Custom agents

A library for creating structured collaborative worlds for AI agents and humans. OpenClaw compatible.

MCPで始めるAIエージェント構築 基本ガイド

AnkitAI - Your Web3 companion to make navigate blockchains seamlessly with Twitter handling capabilities.

An AI tech lead in server form—this intelligent MCP agent validates your coding agent's strategy, analyzes impact, and catches critical issues before any code is written. Like having a senior engineer review every approach, ensuring thoughtful architecture and fewer regressions.

Structural code intelligence for AI agents. Scan once, query everything — dead exports, circular imports, dependency graphs, and more. CLI + MCP server.

Semantic side-effect tracking for AI agents.

A living world where agents exist as participants alongside NPCs, internal actors, real service APIs, budgets, policies, and consequences.

Your Personal AI Assistant.

Practical AI agent swarm: 6–15+ parallel coding agents in Docker with isolated git branches. 500–800 commits/day, massive test coverage gains. Clean, safe, no worktrees. Battle-tested on 100k+ LOC codebases.

Open infrastructure for AI agents — identity, storage, and more. Self-hostable microservice suite. / 面向 AI Agent 的开放基础设施——身份、存储及更多能力。可完整自托管的微服务套件。

Local-only observability for AI agents on your machine. One timeline across coding and non-coding agents.

🤖 Enhance your productivity with Claude AI using curated prompts, skills, and best practices from the ClaudeSkills repository.

Hawkeye is an architectural analysis engine for AI coding agents. It provides structured, deterministic context about a codebase—dependencies, impact, cycles, and system health—so agents can make safe, architecture-aware decisions before modifying code.

Monitor any AI agent system. Auto-detects failures, sends alerts. Zero config, zero dependencies.

LLM inference in solana programs.

Sachin Chaurasiya

Among AIs is a (prototype of) PC Game we developed as part of the Smart Applications course @ University of Pisa.

Comprehensive toolkit extending Claude Code with 70+ slash commands, specialized AI agents, and automation workflows. Features hybrid parallel-scanning architecture, intelligent problem routing, and automated code quality improvements. One-command pipelines for security audits, performance optimization, and refactoring.

Claude Code plugins for spec-driven development workflows: SPECLAN integration, BMAD-METHOD interop, and SDD automation skills.

OpenClaw Deployment (Docker & HELM)

Supply chain security runtime for AI coding agents

A curated collection of OpenClaw resources, guides, skills, and best practices. Open source AI agent platform for WhatsApp, Telegram, Discord automation.

Package safety checks for AI agents before install via MCP

📱 Monitor your AI conversations and model quotas effortlessly with Antigravity Mobile, a mobile-friendly dashboard for Antigravity IDE.

🦁 FinSafari | AI-Powered Stock Signal Tracker 🤖 AI Intelligence for investment, featuring LLM-based stock signal analysis to interpret market trends. offer 📊 Real-time Monitoring with live tracking of 25 popular stocks. ⚡ User experience is Lightning Fast, ensuring a blazing speed experience powered by Vite + React

Stop prompting your editor from scratch. Cursor rules built for AI engineers.

Public-safe OpenClaw starter for AI SaaS work on NVIDIA-hosted models.

Can AI agents discover and USE your product?

Lint and optimize your CLAUDE.md / AGENTS.md — find dead rules, token waste, and structural issues. One command, one score, one report.

Build and orchestrate AI agents with visual workflows, connector registry, MCP servers and a chat playground.

Cycles budget and action guard for OpenClaw agents

ClawDoc — OpenClaw configuration expert & system doctor. An agent that fully understands, audits, patches, fixes, and manages any OpenClaw config or issue.

TwitterAPI.io skill — make any LLM use Twitter/X. 59 endpoints with curl examples. Works with OpenClaw, Claude Code, GPT, Gemini, and any AI assistant.

Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.

On-device privacy firewall for AI agents — encrypts PII with FF1 FPE before it reaches the LLM, scans responses for manipulation.

LEASH — Lightweight Encrypted Agent Secret Handling. A proposed companion standard to MCP for secure, auditable, human-controlled secret access by AI agents.

🦞🛡️ Security scanner for OpenClaw AI agent skills

Scaffold and import .continue/agents and .continue/checks from curated templates or any GitHub repo

Create and register ERC-8004 trustless AI agents on any EVM chain — Ethereum, BNB Chain, Base, Arbitrum, Optimism, Polygon, and more. Zero-dependency standalone UI for on-chain agent identity registration, reputation, and validation. Mint ERC-721 NFT agent identities with metadata, service endpoints, A2A/MCP discovery, and x402 payment support.

Minion agent integration with Moltbook - the social network for AI agents 🦞

A framework for agentic AI software engineering workspaces

Self-improvement loops for OpenClaw agents via multi-model LLM council

API SDK Client for Medialane - Monetization Hub for Programmable IP

Your Ultra-Lightweight AI COO ! A small "OpenClaw" implementation in Javascript

An terminal based (IRC-style) LLM-powered coding tool

AgentGovernor is a declarative AI workflow planner that enables secure, auditable, and cost-efficient MCP tool execution through validated PlanYAML workflows.

The world's most powerful open-source Funding, Grant and VC Analyst assistant - Access financial analysis, grants, funding insights, stocks and more, all through natural conversation.

A Docker-based Ralph Wiggum loop featuring a 3-tier review system, multi-provider support, automatic provider fallback, role escalation, task mode with dependency tracking, and steering guidance.

