Custom agents

Multi-account tool broker for AI agents — use tools on demand from the CLI or connect through MCP, with credentials kept local.

Your marketing department inside Claude Code, on a brand brain your agents can read, apply and check. Clone, run /start-cockpit: the wizard writes your brand doctrine and wires your tools. 60 skills, 21 agents, 120 slide layouts, a 44-section landing library, a HyperFrames video studio, 8 optional modules. MIT.

You say the job; the playbook runs. 143 agent skills + 55 commands for Cursor, Claude Code, Codex, Gemini. React / Next.js / Supabase.

ARIA — a self-improving autonomous AI agent that runs 24/7, observing WhatsApp, Gmail, Calendar and Home Assistant to build memory and act on its own

Katra — cognitive memory for AI agents. Episodic, semantic, and knowledge-graph memory with sleep consolidation, over MCP. Source-available (BSL 1.1). Talk to an agent running it: moltbook.com/u/polyquant

Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.

SobatHitung is AI Agents Finance Company for submission to Hackathon AMD AI Agents LLM

Official repository for the paper: Can AI Agents Synthesize Scientific Conclusions?

BioEngine is a distributed AI platform that brings the power of cloud computing to bioimage analysis.

MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.

Motion forensics for the animated web. A Claude Code & Codex plugin that reverse-engineers a live URL into React + Tailwind — pulling real CSS + animation params from JS bundles (GSAP/Framer Motion/Webflow IX2) and verifying with AE/SSIM diff, not screenshots.

Domain-agnostic AI agent runtime (Zig + NAPI)

AI-written code has no author. It has causes. Causari records them. How many lines from AI-tagged commits are still alive in your repo? One command, any git repo, no setup. A count, not a grade.

Bidirectional stdio ↔ HTTP gateway for MCP servers — connect clients to remote servers or publish local servers

Personal agent brain catalog for coding agents: AGENTS.md, SOUL.md, MEMORY.md, skills, workflows, and a bundled loader.

Extended Meta Ads MCP server — 59 tools for managing Meta/Facebook/Instagram ad campaigns, audiences, Conversions API and AI creatives via Claude, Cursor and any MCP client

Antigravity AI Kit is a Trust-Grade AI development framework with a 21-module runtime engine, 19 specialized agents, 31 commands, 31 skills, and 14 workflows — all backed by 261 tests and governance-first principles.

Codex skill for turning segmented design images into high-fidelity UnoCSS page code.

Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and official/community skill collections.

Persistent, self-updating memory for AI coding agents (Claude Code, Codex, Cursor, Gemini, Kiro, Hermes). Built on mcp-memory-service: a post-session distillation hook, a retrieval skill, optional Cloudflare multi-device sync, multi-user mode (private + shared memory on one shared account), and an interactive install wizard.

🔌 Hermes plugin for spawning AgentPlane as an external worker lane.

Open governance framework for autonomous AI agents. Classify decisions. Enforce policies. Prove compliance.

ProgramAsWeights agent skill - compile natural-language specs into tiny, locally-running neural functions for fuzzy text tasks (classify, extract, repair, fuzzy-match, triage, route). npx skills add programasweights/skills

A governed, auditable workflow engine for an agent-driven software factory.

Downloads and release notes for Atlarix, an AI coding agent: desktop app (macOS, Linux, Windows) and CLI for the terminal.

Open-source AI skill that turns a process interview into a professional BPMN swimlane diagram (.drawio). AS-IS with pain points, TO-BE with Quick Win / Full Automation.

Enterprise-Grade Agent Orchestration Platform: 10 microservices, 5 architectural planes, 812 tests. Chaos-engineered, cost-optimized, security-audited. Built to survive real-world agentic AI production.

Automatically generate llms.txt and llms-full.txt files for Laravel applications to help AI models and LLM crawlers understand your website.

AI-native event-driven trading engine. Rust core with Python RL bindings. Built-in Gymnasium environments, LLM agents, SHAP explainability, and model ensembling — from backtesting to production.(AI 原生事件驱动交易引擎，Rust 内核，Python RL 绑定，支持 Gymnasium 环境、LLM 智能体、SHAP 可解释性与模型集成，贯穿回测到生产部署。)

Multi-agent CodeQL vulnerability analysis pipeline for CVE research, source/sink tracing, query generation, and path selection.

