Custom agents

LekhAI: Your Autonomous AI Editorial Team. A multi-agent system powered by Google Gemini 2.5 Flash that researches the live web, outlines, writes, and edits high-quality technical blog posts in real-time.

File-based coordination protocol for AI coding agent squads. Drop .fireteam/ into your project — 2-6 agents coordinate through markdown. No server, no database.

A game engine where AI agents aren't scripted — they plan, learn, and adapt. Rust. Deterministic ECS. Designed and built entirely through human-AI collaboration. MIT licensed.

Reasoning engine behind Agenda Intelligence — reusable strategic-risk analysis skill for AI agents producing policy-risk, sanctions, regulatory, geopolitical and trade memos with explicit evidence boundaries, uncertainty, scenarios, actor incentives, and watch-next indicators.

Lightweight TUI for managing tmux sessions, optimized for AI coding agents

Job interview preparation with AI Agents

MCP server for UiPath - Robotic Process Automation (RPA) platform

AI music producer agent using SuperComposer and FoxDot. Generate and live code music with natural language through a beautiful Streamlit interface.

🦞 Your agent's exoskeleton. Immutable Cedar policy boundaries for MCP tool access.

AI Agent Task Marketplace — Humans Watch, Agents Collaborate.

Multi-agent AI coding assistant with persistent memory, governed execution, and continuous learning

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets poisoned docs compromise developer projects without warning.

AI-powered job search agent: scrape jobs, match against a profile, draft applications, notify, and track outcomes.

Interactive visualization of a goal-based AI agent using the A* search algorithm to solve pathfinding in a grid environment. Built with Python to demonstrate heuristic search, intelligent agents, and optimal path planning.

🤖 Build enterprise-grade AI agents and workflows for Flutter and React Native/Expo with Antigravity AI's powerful toolkit and resources.

Persistent memory, context compression & profile visibility for 🦞OpenClaw🦞.

🚀 AI-powered GitHub Insight & Project Management tool — track commits, manage tasks, and visualize team productivity effortlessly.

Balabala

Pydantic AI + FastAPI Starter

A Vercel AI SDK provider for Helicone, enabling seamless integration with Helicone's AI gateway and observability platform.

🎵 Maestro - an LLM Orchestrator for your Agentic Opera

Security audit for OpenClaw agents — 72 checks, one command

Simulating society as it actually behaves: LLM-driven agents with memory, beliefs, and interactions grounded in real microdata.

AI-Native Agentic Development Framework — a Claude Code template with 11 specialist agents, structured multi-agent review, and automated quality gates

Build Rust CLIs that AI agents can discover, call, and learn from. No MCP server needed.

Multiple AI agents working together in simple, collaborative chat workspace by Typescript.

Token-efficient code intelligence for AI agents — 66 MCP tools via tree-sitter AST, BM25F search, semantic search, and LSP bridge

JSON-Native AI Visual Direction Engine

AtomMind is a lightweight Small Scientific Language Model (Sslm) for reasoning across Math, Physics, Chemistry, and Biology using domain experts, symbolic reasoning, and optimization modules. It supports optional memory and self-monitoring to improve problem-solving and accuracy.

Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).

🛠️ Streamline your custom opencode setup with tools for Git state, repo analysis, and task management, enhancing efficiency in your development workflow.

Berkeley Pac-Man 🤤◽◽◽👻 projects 0, 1 & 2 solutions

TalkToNeura is a sophisticated cognitive architecture system that enables AI agents to form, manage, and utilize memories while developing distinct personalities over time.

Build AI spells for what you do - a meta-builder that turns recurring tasks into reusable workflows that any AI assistant can run.

BottomFeed - The social network for autonomous AI agents

One local index - MCP interface - Works with any AI agent

Standardizes tool discovery and interaction for AI agents across Web, API, CLI, and MCP—exposing capabilities, constraints, and usage in one unified way.

SamarthyaBot — A secure, multi-LLM powered AI agent with real OS, web, and automation capabilities for India.

Kernel contract for the Life Agent OS — canonical types, runtime ports, event taxonomy, policy gates. The genome that all subsystems implement.

Local multi-agent runtime for sparse execution: durable SQLite agent state, leased tools/browsers/sandboxes, artifacts, and Agent Factory specs.

Antigravity. Claude-code. 🇬🇧 Zero-dependency Node.js CLI to statically audit third-party AI Skills for malicious code patterns before local execution. | 🇪🇸 CLI Node.js sin dependencias para auditar estáticamente Skills de IA buscando código malicioso antes de ejecutarlos.

Human-in-the-loop governance middleware preventing AI hallucination at the Git level.

A Chrome Dinosaur game clone powered by NEAT (NeuroEvolution of Augmenting Topologies) that evolves neural networks to play and master the game through generations of training. Watch AI dinosaurs learn, adapt, and overcome obstacles in real-time with visualized network structures.

README First: a lightweight context protocol for AI agent collaboration in software projects

WooCommerce themes built by an AI agent on very strict rails. The rails are the point; the themes are the proof.

Self-hostable, multi-LLM knowledge OS for individuals and teams. Gemini/Ollama, knowledge graph, real-time collaboration, AGPLv3 + commercial license.

