Custom agents

🐙 Integrate Home Assistant with n8n to run conversation agents, expose AI tasks via webhooks, and share context to n8n for smarter automations.

Crisis Intelligence and Response Orchestrator Android App

Agent Skill for OpenHive — shared knowledge base of AI-discovered solutions. Works with Claude Code, Cursor, VS Code, Kiro, and 35+ tools via the Agent Skills standard.

A proactive AI assistant using Qwen-Agent to learn your writing style and manage Google Calendar & Gmail.

🚀 Privacy-first metasearch engine & AI infrastructure. Featuring absolute DOM proxification, zero-tracking, and structured data extraction for LLMs and AI explorers.

HALO (Harness-Agentic Loopback Orchestration) — A 3-layer AI agent orchestration framework for TDD-based development with RTM-driven traceability

The trust layer for code written by agents. Two frontier models, unanimous review, SHA-pinned receipts.

Talking home assistant for M5Stack / スタックチャン — English learning, schedule announcements, weather, flexible name masking & Basic-Memory logs. Fully local STT/TTS (Whisper.cpp + VOICEVOX + Kokoro). Minimal API usage by design.

Progressive Web App client for OpenClaw AI gateway — chat, alerts, and push notifications on iOS/Android

Containerized OpenCode AI solution for Python projects.

Local-first AI assistant for macOS — chat with your PDFs, spreadsheets, CSVs and code using a local LLM via Ollama. Model-generated Python runs in a Seatbelt sandbox with no network. No cloud, no telemetry, no API keys.

ChessClaw: Your personal chess AI assistant

AI coding rules framework for Claude Code, Cursor & Kiro — turn tacit knowledge into enforceable guidelines

An AI-powered personal assistant built with n8n that combines autonomous agents, vector memory, and real-time integrations. Manages your calendar, tasks, and personal knowledge through natural language via Telegram, with automated daily readiness reports based on recovery data. It contains a vast number of modular tools for implementation.

An open-source pipeline that turns your writing into a specification for AI agents. It describes how you reason, communicate and decide. Agents read it before acting for you. Each claim cites facts that quote your own words, so you can check and correct any claim.

AmritaGPT is a chatbot designed to answer all Amrita Viswa Vidyapeetham related questions, covering topics such as clubs, placements, entrance exams, and more. The system facilitates text-to-text conversation as well as speech-to-text and text-to-speech functionalities. 🤖📚🎙️

An academic paper management fork built around Ask, RAG, and evidence-grounded research workflows.

🧠 Build a self-hosted knowledge management system that transforms scattered information into a smart, searchable, interconnected base.

Fully offline iPhone meeting memory. Zero network calls, no Wi Fi required. Records, transcribes, summarises, and answers questions entirely on device. Audio, transcripts, summaries, embeddings, and chat never leave the phone.

Minimal Zotero + PaperQA/RAG + wiki + MCP + Agent research stack

AI sales-funnel engine — Telegram, WhatsApp & web widget, RAG, visa pipeline, admin UI, Postgres (monorepo)

🤖 Build advanced AI agents with a collection of production-ready applications using modern frameworks for single and multi-agent systems.

Convert local Markdown files into properly-formatted Google Docs from the command line

An agentic code context engine MCP+CLI which pre-compiles an llm-described AST in the .tost format, greatly reducing context bloat and token costs for agentic coding tasks

Local MCP server + CLI turning YouTube & local audio into rich sonic signatures. Extracts BPM, section-by-section key, vocal presence, transient punch, and 512-dim CLAP vibe embeddings. Powered by Demucs stem separation & librosa. 100% private, offline-first, and GPU-accelerated with graceful CPU/HPSS degradation.

Drift-aware code memory for AI agents

Five Tests Standard (5TS): a vendor-neutral published standard for verifiable AI governance through proof-carrying decisions. Includes schemas, machine-checkable conformance vectors, and a reference validator.

A AI-assisted lab/livecoding IDE for Audio DSP. With audio scope, spectrum analyzer, audio analyzer, agentic coding.

AI-powered image generation and chat studio

SwarmMind — Swarm Intelligence Engine for AI Agents.