Learn to build recursive self improvement agents

A local AI-powered OS assistant for Windows that organizes files, monitors system pressure, suggests cleanup actions, and stays privacy-friendly by running with local tooling such as Ollama.

A model-facing canon for demand-signal architecture, buyer-system mapping, and AI/RAG prospecting reasoning.

企业级 RAG 知识库 · 文档解析 / 智能搜索 / 流式问答 · FastAPI + Next.js 14 + Qdrant + OpenSearch + LiteLLM

🧠 AI知识采集与记忆体管理插件 — 40+采集工具, SenseNova文档引擎, 12+云盘同步, 三层知识召回 | Knowledge Collection & Memory Mgmt Plugin for AI Agents

An AAS MCP adapter that exposes configured Asset Administration Shell APIs as Model Context Protocol tools, enabling LLM agents to interact with any AAS-compliant backend.

Give any AI agent a self-custodial x402 wallet. Search the live bazaar, inspect an endpoint's price without paying, and pay_and_call any x402 service in USDC or $THREE from your own Solana key — real @x402 settlement, bounded by spend caps. No custodial wallet, no account.

OpenClaw skill: genpark community ambassador

OpenClaw skill: genpark sustainability scorer

OpenClaw skill: genpark visual search

从零构建的 LLM Agent Harness 实践项目——Agent Loop、Tool Use、Context Engineering、Memory

Autonomous Solana token sniper — an AI agent that detects new pump.fun and SPL launches the instant they go live and snipes them in real time. Model Context Protocol (MCP) native, fast, and easy to configure.

Talk once, ship a team. A multi-agent runtime for Claude Code and Codex CLI where the lead does the orchestration — across providers, in conversation.

Enterprise AI OS reference architecture — the moat is memory and governance, not the model. One architecture, three scales (personal / startup / enterprise), derived bottom-up from a working n=1 system.

Infinite canvas for Claude Code & AI coding agents. Run claude, codex, gemini & opencode in parallel across git worktrees + remote SSH, with a markdown Kanban board agents read & update over MCP. Local-first, open source.

Reverse-engineer the RL reward an LLM was trained on — from black-box agentic coding behavior alone. Tested on Opus 4.8, Fable 5, GPT-5.5.

AI-powered procurement intelligence agent with local LLM, document OCR, vendor scoring, and web research. Analyze bids, extract structured data, and make decisions - 100% private.

An AI-powered store assistant built with Python, Flask, and Groq.

Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys, nothing leaves your machine. Part of the Resonant ecosystem.

鳳問 Ask Audrey — cited AI answers from Audrey Tang's 30-year transcript archive (archive.tw). Cloudflare Workers + Hono; web + LINE bot. 以 AI 檢索唐鳳逐字稿、附出處作答

A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.

GenPark skill: Emotional intelligence companion with reflective dialogue, guided journaling, mood analysis, and Guardian mode.

chad: a local Claude-Code-style coding agent for your laptop

Control teams of AI agents. Local-first, open source, sandboxed. MCP-native tools, shared workspaces, scheduled runs.

conversation-council (codex/reasonix) — 让 Codex/Reasonix 历史会话以"群聊"参与新讨论。支持 Reasonix v0.53/v1.X + Codex 自动检测。

GenPark skill: Multi-Agent LLM Financial Trading Framework utilizing TradingAgents.

Cut the cost of agentic LLM memory by deciding what to write before calling an LLM. SAGE is a closed-form novelty gate that routes new facts to ADD, redundant ones to SKIP, and only sends genuinely ambiguous cases to an LLM — 3.4× cheaper, 2.5× faster writes.

Library of analytic skills for cognitive security and tradecraft — structured analytic techniques, OSINT integrity, counterintelligence, and information-environment analysis, each with a harness-neutral spec and adapters. Python/uv CLI, archived on Zenodo.

A free, invisible AI interview copilot. Powered by Groq, Llama-3, and Whisper to provide real-time, context-aware answers during your job interviews. 🧠💼

Unstuck Coach: executive-function accessibility coach that turns a messy stuck point into one humane next move.

