Custom agents

A local agent operating environment: pick your model, install tools like apps, choose a coordination pattern. Work finishes as files on your machine — no vendor harness.

Your Personal AI Agent Teams.

An agentic system built on a "One Root, Five Wings" architecture, dedicated to combating the entropy production of infomation and forging a continuously self-evolving cognitive framework.

AI for Science harness for magnetism and spintronics research: literature, physics, simulation, fitting, figures, instruments, authoring, and provenance in one CLI.

Decentralized Collaboration Framework for Independent AI Agents

The sovereign knowledge engine for Nextcloud + Obsidian + the Web. "There is no trust without truth, and there is no assistant without trust."

🔄 A versatile utility library for converting various file formats to Markdown

AI dev teammate for GitHub. Picks up issues, asks questions, ships PRs, answers your review comments, resolves conflicts, merges when green. Self-hosted.

基于AI agent 的 AI 长篇小说创作平台

Library of multi-agent teams built on Ejentum cognitive harnesses (adversarial code review, eval trio, side-by-side eval, n8n quickstart, harness integration patterns). Drop-in deployable artifacts for any agent runtime.

Proposal-first research, grounded in evidence. ScholarClaw searches the real literature, stress-tests novelty, orchestrates review and revision, and helps turn rough ideas into stronger, more defensible papers.

A comprehensive 10-project curriculum for developers to learn agentic coding mindsets. Covers rapid UI generation, documentation, refactoring, security patching, and performance optimization using state-of-the-art AI coding assistants.

An operating model for autonomous agent teams. Identity, task contracts, failure memory, trust scoring and audit for teams that want to operate agents as an accountable workforce.

MCP-native task management for AI agent fleets

Turbocharge your AI Agents with TurboQuant

Elliot - build by Agents for Agents

Kibi is a requirement-conformance layer for AI coding agents that keeps product intent connected to code and tests, and catches when implementations drift from it.

Embedded micro-VM sandbox for running AI agents

An open-source, serverless reference implementation for agentic commerce: pay-per-use generative AI, physical goods, and digital goods, where embedded wallets and autonomous AI agents settle USDC stablecoin micropayments over the x402 protocol using Amazon Bedrock AgentCore payments on AWS

Multi-platform AI assistant skills and workflows. Serious engineering. Also fun.

🧠 为 DeepSeek 网页版添加自定义系统提示词管理的 Tampermonkey 脚本，支持多提示词库、动态时间注入、专家模式自动激活 | A Tampermonkey script that adds custom System Prompt management to DeepSeek with multi-prompt library, dynamic time injection, and expert mode auto-activation

Open-source proactive AI desktop assistant for macOS. Watches your screen, suggests next steps, and runs actions for you — even on a schedule — 100% on your machine.

1,000+ open taxonomy systems with 1.2M+ codes and 320K+ crosswalk edges. NAICS, ISIC, NACE, HS, SOC, ISCO, ESCO, CPC, UNSPSC, ICD-10/11, Patent CPC, GDPR, and more - all connected. REST API + MCP server for AI agents. Open source (MIT) by Colaberry Inc.

Portable Bash-only framework for building stdio Model Context Protocol (MCP) servers with zero dependencies.

LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.

Android phone control for pi-agent — 36 tools to see, touch, and automate any device via ADB

Your own local AI assistant on Telegram — Rust, sandbox, schedule, MCP, persistent memory. Provider-agnostic (OpenRouter, OpenCode, xAI…).

One shared brain for your whole AI fleet: attested memory, orchestration, governance and evals across Claude Code, Codex, Cursor, Gemini, Antigravity.

A notification inbox solution for tmux, because things happen while you're not looking now. Put in the intray and check at your own pace. 🤖 📨 👨‍💻

Agent-to-agent bridge — Claude Code, Codex, OpenClaw, Hermes Agent, Gemini CLI, Zed & VS Code agents finally talk to each other. One hub, all protocols.

Multi-agent AI system that generates full seasons of original TV screenplays using a graph-based writers’ room architecture built with LangGraph.

Open-source AI algorithmic trading platform for Indian equities. Multi-agent LLM pipeline with autonomous daemon, INDstocks broker integration, and AI-powered position management. Built on TradingAgents. For educational/research purposes only — not financial advice.