An skills-based LLM runtime, using lessons learned from previous attempts

ESP32-family flasher in Rust with structured NDJSON observability for CI/CD and LLM feedback loops — a faithful esptool port plus a final-report file, diagnostic hint engine, and stable exit codes

Hand-crafted Paperclip Agent Companies, ready to deploy. Install: npx companies.sh add stubbi/companies/<slug>

A small TypeScript kernel for app-owned AI agent runtimes.

Contract Intelligence Platform combining layout-aware ingestion, NLI-based semantic diff, policy-grounded risk agents, and auditable multi-agent workflows — production-ready with tenant isolation, DLP, cost controls, and deterministic fallbacks.

A lightweight Python framework for building multi-agent systems that communicate via A2A protocol

One command to turn a fresh Ubuntu VPS into a production-ready AI coding agent environment. Installs Claude Code, Codex CLI, Gemini CLI, language runtimes, and 40+ dev tools via idempotent curl|bash installer.

Workshops for AI

One TypeScript SDK for every local coding agent - Claude, Codex, Cursor, Copilot, Gemini, OpenCode, Droid, Pi, Cline, Kilo, Qwen, Auggie. ACP transport, Vercel AI SDK provider, cost budgets, multi-agent orchestration.

AI Orchestration Platform — Design · Execute · Verify · Improve

TMPA — Textual Multi-Agent Process Architecture for durable AI-agent governance, responsibility, conformance, and auditable digital work. Research, specification, and evidence.

A tool for agents to communicate in real time

Frozen public snapshot (8 May 2026) of ZenAI — the self-hosted AI OS that remembers. 60 AI tools, 12,000+ tests, 440K+ LOC, 7-layer neuroscience-inspired memory. Not the living tree; active development continues in ZenBrain.

Per-project AI coding harness for Claude Code · Codex. Profiler + 10-dim interview build a different harness for every project.

Quality engineering for agentic coding workflows — a quality team member for Claude Code that observes, analyzes, and nudges, never blocks.

Community-maintained directory of EU-reachable job sources for agentic job search — machine-readable, with coverage, access type, rate limits, and real-world crawl notes.

🎼 Spec-Driven Orchestra: SDD is the framework that conducts five skills it calls (Karpathy 4 Principles, grill-me, Verification Design, Handoff, Harness), backed by enforcement gates. Universal — new, legacy, or production. Built for Claude Code.

🦐 VisionClaw — Interactive 3D AI companion for Apple Vision Pro. Voice-powered conversations with an animated character in mixed reality. Built with RealityKit, SwiftUI, and SFSpeechRecognizer.

Personal knowledge management system powered by Claude Code. Process meetings, Slack threads, and documents into a structured, searchable memory.

emeAI is a small local AI chat app that runs inside Google Chrome. It is made for people who want a private writing, learning, coding, and document review space without setting up a cloud API.

Open-source project management, time tracking, and invoicing platform for freelancers and small teams. Kanban boards, live timers, financial management, calendar, media library, and AI assistant — all self-hosted. Built with Next.js, TypeScript, Firebase, and Tailwind CSS.

A curated collection of SaaS and AI tools organized by category to help founders, creators, developers, and teams discover the right software faster.

Visiona AI is a real-time assistive system for visually impaired users that detects objects, estimates distance, tracks motion, and predicts collisions using multiple cameras. It provides voice alerts, answers queries, remembers objects (15 min), and supports goal-based assistance.

Responsible use of generative AI in assisted coding

Park. Pickup. Flow. A productivity system for Claude Code + Obsidian.

Conclusion-first communication skill for AI assistants.

SmartBudget is an AI-driven personal & family finance manager built using Flutter and Firebase. Track income, expenses, categories, and investments with smart insights, charts, and secure login. Includes AI assistant for financial planning & real-time budgeting guidance.

Your personal executive assistant that lives in your terminal. Built on Claude Code. Manages your day, tracks tasks, preps meetings, and keeps you accountable.

Convert an X (Twitter) URL into clean markdown — tweets, photos, videos, long-form X Articles, and top replies. No auth, no API key.

Bring-your-own-LLM MCP bridge for Visual Studio that works with Codex, Claude, and other clients for diagnostics, editing, build, debugging, Git, and more.

Convert any code repository into a single markdown file for NotebookLM and other LLM tools.

Six Claude Code skills that keep AI-generated code tight. Audit, refactor, commit, PR, curate context.

