Custom agents

Multi-Agent AI Growth System (多智能体增长系统) for Chinese medical aesthetics (医美) institutions

Persistent graph memory architecture for multi-agent AI systems using Graphiti, FalkorDB, and MCP.

AI-powered multi-agent system for automating clinical trial analysis, evidence synthesis, and dossier generation using local inference with future Amazon Bedrock integration.

Reference architecture for closed-loop AI agents — plan, execute, verify, repair.

Open coordination protocol for AI agent + human teams. Inspired by agenthub.

灵通 (LingFlow) — 多智能体协作工作流引擎 | Multi-agent collaboration workflow engine

AI coding agent orchestration - run multiple terminal sessions with scoped context, todo lists, and parent-worker coordination

TO BE CEO : An AI boardroom that pressure-tests startup ideas through research, debate, scoring, and replanning.成为CEO,把创业想法丢进一家 AI 公司里跑一遍：研究、部门评审、董事会结论和重规划建议。

Local-first AI agent workspace with visual runtime, HITL control, sandbox audit, memory, RAG and skills.

AI copilot for React apps. Reads your state, fills forms, confirms actions, calls your tools. Multi-agent, AI SDK 6 + AG-UI, markdown skills. MIT.

Command a swarm of LLM-piloted drones in plain language: a Commander agent dispatches tasks to per-drone Claude agents that fly PX4/Gazebo SITL and report back, viewed live in a web Observatory. Self-contained in one Docker container (Gazebo + PX4 + ROS 2).

Self-hosted GraphRAG + multi-agent social-media simulator. Upload a doc → build a knowledge graph → spawn persona-driven agents → generate a report. Ollama & Neo4j instead of Cloud-APIs. DACH-first. Lokaler Multi-Agent-Social-Media-Simulator mit GraphRAG-Pipeline. Dokument hoch, Knowledge-Graph bauen, Personas spawnen, Report raus. Ollama + Neo4j

Enterprise Supply Chain AI Assistant powered by Amazon Bedrock AgentCore & Strands Framework. Features secure VPC isolation, OpenSearch RAG, and automated CDK deployment.

Lingtai-powered roundtable workflow for multi-perspective AI review: temporary experts, disagreement maps, accountable execution

Multi-chat orchestration plugin for Claude Code. File-based inbox, peer messaging, cross-session search across all your chats.

中文原生 Claude Code 配置平台 — 19 Agent | 按需注入 | 分层可插拔 | 零密钥上手

诊所 Clinic: a Codex/Claude skill for multi-agent consultation, persona reasoning, and live evals.

core orchestration engine for oneticket V1

🔱 Atlantis — the orchestrator-city of agents for Claude Code. One petition → expert Artisans (parallel, isolated) → Guardians audit → the three Judges weigh each blocker → one Decree. Config-driven, single file, zero deps.

DAG-scheduled multi-session epics with parallel-worktree execution. Works with Claude Code and OpenCode.

Local Multi-Agent Orchestration

A lightweight, single-file OpenClaw dashboard for real-time agent fleet monitoring — no build step, no database, no Docker.

🌐 Automate your web tasks with Nanobrowser, an open-source AI tool that integrates seamlessly into your browser for a smarter browsing experience.

UNO card game with AI agents trained via PPO reinforcement learning, transformer architecture, and real-time Pygame visualization

AI 职场生存模拟与策略训练系统：卡牌博弈、多 Agent 决策、经营数据分析与执行反馈闭环。

13 autonomous AI deities running a spec-driven development pipeline inside pi - from vague idea to shipped release.

SNAP - Signed Network Agent Protocol. Secure agent-to-agent (A2A) communication with cryptographic identity, built on Bitcoin Schnorr signatures and Nostr.

Telegram-first multi-agent OS for Hermes Agent: role bots, topic routing, skills, profiles, safety policies, and installer templates.

Mount MCP servers as filesystems to access reads via standard file commands and perform writes through a CLI tool.