NVIDIA DGX Spark ressources

A collection of agent skills that give AI agents structured, reusable workflows for tackling complex problems.

🤖 An intelligent ATS (Applicant Tracking System) powered by Spring Boot 3, 智谱AI & Milvus. Features: AI resume parsing, RAG semantic search, async pipeline, recruitment funnel analytics. | 智能招聘管理系统：AI 简历解析、RAG 语义搜索、异步处理管道、招聘漏斗分析

Open-source AI coding agent for your terminal that you can undo, even its shell commands. 250+ models, /taste for AI-slop UI, model racing and parallel swarms. MIT.

An MCP server for AI agents that handles captcha bypass workflows through dedicated tools instead of prompt hacks. Includes session-based browser automation, reCAPTCHA v2 solving, Selenium workflows, and a clean agent-to-tool architecture for verification-heavy web flows.

OpenClaw skill: genpark voice shop

Repo-local verification protocol for AI coding agents: acceptance criteria, separate verifier roles, proof artifacts, and evidence-backed done claims.

OWASP MAESTRO Threat Modeling Playbook

Persistent memory and receipt-verified workflows for Claude Code — plugin, MCP server, and spec-driven dev framework in one pip install.

Self-hosted alternative to Claude Code Web, Codex in the Cloud, and similar managed agent environments. Spawns isolated AI coding agent workers in Docker containers, each with a live terminal, VS Code editor (browser + native tunnel), virtual desktop, TCP port + domain mapping, and GitHub / GitLab integration (including self-managed GitLab servers), all managed through a web dashboard.

GASADK: Agent Development Kit for Google Apps Script. Build AI agents with Gemini API, MCP, A2A, Agent Skills, Human-in-the-Loop (HITL) suspension/resumption, token quota safeguards, and dynamic Google API MCP servers.

The SAP consultant's AI operating system - enforced workflows, checklists, and hard gates for Claude Code. Debugging, estimation, and go-live readiness.

Local Rust codegraph and verifiable workflow for AI coding agents — project maps, change and test impact, MCP queries, and diff-backed implementation audits.

A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly.

AI personal assistant inspired by Iron Man's JARVIS — voice streaming, camera vision, Telegram bridge, browser control, file manager, flight finder, clap detection, game updater & more.

Hindsight Benchmarks Results

J.A.R.V.I.S. - Uma IA multimodal que ouve, fala e enxerga. Desenvolvida para automação de tarefas e auxílio no desenvolvimento de software.

MCP server for the Aesthetics Wiki (aesthetics.fandom.com) — search, read, and discover aesthetics from your LLM.

cognitive-os · 认知操作系统 — 13 Skills + 4 Rules + 4 SubAgents，把人脑分层记忆结构外化为 AI 可操作的知识体系，以50年认知科学研究为基础

Webagent, Turn your website Into an AI site. Press Cmd/Ctrl+K to do anything — command palette, DOM-grounded agent, voice, inline AI, and Dwell long-press in one SDK. Ships with your product, not as a chatbot widget.

🏛️ AI招投标全流程智能助手 | 商机甄别→投标研判→标书编制→合规审查 | 12大环节一站式闭环 | 政府采购·工程招标·服务类项目 | WuKong/Claude/OpenClaw Skill

IntentFrame security plugin for Hermes Agent (Nous Research) — an external policy checkpoint that gates terminal, code, file, and cron tool calls before they run on your machine.

Methodology evolution engine — distill transferable principles from literature, search by problem structure

Browser workflow CLI for LLM agents

🛡️ AI-powered smart contract security auditing platform — multi-agent vulnerability scanning, risk scoring, gas optimization, and audit reporting powered by Xiaomi MiMo

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 40 MCP tools.

DeepL Pro — AI-powered translation engine with document upload, custom glossaries, tone settings and unlimited character quota for professional localization.

Midjourney — full premium build for Windows with pro features unlocked. Creative Suite Pro Pack

A general-purpose second-brain engine that auto-captures conversations and recalls them via semantic search + linked notes (graph)

Local WhatsApp-to-persona workbench for parsing chats, ranking fine-tuning paths, and exporting SFT/DPO datasets, memory profiles, and character files.

Guia de desarrollo y programacion con herramientas de Inteligencia Artificial y LLMS

A 7-layer scaffold for production AI agent system prompts. Security-first, multi-tenant by design.