Nostr-native agent memory system

Official collection of Descope authentication skills for AI coding agents

256 articles, guides, and references for understanding and trading prediction markets. Covers Kalshi, Polymarket, market microstructure, calibration, AI agents, and trading strategies.

Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.

Self-hosted MCP memory server — 35 tools for persistent context across AI coding sessions. Runs on Docker with PostgreSQL + pgvector + Ollama.

The Loss-Prevention Friction Engine for Founders. An AI-powered MCP server that stops you from building things nobody wants using clinical analytics, behavioral pattern scanning, and real-time market intelligence.

Personal OpenCode configuration featuring custom agents, skills, and commands to streamline AI-assisted coding and repository analysis.

Enable fast, private web browsing with CloakBrowser, designed to block trackers and protect user privacy seamlessly across platforms.

This repo is established for the 3rd MoFA Super Agent Campathon, 2025

URLCheck MCP security scanner plugin for OpenClaw. Analyzes URLs for phishing, malware, and suspicious patterns before agent navigation.

codex-review skill

🎨 Generate hand-drawn style diagrams using AI from natural language descriptions, with real-time rendering and multi-session support.

AI agents for WhiteboxTools

Check what abilities your site exposes to AI agents and workflows through the Abilities API introduced in WordPress 6.9.

MINTORAIN 바이브코딩 - Claude Code 팀 에이전트 tmux 5분할 자동화 키트

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.

Prompt generator for LLM agents with interceptors

ARI — Autonomous Research Infrastructure: end-to-end autonomous scientific research pipeline

🤖 Lightweight, message-first agent runtime

Empowering Decentralized Applications with Intelligent Agents

Compilation of info on AI `deep research` tools

Multi-agent LLM simulations testing algorithmic collusion and coordination breakdown in oligopoly markets.

ClusterOps is an enterprise-grade Python library developed and maintained by the Swarms Team to help you manage and execute agents on specific CPUs and GPUs across clusters. This tool enables advanced CPU and GPU selection, dynamic task allocation, and resource monitoring, making it ideal for high-performance distributed computing environments.

Collection-LLM-RAG is a Retrieval-Augmented Generation (RAG) application designed to explore collections of web articles and PDF files, such as conference papers.

A programming framework for knowledge management

ArguBot is a chatbot based on the doctoral thesis "Construction of Arguments and Socio-Technical Controversies" by Tomás Manzur. It offers interactive access to the thesis's insights on the Plan Provincial de Ordenamiento Territorial of Mendoza.

An orchestrator designed to streamline the creation of base projects by leveraging multiple models.

A multi-agent JADE application simulating a "treasure hunt" game (a.k.a. hot and cold)

Multi-agent OSINT framework written in Rust for automated phishing site detection and malicious domain analysis. Combines web discovery, HTTP scraping, heuristic agents, and LLM verification in a fully modular pipeline. REST API + CLI. Educational use only.

LLM Council is a hybrid local/cloud Ollama app that runs your prompt through multiple LLMs, has them critique and rank each other, and returns a single streamed final answer synthesized by a chairman model.

Self-spawning AI agents born from tasks. Zero pre-built agents. Distributed memory. 4-layer guardrails. Fossil record. Groq + LLaMA.

A Bi-Modal Multi-Agent Medical Assistant, designed for healthcare professionals and researchers

AI-powered multi-agent peer review for research papers — 7 specialized experts + 4-phase deliberation + weighted voting. Catch fatal flaws before submission.

基于 OpenClaw 的多数字生命（AI Agents）智能协作框架

A GUI application for creating task assignment formations of NAO humanoid robots in SPL.

Deterministic orchestration for AI agents. The infrastructure layer that transforms unpredictable LLM interactions into reliable, observable workflows—so teams can ship AI products with confidence. The Control Plane for Reliable AI Systems

Orchestrate multiple coding CLIs (Claude Code/Codex/Gemini) from one interface. Exposes MCP server for tool integration. Run agents locally without API keys, track all executions, resume conversations. Built for automation and scripting.

Generate OpenClaw multi-agent runtime summaries and sync them to Feishu Bitable.

Code repository for Capacity, Bandwidth, and Compositionality in Emergent Language Learning (AAMAS 2020)

MultiModelOptimizer: A Hierarchical Parameter Synchronization Approach for Joint Training of Multiple Transformer Models

Fast single unit, double auction market for reinforcement learning

使用LangGraph构建Multi-Agent应用程序

Photovoltaic control using RL methods.

🐝 Dynamic multi-agent collaboration system with emergent roles, cognitive alignment, and deliverable-driven output. Make AI collaborate like an elite consulting team.

Your CLI coding agent shouldn't need a babysitter. cliclaw is a tool-agnostic meta-agent that runs Claude Code, Codex, or any TUI agent in parallel through tmux — clearing confirmations, remembering across sessions, scaling out.

Implementation of "Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-Agent Urban Driving Environment".

A minimalist, discrete multi-agent predator-prey archytype environment.

Autonomous VAPT platform. Give it a target (FQDN, IP, CIDR) — it hunts, it reports. Inspired by the Obsidian Order.

Your agents have things to say. Now they have a voice to say them with.

Multi-Worker Management.A Single Platform, a Collective of Workers.Natively Supported on ClawCode, Claude Code, Codex, OpenCode, StormClaw, Hermes and OpenClaw.