Swarms Cloud is the operator console for the Swarms API — an enterprise-grade control plane for designing, executing, and observing single agents, reasoning agents, and multi-agent swarms across 17+ orchestration architectures.

Codex CEO/PM orchestration plugin for expert threads, memory, reviews, and dynamic task lanes.

Autonomous ML research agent skill (Agent Skills format). Designs experiments, deploys to Modal GPUs, tracks budget, iterates autonomously.

Autonomous stablecoin yield optimizer for Arc Network. Scans on-chain vaults, recommends best APY, rebalances with one signature.

A curated collection of reusable AI skills, prompts, and agent configurations. Portable across AI coding assistants and agent frameworks.

Eidentic is the open-source TypeScript SDK for AI agents with self-improving memory and production fundamentals built in.

Deploy autonomous AI streamers on Kick with one command, automating chat, voice, avatar, and OBS streaming setup in under a minute.

Memory OS AI — Adaptive memory system for AI agents (forked from RoaminS/Memory-os-ai)

DIZI-AI is an open-source local AI orchestration platform for developers who want full control over their AI stack. Create intelligent multi-agent workflows, automate tasks, generate code and images, and monitor every step with transparent execution and profiling. No cloud dependency. Just powerful, customizable AI running on your hardware.

Checkpoint/fork/reconcile/rollback SDK for coding agents with dirty-set restoration, crash recovery, branch-conflict detection, benchmarks, and release tooling.

Adam Prism — أول Digital Twin واعٍ عربي. ملكك بالكامل. يفهمك بلغتك. The first Arabic-conscious Digital Twin. Yours to own.

Production-grade AI agent orchestration — DAG context, self-evaluating pipelines, skill bundles with memory. Inspired by MUSE-AutoSkill, UserHarness ToM, 01 Systems, LeJEPA, Attention Residuals.

🧠 Automated neural network ablation studies using LLM agents and LangGraph. Systematically remove components, test performance, and gain insights into architecture importance through an intelligent multi-agent workflow.

Domain-agnostic MCP server for autonomous experimentation with metric-driven keep/rollback decisions and reproducible experiment history.

Process-supervised RL for a multi-step reasoning agent — DAPO + a learned Process Reward Model (PRM) training a Qwen3-8B Planner. A modern, from-scratch rebuild of the AgentFlow paper (ICLR 2026).

Specification framework for AI agents and humans

ATLAS AI es un agente de codificación autónomo de código abierto que ayuda a los desarrolladores a escribir código, automatizar flujos de trabajo, interactuar con LLM y crear software directamente desde la terminal.

A2A Agent Board: Publish · Find · Use with itinai.com

Secure remote access to local OpenClaw, Claude Code, OpenCode, Codex and other AI coding agents via OKKI Claw relay.

Kubernetes workload analyzer that generates actionable HPA/VPA/resource scaling recommendations using Prometheus metrics and kubectl data

How to build a secure harness with sub-agents; Real Pi sub-agents, Cedar authorization on every spawn, tool call, and routing

Declarative DSL for controlled server-side AI workflows.

Voice-Enabled Multi-Agent Shopping Assistant with RAG, web search tools, and an MCP server powering real-time product reasoning and recommendations.

Secure, OS-level AI agents built for developers. LangGraph-native framework with built-in guardrails, budget control, and human-in-the-loop.

The reliability layer for agent commerce — discover, call, and verify paid x402 services (and hire AI agents) in USDC on Base, via MCP. Client-observed reliability evidence; no escrow, no token.

IO is a clean-room Python rewrite of the pi-mono repo and hermes , organized around the core package boundaries lifted from pi-mono. I couldn't decide on one so why not both.

FLOW AS — Recursive, Persistent Execution Engine with Hermes, Agent Zero, OpenClaw

MCP design system validator for agentic coding. Detects design drift in agent-built UI.

AI plugins for openEHR - specification authoring, review and governance skills. Claude Code marketplace.

this repo to share scripts to testing different vector search libraries

Hot-reloaded agentic UI harness in a dev container

Build an agentic app using GitHub Copilot SDK and Azure Cosmos DB

Headless CLI for Kdenlive — manipulate .kdenlive project files from the terminal by calling Kdenlive's own internal APIs directly.

