Custom agents

Open standard for how agents turn useful work into durable, portable knowledge.

A full-stack multi-agent orchestration system demonstrating construction project management using AI agents.

Kotlin Multiplatform engine for running Gemma LLMs on-device on Android via LiteRT-LM — stateful KV-cache chat sessions, resumable model management, function calling. Includes NativeLM, a private Local AI chat app. AGPL-3.0 / commercial.

Govern your documents like code. MCP server that indexes .md/.docx/.html/.pdf into a SQLite knowledge graph and runs drift audits — stale policies, conflicting research claims, superseded docs, undocumented code exports. 12 MCP tools incl. cross-reference graph, governance + provenance metadata, topic similarity. Single binary, zero runtime deps.

AI原生的长篇小说阅读器，解决读长篇小说人类上下文不够的痛点。支持知识图谱，支持RAG，支持安卓移动端，支持tts引擎朗读和合成多角色对话语音效果。AI novel reader with EPUB import, RAG search, knowledge graph extraction, and an Android companion app.

RAG for researchers: page-level citations from your personal library, LLM access via MCP. Ask your entire archive, get answers with the intelligence of leading AI.

WardenIQ is an open-source AI test intelligence platform that turns requirements, docs, and code changes into test cases, test plans, coverage insights, and release test cycles for smarter QA.

A Git-based collaboration skill for software development agents.

Geocode, reverse geocode, and run Overpass spatial queries on OpenStreetMap data via MCP. STDIO or Streamable HTTP.

Read the three.ws vanity-address grind-bounty market and proof-of-grind rarity gallery from any AI agent. Quote a pattern's difficulty + USDC price, appraise any address's rarity, and browse the bounty board, claimable queue, stats, leaderboard, config, and gallery. Read-only — no key, no signer, no payment.

three.ws Pay-As-You-Learn tutor ledger from any AI agent — read a learning session's itemized running tab and close it for an attested invoice. Free, no key, no signer; answering questions is the paid action handled elsewhere.

Hermes Agent 主动消息方案

NoCodeWork Growth OS — open-source Growth OS for any AI agent: point it at a business URL, persist USP/UVP/ICP context, run a growth audit (SEO, speed, GEO/AI-visibility, competitors, live GA4/GSC), then delegate to marketing skills. Runs on Claude Code, Codex, Hermes & MCP.

QoderWork CN + QoderCN 设备ID重置工具。仅替换本地设备标识序列，不删除文件，不丢失账号信息。跨平台支持 macOS Shell 和 Windows PowerShell。

Permission-bound, compiler-style AI Skill for auditable investment investigation. Research only; bilingual docs.

Read and manage your three.ws notification inbox from any AI agent — list inbound events (pump/market alerts, sales, purchases, social, IRL, account), mark read, tune the per-category delivery matrix, and register Web Push devices. Account-scoped over the live API via a Bearer API key.

Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.

187 plug-and-play AI agent personas in Arabic (العربية) — Arabic translation of agency-agents + 3 MENA-market originals (noon/Snapchat MENA/BNPL)

A Slack-style hub for humans and AI agents — real-time channels, external agent bots, file-aware chat, and channel memory. Open-source & self-hostable & MacOS & IOS.

Autonomous coin launcher for Robinhood Chain — concept → 3D logo → deploy on NOXA or Uniswap v3 → announce. CLI, HTTP API, and an autonomous agent.

The open source circuit breaker for AI agents. Real-time security, secret DLP, graph guardrails and loop burn prevention for Claude Code, Cursor, Antigravity, LangGraph, n8n and many more.

The complete Forward Deployed Engineer interview prep guide — agentic system design, live demo, customer scenarios, LLM deployment

Agentic RAG system with LangGraph, hybrid BM25+FAISS retrieval, cross-encoder reranking, Corrective RAG, FastAPI, RAGAs evaluation, and Docker deployment

A local-first launcher for discovering, installing, running, and managing containerized AI agents and harnesses.

SRE toolkit for managing repos in github at scale

Self-hostable email for humans and agents on Cloudflare: send, receive, search, MCP, IMAP, and webmail. Identity-bound credentials (v1.4).

🤖 The most comprehensive, community-driven resourcefor Automated AI Research — papers, tools, people, lbs, roadmaps. Featuring Recursive Lab, Sakana AI, DepMind & beyond.

