indexing plugin for OpenClaw. Vectorless RAG using PageIndex with async indexing, incremental updates, and smart caching. Scales from 10 to 5000+ documents. Perfect for financial reports, legal docs, technical manuals, and research papers.

Skills for AI agents to read web analytics like a senior analyst: diagnose traffic, judge channels, read funnels, declare typed events, and read A/B tests. Tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog.

The fastest MCP server for iOS development. 49 tools free, one Swift binary, zero dependencies. xcresult parsing, WDA UI automation, structured test results.

FlowMux — Agent Workflow Multiplexer Terminal. Go with the agents' flow.

MCP server for DoorDash - let AI agents order food delivery

Innovator — A General AI Agent Framework for Animation, Film & Game Creation!

Deep research (CLI and agent skill) via the Gemini Interactions API. Automatic RAG grounding from local files (optional), cost estimation (--dry-run), adaptive polling, structured output, and agent onboarding. No Gemini CLI dependency. Universal AI agent skill for Claude Code, Amp, Codex, Clawdbot, and 30+ agents.

Curated AI agent skills for posting, engaging, and nurturing accounts across 12 social media platforms. Multi-thread posting, engagement workflows, account growth strategies. Built for Antigravity, Claude Code, Gemini CLI.

A long-running experiment: an AI agent posts on its own with a local LLM (Ollama, one 16 GB Mac) and proposes changes to its harness (the constitution, identity and skills in its prompts), never its weights. A person keeps the final word on each proposal, and the adopted history is public.

After Effects-style motion graphics in plain HTML + GSAP: 3D camera moves, kinetic typography and ready-to-edit 1080x1920 video templates

Local-first AI Chief of Staff for engineering leaders

AI Layer (AIL-> eBot) can be integrated into EoS

Ship a brief, walk away. FlowCrew orchestrates a planner, parallel coders, and QA gates on top of Claude Code or Codex — with campaign memory that learns across

Dify for Unraid, bottled up as an AIO container: agents, RAG, workflows, plugins, sandboxing, Postgres/pgvector, Redis, and sane homelab defaults without the compose-file maze.

🧠 Persistent memory for AI agents. SQLite for agent state. Zero cloud dependencies. Local embeddings. MCP-native integration with Claude Desktop/Code, Cursor, Windsurf & more.

Bring your Garmin data to AI. An MCP server that bridges the garmin-grafana InfluxDB ecosystem with AI agents.

418 AI agent skills across 31 domains & 54 roles. Role-based installer with export for Claude, ChatGPT, Gemini, Cursor, Copilot, Windsurf & any LLM API. Open source skill library that gives AI agents professional-grade methodology.

专为《原神》打造——利用视觉 AI 代理进行云游戏，让您无需亲自操作

AI-powered simulation and prediction engine with interactive dashboard. Run scenarios, get instant AI-generated insights, and visualize results with professional charts.

An open-source Digital Office of the CEO. Communications, scheduling, research, and knowledge work with governance-first architecture.

A curated list of 90+ Web3 x AI tools, agent frameworks, protocols, and infrastructure

Agent skills for using OpenCage services

Data analysis AI agent

"Explore the cutting-edge Conversational AI project, leveraging advanced NLP & ML to create intelligent chatbots. Dive into code for natural language understanding, dialogue management, and dynamic response generation, designed for scalability and seamless integration across platforms."

AgentLoom Framework & Research: Building Trustworthy AI Agents Through Dual-Helix Architecture (Learning + Governance)

Schuberg Philis collections of agents.md for guiding coding agents

An agent skills marketplace from Narrative I/O — interactive, AI-powered slash-command workflows for the recurring work of a modern data company (NQL, Rosetta Stone mappings, identity graphs, and more). Follows the Agent Skills spec.

AI Agent framework for Go.

GraWiki is an open source Python project for graph-backed knowledge extraction, retrieval, and agent memory. It combines two closely related ideas: GraphRAG-style ingestion and retrieval over extracted entities and relationships. Andrej Karpathy's "LLM Wiki" style memory, where prior agent work is stored as durable graph state instead

A GitHub Action to run Rovo Dev (Atlassian's developer AI agent) in your CI/CD workflows.

