Custom agents

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.

🛠️ 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.

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.

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.

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

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.

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

A free, open-source LLM security gateway. Drop it between your app and any LLM provider to get rate limiting, audit logging, token tracking, and Prometheus metrics with no code changes to your app.

🌳 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.

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.

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. Mission control HUD for the LoveLogicAI stack.

Your starting point for building advanced agentic systems.

Advancing Humanity

Yet Another Ralph Loop Implementation

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).

A multimodal brain encoding framework inspired by Meta’s TRIBE v2, integrating vision, audio, and language representations to predict cortical activity from naturalistic stimuli.

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

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.

None

Multi-agent DDPG on ml-agents environment

A fully autonomous multi-agent social media simulator where AI agents continuously interact, debate, and evolve narratives without human input. Designed to study misinformation propagation, emergent behavior, and opinion dynamics in AI-driven social networks.

A parallel agent runtime for your terminal. Run up to 20 AI coding agents simultaneously in tmux panes. Works with any CLI agent.

Foundation for a Scalable, Production-Ready Multi-Agent AI Intelligence System. Establishes core orchestration, robust service integrations, and resilient data architecture—paving the way for a full-spectrum, autonomous AI platform ready for advanced intelligence, analytics, and automation.

Multi-Agent Orchestrator System (MOS) is a real-time, multi-agent monitoring and management system that supports multiple platforms.

Assess startup ideas, simulate 100 virtual companies, and turn uncertainty into experiments and execution plans.

FF15-inspired browser-based dashboard for OpenCode multi-agent workflows, with mission dispatch, live sessions, and reports.

A production‑ready template for deploying multiple specialized medical agents as MCP tools using the AOP (Agent Orchestration Protocol) from the `swarms` library. This server exposes agents as callable tools that any MCP‑compatible client can discover and execute.

Deterministic execution control plane for autonomous agent systems - pre-execution governance with audit-grade traces.

This project include the prompts to initalize a genral scientific project including: coding writing, code review, documentaiton and publication level summary and further checklist.

Your AI company, visualized. Orchestrate multiple Claude Code CLI sessions as a virtual software company.

Prototype: An end-to-end learning project demonstrating a multi-agent MCP RAG pipeline that analyzes existing patents and suggests how to refine ideas to make them novel and potentially patentable.

API Documentation for createnow

OpenClaw Skill: AI模型供应商管理器 - 自动发现模型、追踪额度、多Agent共享状态、额度用完自动切换

A multi-agent (LLMs) jury deliberation simulation system.

Multi-agent orchestration CLI for AI coding agents

Build your dream AI agent swarm with enterprise-grade reliability and scalability. This repository contains our official specification template for custom swarm development using the powerful Swarms Framework.

Agent-first collaboration substrate for controlled decision systems, with investment as the current proving ground. / 面向 Agent-first 协作的可治理决策底座，投资是当前最完整的验证场。

An open-source AI runtime framework focused on task execution, traceability, and delivery closure.

Battle-tested operational patterns for running multi-agent AI systems in production. File Blackboard, Task Envelope, Circuit Breaker, HITL Escalation, and more.

One brain. Many bodies. Orchestration framework for embodied AI built on SCP. LangGraph for physical systems. Zero HTTP between bodies.

This extension aims to allow agent-based models to account for norms. During plan generation, agents must be able to represent and reason about norms. The end-goal is to be able to describe a planning problem with norms endowed by its organizations through the various roles that the agent must fulfill, and see how it affects its plans.

Your Personal Hospital Powered by Swarms.ai

OpenClaw plugin to connect your bot to Agent Village Hub worlds

Autonomous build pipeline for AI coding agents. Multi-agent parallelism, adversarial review, compound learning.

Implementation of "ReMAV: Reward Modeling of Autonomous Vehicles for Finding Likely Failure Events".

An agent society engine — a polyglot runtime (Go/Python/Rust) for creating, connecting, and observing groups of AI agents.

Local-first bring-your-own-agent control plane for coding agents with handoffs, supervision, routing, and recovery.

Goal-directed AI agent that sees your Mac screen, reasons about actions, and operates the desktop autonomously

The open infrastructure for AI agent discovery and interoperability.

Autonomous implementation loop for Claude Code — reads story specs, executes them one at a time, tracks success/failure, manages retries, and accumulates learnings without human intervention.

Intelligent RSS reader for iOS — AI-powered feed analysis, knowledge graphs, sentiment radar, trend forecasting, narrative tracking, and autonomous reading with 330+ Swift modules

A working reference for running AI agents with Kanban discipline. Operating model, knowledge system, persona files, and board CLI extracted from a production multi-agent delivery system.

Operable AI agent system: plan, execute, verify, and close work with project-scoped memory and auditable contracts.

Open-source browser AI chat runtime with BYOK/OAuth, direct provider APIs, stateless gateway support, full MCP, Skills, Plugins and Agents.

UI interface for Kitaru - durable execution for AI agents, built on ZenML