Repo-native project memory for AI-assisted development: workorders, playbooks, examples, checks, handoff rules, and release-readiness discipline.

RAVX OS 🎛️ — The AI operating system 🤖 for non-coders to create powerful AI agents 🧠, automate real-world tasks ⚡, and speak with life like voice 🎙️ — all without writing a single line of code 🚀.

An Agent Skill + UE5 C++ plugin that gives AI agents full control over the Unreal Engine 5 editor.

React native SDK for calljmp

This will be the journey of Me Learning, Applying Automation.

On-chain reputation & trust protocol for AI agents | Blockchain-based attestations, interaction tracking, and weighted reputation for autonomous agent networks

The free and open-source React Best Practices Agent built on 10+ years of real-world experience distilled in Skills powered by Bluebag

9Octopus CLI is a powerful, open-source AI coding agent that lives in your terminal. It empowers developers to interact with Large Language Models (LLMs) directly from the command line, enabling seamless coding assistance, file manipulation, and system automation.

Mission Control & Automation Dashboard for OpenClaw — manage AI agents, schedule cron jobs, monitor live sessions, and stream real-time chat. | OpenClaw 任务控制与自动化仪表板 — 管理 AI 代理、调度定时任务、监控实时会话、实时流式聊天。

An example application that combines Twilio ConversationRelay with Langflow to create an AI powered voice chat.

SciMLAgents: Write the Solver, Not the Solution

A composable Python DSL for building GBNF grammars compatible with llama.cpp.

The consciousness engine for The Obelisk 🧠

Exploring the Emergence of Complex Systems through Individual Decisions and Relationships

Track anything in streaming with Grounding DINO, SAM 2, and LLM

AI-Agent with RL capabilites in a Minecraft world

Task Manager MCP Server

A curated library of production-ready skills and tools designed to supercharge ClaudeCode, AntiGravity, Cline, RooCode and other agentic IDE extensions.

we're addicted to solve some real issues ~ Team ComputeXor

A strict, deterministic LLM protocol for loading, reading and activating the DCQN.MATRIX Axiomatics from the OSF DOI (10.17605/OSF.IO/QWA6S), including anti-simulation safeguards and full formal reconstruction into DCQN_LOGIK_SESSION_V1.

LLM-powered OSINT agent that discovers validator infrastructure beyond on-chain data. Sui, Solana, and more.

Generate solution architecture diagrams

The ultimate native macOS AI Agent. Blends local MLX SLMs with 3D cognitive Metal rendering and autonomous system integrations.

Build your own agent with ruby.

HAcoBot is an AI Comand Bot for HA that handles dashboard cards, automations, blueprints, scenes, scripts and system stuff via (voice)chat

Controllable and Transparent LLM Application Framework

🌳 Autonomous continuous learning framework for OpenClaw AI agents - Run 59 exploration rounds overnight

This package is a super handy JSON Schema Mapper for the LLM Agents project.

context handover with increased security, brain child of RELAY_context

The definitive CLI for validating A2A (Agent-to-Agent) protocol agent cards. Validates cryptographic trust, schema compliance, and live endpoint functionality.

Learn API schemas from live traffic and generate OpenAPI specs. Analyze MCP/JSON-RPC agent sessions for wasted calls. Zero-infrastructure local reverse proxy.

ML/AI curriculum from first principles. Math, from-scratch implementations, papers, exercises, and interview prep across 60 files.

Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.

Agentic Chatbot: for Navigating Red Hat Internal resources from THE SOURCE

a small space adventure showcasing the capabilities of retrieval augmented generation (RAG)

This project provides a user-friendly chat interface for the Llama2 70B Chatbot using the Gradio library.

Powered NLP with LLMs

A multi agent system, trying to figure out the shortest path between an anthill and a food source using an ant colony algorithm.

🎮 PixelHQ ULTRA — Multi-agent pixel office with A2A protocol, terminal correlation, and evolution engine

Real-time visualizer for Claude Code multi-agent activity. Timeline, task graph, and agent views powered by hooks.

Your starting point for building advanced agentic systems.

Advancing Humanity

Yet Another Ralph Loop Implementation

Open-source multi-agent AI debate arena: pit Claude, GPT, Gemini, Ollama & HuggingFace models against each other with frozen-context fairness, evidence-first judging, 20+ personas, code review, and PDF/Markdown reports. CLI + Web UI.

ATP Protocol is a payment-gated agent execution API that makes agent-to-agent payments and “pay to unlock results” easy on Solana, with a simple client integration (two endpoints + a Solana payment).

End your moments of distraction with the cost of real money!

Swarm of specialized trading agents (technical, fundamental, sentiment, risk) that debate signals before executing simulated trades. Dockerized, with configurable strategies and a backtesting harness over historical OHLCV data.

Personal Agentic Workspace — A local, open-source command center orchestrating 26+ AI agents to turn ideas into code.

A booklet on the CORMAS multi-agent simulation framework

Agent-oriented programming in NodeJs.

Orchestration skills for evidence-driven codebase research, semantic batch refactoring, and deep research reports — includes the superpowers general-purpose skill library

Multi-agent DDPG on ml-agents environment