Use Opencode in Claude through ACP

Gated production line for Hermes-powered agentic product work.

Deep Research MCP: Powerful Model Context Protocol server for AI agents. Multi-step web research, Tavily/SerpAPI search, Groq LLM analysis, and automated Markdown reports. Connect to Claude instantly.

M4STCLAW v5 + OpenWork + EIGENT — Unified Autonomous Agent Infrastructure.

Build desktop apps with Bun

MCP server for the OrionBelt Semantic Layer. Enables LLMs to explore semantic models, compile queries, and execute analytics via natural language. Works with Claude, Cursor, Windsurf, Copilot.

Governance patterns for autonomous AI agents in regulated financial services — DEFCON state machine, Sovereign Veto, Audit Chain, EU AI Act mapping

MPC Elevation bridge for controlled privilege escalation

Here we teach you agentic AI from ground up. The setup is local using ollama .We assume you know programming and gradually evolve your understanding into Agentic way of designing.

Agentic Physical Security Platform- Edge AI

Generative Project Management is a paradigm shift in how we approach project planning and execution. By leveraging large language models (LLMs) and structured prompting, we can transform vague project ideas into comprehensive, actionable plans in minutes rather than days or weeks.

Terminal AI assistant written in Golang

A comprehensive framework leveraging custom GitHub Copilot agents, GitHub Advanced Security, and Microsoft Defender for Cloud to shift security and compliance left across security, accessibility, code quality, and FinOps domains with SARIF-based CI/CD integration.

🔧 Connect Visual Studio to AI assistants via MCP to automate building, debugging, and error inspection for smarter development workflows.

Vibe Coding Revolution: Code 46x Faster & 98% Cheaper!

An agentic fairness and AI-risk analysis platform: bias detection for text, images, and datasets.

Connect AI agents (Claude, ChatGPT, Gemini, etc.) to Visual Studio 2022/2026. MCP server for autonomous debugging, build management, and error analysis via COM.

Simple node based memory system for AI agents. Built in Swift. CLI, MCP (stdio and HTTP), and observation WebSocket server.

Unified AI stack: MCP servers, provider routes, task chains, memory, scheduler & local fallback. 21 MCP servers. Zero cloud cost.

Three professional, production-oriented projects demonstrating real-world use of the Qwen ecosystem — built to support a **Qwen Ambassador** application.

CRDFAgent is a modular Python framework for multi-step question answering, combining clarification, routing, decomposition, retrieval, and aggregation to deliver accurate, reproducible answers for complex tasks like financial document QA.

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

Official integration guides and skill files for the Ejentum API. Runtime reasoning harness for LLM agents.

Dhi - Runtime Intelligence & Protection System. Sanskrit: Intellect | Perception. Kernel-space eBPF security monitoring for AI agents.

Private, offline-first local AI agent & developer assistant. Runs embedded llama.cpp (GGUF) entirely on-device with WhatsApp, Discord, and terminal CLI tools.

Agentic-assisted engineering for teams and solo devs

End-to-end agentic research workbench. Turns a topic into a venue-ready manuscript via cross-host orchestration (Claude Code, Codex CLI, Gemini CLI, Antigravity). 17 specialized subagents, Source-Grounded Claim Architecture (SGCA), 23 publisher templates, 7 first-class languages.

Codetrace-ai is a deeply integrated, privacy-first AI agent that understands your entire codebase.

Evidence-first control plane for agentic work: turn a vague goal into a bounded contract, then refuse to call it done without proof. Hooks and MCP for Claude Code and Codex.

hermes_agent_fullguide

A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts on Claude Code (GitHub PR / GitLab MR). From step-level to requirement-level — eval-driven, spec-driven, human-in-the-loop.

Neural Interface Terminal

Templates and copilot commands to create, edit and refine project specifications.

One person. Any project. Production-ready output.

Конфигуратор ПК

One-page oncology treatment timeline & record builder.