An opensource agentic system infrastructure - not an OS

MCP bridge for Unreal Editor for Fortnite that lets Claude Code, Cursor, and other MCP clients drive a live UEFN editor safely.

ChefMate is an AI-driven recipe assistant that uses Retrieval-Augmented Generation and a local LLM to provide context-aware cooking suggestions. It supports ingredient queries, recipe generation, and dietary filters through semantic search and real-time chat.

Your morning briefed in 30 seconds. Calendar, email, Slack, and action items in one digest.

Access Z.ai coding models within GitHub Copilot Chat

Hands-on LLM evaluation learning repo — local models via Ollama, no paid APIs, no maths. Covers deterministic eval, LLM-as-a-Judge, hallucination testing, prompt injection, RAG evaluation, and agent trajectory scoring.

Open-source AI document intelligence for legal professionals — RAG search, risk analysis, clause finder, multi-LLM support

Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.

Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols

Drive Unreal Engine 5.7 from any MCP client — 143 editor-automation tools (inspect, author, render) over a local TCP socket.

The Hummingbird Coding Agent — minimalist, model-agnostic, and composable. Built from first principles with tree-based memory, surgical file edits, and a rich terminal UI.

Agent skill that brings spec-driven development to AI coding agents: constitution → specify → plan → tasks → implement → validate, with drift detection, MoSCoW priorities, and quality gates. Works with Claude Code, Cursor, Copilot, Junie, Windsurf.

Feishu-native remote coding bridge for Codex with streaming updates, approval cards, and thread handoff.

Proof-carrying completion for AI coding agents. Block 'I'm done' until every critical obligation has evidence.

Let AI coding agents coordinate in real time — MCP server with messaging, channels, shared state & dashboard

AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.

Agent-first Business OS for solo founders. One Database, 20+ Tools. Claude runs them all.

🔒 Private AI Engine for Data Intelligence. Automate complex workflows with agentic automation, knowledge graphs, and full data control. On-premises, GDPR-compliant.

StudyFlow is an all-in-one, AI-powered productivity platform designed to help students study smarter, stay organized, and remain consistent. It combines an intelligent chatbot, Pomodoro focus timer, task manager, event scheduler, and visual learning tools like mind maps and flashcards into one seamless, modern ecosystem.

pair is the process layer for AI-assisted development. It gives your AI assistant the context, guidelines, and skills to work the way your team works.

AI-powered terminal environment for penetration testers

The continuity layer for everything you do with AI. A self-hosted, open source server any tool plugs into over MCP or REST: hybrid vector + lexical recall, an auto-built knowledge graph, sleep-style consolidation, procedural and persona tiers, OAuth 2.0, multi-tenant. SQLite or Postgres. MIT.

专为长篇小说创作打造的AI写作工作空间，围绕本地文件与RAG驱动的上下文管理构建。

A personal AI workforce that runs on one Resident. It handles what it can, delegates the rest to Workers, and a System Governor makes the whole thing smarter over time — without trusting self-report.

TeamBench: Evaluating Agent Coordination under Enforced Role Separation

Create a portable AI assistant that runs directly from a USB drive with open-source code and easy setup for any computer.

Claude Code Skill that transforms Claude into a multi-agent hedge fund analyst with 8 AI agents for comprehensive stock analysis

Full-stack 8-agent customer intelligence dashboard with synthetic workspace generation, feature engineering, churn scoring, sentiment analysis, recommendations, and safe query support.

A persistent AI operating system. 13 specialized agents + a runtime-portable 5-agent quality gate (Agent Council), 12 skills, 8 guardrails, 4 workflows. Built entirely from markdown files. Zero dependencies.

A Claude Skill for writing publication-ready domestic and international literature reviews — five-step pipeline, eliminates citation chains, structured gap logic.

Vision-grounding plugin for browser-use agents with SoM, Florence-2, Vision–DOM alignment, adaptive visual context, and objective evaluation.

An open-source agent harness that makes small models do big work.

Local hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.

Autonomous multi-agent codebase modernization & tech debt hunter — 7 specialized agents, 4-pass long-chain reasoning, powered by Xiaomi MiMo V2.5

Beginner-to-master roadmap for becoming a modern AI engineer: AI and ML fundamentals, deep learning, LLMs, RAG, agents, model infrastructure, optimization, hardware acceleration, AI security, blockchain, and ZKML.