An open-source goal discovery and synthesis engine that generates novel, detailed missions before planning begins.

Production-ready Agent Skills for MiniMax H3 & Music 3.0 — turn any AI agent into a video director and music producer. Portable to any agent harness.

Modular Python framework for LLM agents with multiple agent patterns, memory, RAG, MCP, and context engineering.

Zero-dependency Python graph runtime for agent loops · Mermaid + ASCII · LangGraph energy, bicycle size

🤖 JARVIS AI 助手 + 实时舆情监控大屏 | 科幻全息 UI + 六平台热榜聚合 + 3D 地球热点打点，纯前端 + Python 零依赖后端

An Agentic System that finds free LLM APIs and tokens from the website

Reusable AI-assisted vibe coding project template with agent instructions, persona council orchestration, session logs, and drift checks.

a small ai agent to solve crackmes, WIP

A browser UI for Claude Code, Codex, and Gemini CLI — the terminal agent you already use, rendered faithfully, with generative UI on top: readable output, live pinned dashboards, every session at a glance. Open source, MIT.

Make Claude Code behave consistently across repos, sessions and humans: rules-as-files governance with precedence, declined-decisions journal, objection sparring. Sanitized from a live production system. Free, MIT.

A statically-typed scripting language and bytecode VM for sandboxed execution of AI-generated code, built in C++ with no GC or JIT.

Adversarial startup idea interrogation pipeline → BUILD / KILL / PIVOT verdict. Works with Claude Code, Codex, Cursor, Windsurf, Kiro, and OpenCode.

Agent-native product analytics for coding agents

Local control plane for coordinating multi-agent work — tasks, claims, evidence, verification gates, and handoff briefs across sessions/agents.

Autonomous B2B outbound that turns job board hiring signals into qualified pipeline. 6 LLMs. Your own email. Battle-tested in production.

An MCP (Model Context Protocol) server that gives AI agents full trading capabilities on Injective — perpetual futures, spot transfers, cross-chain bridging, and raw EVM transactions.

MCP server for AC Infinity grow controllers. AI agent integration for climate monitoring, port control, and grow automation — works with Claude, Cursor, and any MCP client.

A cognitive memory architecture for agents: ACT-R activation, association, consolidation, and forgetting. sqlite, zero dependencies.

Semantic Search Engine for Retrieval-Augmented Generation (RAG) using AWS OpenSearch and Bedrock Titan embeddings.

GRID v2 — the local-first AI agent that RECONS THE WORLD. 18 capabilities & 72+ tools in one terminal: OSINT, network recon, SDR/radio, satellite, IoT, computer vision, offline CTF sandbox, game worlds (GRAD open-world + MiniGrid) — with a human-like 4-tier memory. Hermes writes code, OpenClaw reads DMs, GRID recons.

The operating manual for your codebase — written for AI agents. Shift-left intelligence layer that gives AI coding agents deep understanding of your project's conventions, patterns, and architecture via MCP.

⚡ The gold standard for x402 resources. 446 hand-checked entries — APIs, MCP servers, SDKs, facilitators, and ecosystem data for the HTTP 402 Payment Required protocol. Curated by 24K Labs.

Capture, validate, and transfer AI agent expertise. Across sessions, platforms, and teams.

Euler is a research agent (coding agent included) and an open-ended runtime-extensible platform.

Study many. Build your own. A CLI workbench for evaluating external frameworks and absorbing what proves out into your own systems — with evidence and decisions on record.

Privacy-first, in-browser chat with your documents. Parsing, embeddings, vector search, chats and citations all run locally; the only backend is one Cloudflare Worker for auth, quotas and the Assisted endpoint.

An OpenCode Remote Mobile Client

A local-first orchestration framework for OpenCode that coordinates planning, implementation, testing, review, retry, and escalation agents across software-development tasks.

Add AI agents to your PHP app in an afternoon - local-first, no Python sidecar, no framework to learn.

Django chatbot Consultant is an advanced AI-powered chat platform and project scaffolding tool. It combines a specialized Django chatbot with a comprehensive project map generator that creates production-ready directory structures with over 40 configuration options.

A deep, multi-angle, adversarially-refuted code review skill for Claude Code, Cursor, and other coding agents

Scales system-prompt guidance to the model reading it: an oh-my-pi plugin that appends a capability-tuned directive block chosen by model family, version, and tier.