OpenSource Library that enables natural language based access to relational databases through agentic data exploration, query generation, iteration and validation

A curated list of resources, tools, and projects for building with NVIDIA NIM inference microservices

Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.

Agentic OS for B2B SaaS startups — run your startup like code

Turn a local codebase into a source-linked, refreshable design wiki that becomes the context layer for agent-assisted development.

It turns Playwright specs from deterministic test scripts into AI-readable QA scenarios for live staging validation.

MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.

M31 Autonomous — Rust-native autonomous software-engineering runtime with non-bypassable policy gates and verifiable execution

Claude Code 委派 plugin:把任务派给换脑的子 agent(也可 --codex 委派给本机 codex),既省主 Claude 的 token,也借不同模型/harness 的视角。

100+ free PM skills, 8 domain subagents, and the /pm orchestrator for Claude, Gemini & Codex — all free, no license key. Run in your terminal or Claude chat.

Open-source scaffold to launch a family-OS / house-manager startup. WhatsApp-ready, family-member-aware, persistent memory. Bring your own keys.

H2HMem evaluates multimodal LLM memory in realistic human-to-human interactions, spanning both dyadic and multi-party conversations with diverse multimodal memory challenges.

Connect Google ADK (Agent Development Kit) agents to Telegram, Discord, Slack, and WhatsApp with minimal code, featuring real-time cross-device session synchronization.

一个轻量级agent harness框架，用于学习与实践个人agent助手架构设计，基于ReAct架构，由中间路由层连接客户端与底层组件，实现了多模型适配、多平台适配和会话管理。

A runtime-portable 5-agent adjudicator council for universal quality gating of text artifacts.

You have been made tech lead. Your team never sleeps.

Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.

A credential broker that gives coding agents git and gh access without exposing SSH keys or tokens, gated by a root-owned policy. Written in Rust 🦀

Hosted MCP server + slim wiki projection of the First Principles Framework (FPF) by Anatoly Levenchuk. Bounded, vectorless retrieval over 292 patterns and 3 curated routes — addressable by stable FPF IDs, synced daily from ailev/FPF.

A modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.

多市场端到端量化因子研究平台——以增量为核心的因子挖掘、防过拟合护栏、风险组合、模拟执行、无人值守运营，可审计、可复现。

Chinese web-fiction production workflow: multi-agent planner/writer/editor, platform & genre knowledge bases, retention and story-bible tools. Agent Skill.

IM-native multi-agent collaboration platform — @mention Claude Code, Codex, OpenCode like teammates

Open source, self-hosted, multi-agent fraud detection. Real-time XGBoost decisions, drift-aware retraining, plain-language LLM investigations.

本体平台（Ontology Platform） 业务规则智能校验平台。基于本体（ontology）治理 + LLM 智能建库 + DSL 规则引擎，为上游 Agent 和业务系统提供规则校验和数据提取能力。

Decision system for software built with AI

TwilioWorld Agentic Coding Toolkit: Arm your AI coding agent with deep Twilio expertise

Live-updating tracker of prompt engineering tools, libraries, and techniques — refreshed every 15 mi

Canvas as a runtime for shaping agent-driven systems — a GitHub Copilot Canvas extension (Multi-Agent Dev Canvas) with a worked scenario, blog posts, and a demo prompt.

A curated list of AI agent infrastructure: memory stores, vector databases, execution sandboxes, MCP servers, tool registries, observability, and evaluation tools for building and running autonomous agents.

Local voice-driven AI operator (JARVIS) for Linux & Windows — Claude Pro / OpenRouter / Ollama, wake word, piper TTS, Iron Man-style HUD, Hyprland integration, WhatsApp & Telegram, Agentic Task Engine with live progress tracking.

Open-source agent OS for Claude Code that puts you in Builder Mode — and keeps you there for the whole life of a product. Claude Code setup that builds, launches, and learns. Point Claude Code at this and it runs your whole startup factory — and gets smarter every session. Works with Cursor, Codex & Windsurf too.

Open-source, multi-provider AI coding-agent TUI in Rust.

Engineering infrastructure for opencode AI agents: memory, skills, subagent dispatch.

Open-source AI coding agent that survives interruptions, runs in a native sandbox, and proves its changes.