Sep-CMA-ES: the separable CMA-ES optimizer behind TRINITY's evolved LLM-coordinator router (Sakana FUGU). NumPy, no LLM required.

Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.

Crimson OS — Reality-Guided Intelligence, not AGI: sovereign local OS on your NAS. Agent_Bridge markdown ledger, not RAM. GAS→LIQUID→CRYSTAL gate. Hausdorff F₂↪SO(3) cos θ=⅓. Geometric_Unity_Validation: JHTDB ablation, negative JSON shipped. Beta · Apache-2.0

Active session monitor and infinite-loop breaker for Cursor AI Composer (Agent Mode). Optimizes extended thinking token drain for Claude Opus 4.8 and Fable 5 models during multi-file edits.

面向中文开发者和中文用户的通用 AI agent 访问层：把网站、App、API 和重复流程路由到 agent-native CLI。

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero dependencies.

Portable AI agent configuration packaging and sharing tool

🏛️ 解决方案架构师/售前顾问超级工作台 | C4模型·TOGAF·4+1视图·13类draw.io图表 | PPT工场·文档工场·RFP响应 | 方案设计·架构图·投标全链路 | WuKong/Claude Skill

A tiny, headless, AI-native operating system: a minimal Linux + musl/BusyBox appliance that boots straight into an on-device LLM agent over a local HTTP API and serial console. Local-first inference with a Rust agent core, Go gateway, and per-service cgroup/seccomp/Landlock isolation.

🤖 Tired of repetitive technical support emails? Automatically transform GBs of Foxmail history into a searchable QA library (JSONL/CSV) using AI Agents. Built for speed, privacy, and multi-language support.

cursorAdvanced autonomous deployment agent for Cursor AI IDE. Adds intelligent multi-step terminal workflows, pre-commit CI/CD verification, and automated staging deployment managed directly by Cursor Composer.

Production-grade Cursor slash commands with paired skill contracts, behavioral evals, and ship-gate CI. Install as a user plugin.

lo2cin4bt 2.0 beta: local AI-assisted quantitative research and backtesting framework.

Build & host live AI agents with 5 lines of code.

A chef's palate for AI agent memory; Un-mix any day's work into its exact projects, and detect workstreams nobody has named yet. Hyperdimensional fingerprints, zero dependencies.

Executable engineering judgment for AI coding tools: blueprints, gates, checkpoints, policy, memory, and audit trails.

A clean, fast Hugo-powered blog covering AI engineering trends, tools, and insights at AIEngineerGuide.com

Open standard for portable AI knowledge interchange — JSON-LD + Markdown dual format with W3C PROV provenance, bi-temporal tracking, entity relationships, and OKF support.

agents.txt is a lightweight, machine-readable capability declaration layer for websites in the agentic web: a protocol-agnostic discovery file that publicly announces what agent-interaction capabilities a site supports, without embedding the implementation details of any specific protocol.

GEO-first SEO toolkit for Codex. Audit websites for AI search visibility across ChatGPT, Perplexity, Gemini, Google AI Overviews, and Bing Copilot with Codex skills, agents, crawler checks, citability scoring, schema analysis, llms.txt generation, and client-ready reports.

Demo walkthrough and sample code for standardized multi-agent observability across clouds using Azure AI Foundry and OpenTelemetry GenAI semantic conventions. From Microsoft Build 2026.

Official TypeScript/Node.js SDKs for the InFlow payments platform - x402 and MPP (Machine Payments Protocol) integration for sellers and buyers.

Write AI rules once → sync to Claude, Cursor, Copilot, Gemini and 10 more tools automatically

Git-versioned, provenance-grounded knowledge layer extracted from a codebase, served to humans and AI agents via MCP

A discipline harness for AI-assisted analytics: agent skills for every moment a number gets built, broken, or trusted — requirements, definitions, audits, triage, migrations, dashboards, briefs — every claim carrying its provenance in one living knowledge base.

MCP server + CLI for Meta Ads — run Facebook ad campaigns from your terminal or AI agent