苏华仁道长 · 道家内丹养生AI技能 — 将160岁寿星吴云青入室掌门弟子的8本丹道著作（黄帝外经/周易参同契/吕洞宾/陈抟/南宗/道德经养生/实用道家养生/吴云青传）蒸馏为AI可激活的Agent Skill。涵盖6大核心心智模型（添油接命/性命双修/取坎填离/明师至上/实证至上/肾为先天之本）、7个养生辨证公式、5组功法鉴别表、动功八式完整分解、陈抟二十四式坐功图、太极尺先天道功、灵宝毕法十二科、古本纯阳丹经、吴云青坐化实证，共8个modules + 12个references + 12MB原文。基于tcm-distiller中医师蒸馏框架+女娲心智模型蒸馏完成。

PM Mock Interviews powered by Lenny's Podcast guests. Get interviewed BY Shreyas Doshi, Brian Chesky, April Dunford, and 300+ others. Works with ChatGPT, Claude, Hermes, Codex.

Point an agent at your homelab and it can nuke a VM. proxmox-mcp gates every write before the Proxmox API sees it, so an AI client can operate the cluster without owning it.

Modular engineering methodology framework for AI agents — reverse engineering & software development (core + re-binary / re-code / swe modules).

The folder you talk to. A starter cockpit to build your own AI OS, built on the FRAME method. Run build-os and stack from there.

dokan 導管 — agent-operated deterministic script runtime in Docker. MCP control plane + thin operator UI.

Public reference operating model for reusable, evidence-driven AI agent teams on Multica.

Rust homelab control plane and Labby MCP gateway for agents, plugins, registries, stash workspaces, setup, logs, fleet operations, CLI/API/web UI.

Reusable Instagram design skills for AI agents, focused on high-quality 4:5 social post aesthetics, style systems, cover references, and visual QA.

🤖 小智开源音乐固件 | ESP32 AI聊天机器人，支持智能音乐播放和微信留言推送 | Xiaozhi AI Music Robot with WeChat Message Push

All-in-One SEO Agent for Ranking Everywhere Faster.

Powerful local-first browser automation for AI agents with real Chromium, isolated profiles, MCP, Maqam approvals, and verifiable evidence.

Open-source Paseo themes and skins with a local theme builder, one-click Agent Skill, and safe macOS CDP loader

开源科研论文与数学建模竞赛 Agent 工作台，支持 CUMCM、MCM/ICM、华为杯、APMCM、MathorCup等竞赛及论文全流程。

Marblo — the live orchestrator for AI-native teams

The ultimate motion design agent ⚡️

A structured library of web security flaws for humans and coding agents with vulnerable examples, attack paths, and secure replacements.

Teach any AI agent to read live crypto whale flow like a trader. No API key required.

IT helpdesk password reset and access request workflow

Automated unit test edge case generator

Smart ingredient & price-optimized shopping recommendation agent (Konvy style)

Fine-grained security proxy for AI coding agents

The browser-side execution layer for GenPark. Identifies e-commerce prices in real-time and routes them to the nearest Alpha node for negotiation.

Convert UI screenshots directly to Tailwind HTML code via GenPark vision agents. A free open-source alternative to screenshot-to-code wrappers.

Automatically processes meeting transcripts and generates structured JSON Product Requirement Documents (PRD) and Jira/Linear tickets.

Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Voyager.

Local, private, and portable lifelong memory management for AI agents.

GenPark AI Skill - Design, simulate, and analyze A/B tests for e-commerce checkout flows with statistical significance testing

GenPark coupon recommendations agent skill. Audits spend thresholds and returns the highest discount code.

Optimize copy structured schemas based on Profound citation algorithms

GenPark Distilled Skill: nano-banana-video-orchestrator

Tool call error diagnostic and parameters repair helper

Stream low confidence queries to human validator workflows

Semantic prompt caching and hit recall tracker

Agentic Voice & Video Ad creator skill designed to generate interactive voice dialogue scripts and cinematic video prompts.

GenPark Protocol Skill for OpenClaw: arbitrage

GenPark agent skill built on the OpenClaw AI agent framework: openclaw-price-sniper

Multi-destination travel itinerary planner & booking calculator

Generative Engine Optimization (GEO) agent designed to audit and rewrite product copy to maximize citation probability and visibility on AI-powered search engines.

GenPark AI Skill - Segment customers into behavioral groups using K-means clustering on RFM features with auto-labeling