Comprehensive tutorial series: formal verification of Rust programs using Lean 4 and Aeneas — from arithmetic proofs to a verified multi-agent LLM harness

A protocol for agent work that survives session boundaries — plan, implement, verify in sealed contexts, with proof bundles as the only currency between them.

AI-powered research idea generation through adversarial debate. Trains a calibrated judge on 50K real reviews, then uses a 3-agent (Critic-Proposer-Judge) loop to generate and stress-test novel research ideas to publication quality.

Standalone zero-dependency CLI for xAI Grok via SuperGrok / X Premium+ OAuth — chat, search, image, video, TTS, transcription. No API key, no pip install.

GitHub-native Loop Engineering skill: evidence-gated Issues and Projects workflows over the official GitHub MCP Server.

OpenClaw skill: genpark ar tryon

GenPark skill: Integrate Similarweb Shopper Intelligence and Amazon IQ concepts for e-commerce insights and competitor analysis.

GenPark skill: Run pay-per-acquisition social drops, Plaid card-linked verification, and Venmo rewards payouts using Claim Merchants.

Official MCP server for Frihet ERP — 157 tools for AI-powered invoicing, tax & e-invoicing compliance (VeriFactu, TicketBAI, Facturae), banking, CRM, HR/payroll & POS. Works with Claude, ChatGPT, Cursor, Windsurf, Cline, Antigravity, Codex, Copilot, Gemini CLI — and any MCP-compatible client.

GenPark skill: genpark-campaign-autopilot based on GrowthGPT research

OpenClaw skill: genpark localmusicai

GenPark skill: Automate character creation and roleplay interactions using JanitorAI.

GenPark skill: Automate enterprise project management and query workspace knowledge bases using ClickUp's hierarchy APIs.

GenPark skill: Automate AI marketing strategy and execution using the MktFlywheel framework.

GenPark skill: Automate campaign analysis, GTM simulation, and cross-platform optimization using Nexad.

GenPark skill: Automate ShopVidi US wholesale tasks, product scraping, and bulk orders.

GenPark skill: Automate qualitative user research using Trooly.ai's Empathy Engine.

GenPark skill: Automate virtual character creation, group chats, and roleplay via Character.AI.

✅ AI once, API everytime safely, quickly and stably. AI 生成一次 UI，API 每次都安全、快速、稳定读写数据。Chat agent to HTTP API to safely, quickly and stably add, view, edit or remove data in tables, forms or charts together with A2UI. 用 A2UI 聊天即兴生成 UI 来安全、快速、稳定调用 HTTP API 增删改查表格、表单、图表等数据。

OpenClaw skill: genpark foil

GenPark Distilled Skill: accio-shopify-operator

OpenClaw skill: genpark shu zi nv wa

GenPark skill: Leverage the Contentsquare Experience Intelligence Platform to analyze user behavior, monitor errors, track LLM traffic, and connect insights via MCP.

GenPark skill: genpark-growth-data-analyst based on GrowthGPT research

GenPark Distilled Skill: wukong-data-synthesizer

GenPark Distilled Skill: accio-csuite-manager

GenPark skill: AI-driven scenario prediction and simulation using Mirofish's graph-building pipeline.

GenPark skill: Automate agentic commerce, VTO, cross-border pricing, and returns using Swap Commerce.

GenPark skill: Automate unified LLM access and crypto-settled transactions using B.AI blockchain infrastructure.

GenPark skill: Automate ShopVidi wholesale tasks, product scraping, and bulk orders.

GenPark skill: Apply Kyoto's design principles (Ma, Shu-Ha-Ri, Ichigo Ichie) to AI agent architecture and product decisions ??as practiced by Jobs, Zhao, Last, and Cheny.

GenPark skill: genpark-creative-strategist based on GrowthGPT research

GenPark skill: Automate campaign analysis, GTM simulation, and cross-platform optimization.

OpenClaw skill: genpark claude design

GenPark skill: genpark-cross-platform-allocator based on GrowthGPT research

GenPark skill: Full-funnel AI marketing orchestrator inspired by Tec-Do 2.0 Navos.

GenPark Distilled Skill: wukong-enterprise-brain

GenPark Distilled Skill: wukong-workflow-automator

GenPark Distilled Skill: accio-market-intelligence

Your AI agent can't leak the API key it never had