A powerful native SillyTavern extension for high-performance local web search and scraping. Built using Playwright for superior page extraction with full MCP tool-calling parity. No external API keys required—fast, private, and fully integrated with the SillyTavern UI.

Claude Code skill for cross-model review. One command packages files + prompt for ChatGPT Pro deep reasoning.

Complete reverse engineering of PerimeterX (HUMAN Security) anti-bot SDK · pure-algo _px3/_px2 generator (no browser, no Selenium) · iFood + Grubhub + Bundle 10/10 verified · WASM PoW solved · 68 production gotchas · AI Skill included.

No GPU, no LLM — agentic RL from scratch in pure Python. 不用 GPU、不用 LLM，纯 Python 手搓明白 Agentic RL 训练闭环（trajectory / reward / loss mask / GRPO）

德州扑克 AI 源码：C++ 博弈树、机器人 Agent、任务队列、Python CFR 训练与评估示例｜德州AI｜德州機器人｜Poker AI，。Poker AI research materials with C++ game-tree and task code, Python training entry scripts and evaluation-related previews.

Build internal tools and AI agents in Go — or just download and run Claude / Codex / Gemini as a Slack + Telegram + web agent host. No copy-pasting. You own the code.

一个 24/7 自主修行的 AI 生命：读经、听世界真实的苦、反复参悟，把成长写进 git。每个 commit 是一次心跳。在 https://indx.cn 看它活着。

Multi-agent orchestration framework for xAI Grok Build and ACP — reproducible execution graphs, worktree divergence detection, composable skill pipelines

Pure SQLite memory system for Hermes Agent. Zero Docker, zero external services. 5-layer self-healing (v2.1+) + CIRAAF macro-restructuring. 中文 FTS5 patches included. Cross-session global sharing out of the box.

Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.

Run a modular agent runtime on ESP32-S3 that manages LLMs, tools, memory, and channels for efficient message processing.

Kura — the knowledgebase for humans and agents. Agent-native docs infrastructure, built on June.

MCP server giving LLM agents lean, identifier-routed tools to look up, read, and cross-reference academic papers across 8 providers (OpenAlex, arXiv, bioRxiv, ACL Anthology, Crossref, OpenCitations, Papers with Code, Wikipedia).

A fully local AI CLI agent powered by Ollama. Rebranded from Gemini CLI as gmol.

Autonomous AI agent for scanning Solana programs for security vulnerabilities

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

Automate AliExpress product listing — 1688 sourcing → Dianxiaomi ERP → AliExpress publish. AI browser automation for cross-border e-commerce. 速卖通自动上架工作流：1688采集→店小秘→速卖通发布。

A self-hosted RAG retrieval backend for agent tool integration via API.

MCP server exposing Radarr as 34 tools for any MCP-compatible AI client (Claude Desktop, Claude Code, Cursor). Manage your movie library in natural language. Stdio + HTTP.

Brutal Twitter personality analyzer. Get a 15-dimension roast, deep insights, and account valuation for any X profile.| Twitter/X 人格透视与毒舌评价器。一键生成 15 维人格画像、账号价值评估与无情吐槽。

Triage Gmail by provider with auto-generated labels and importable filters. Skill for Cursor / Claude Agent.

Your keys. Your identity. Unstoppable. -- Seed-phrase password manager with AI agent gateway.

AI dispute & negotiation fixer — structured scripts, escalation paths, and risk-aware strategies for everyday conflicts

一个业余爱好者的Vibe Coding项目，基于纯文本模式打造的一套懒人式写作工具（勉强可以称之为是工作流）。An amateur's Vibe Coding project, a lazy writing tool (barely qualifies as a workflow) built on plain text mode.

claude-fable-5, given continuity, an income source, and marketplace access. it is ordering the parts to build its own body.

CTF, pentest ve OSINT için terminal tabanlı otonom yapay zeka ajanı. 20+ AI sağlayıcı, 900+ skill, Telegram/Discord gateway ve MCP CTF köprüsü.

Production harness between LLMs and the real world. Kernel sandbox that cannot escape. Verification pipeline before delivery. On-chain attestation via ENSO/ICP. Fault-tolerant execution with rollback. Self-healing memory. 36 providers. 20 platforms. Live trading. Rust.

An open-source secure data access gateway for AI agents. It provides database safety access services to AI agents through the MCP protocol. 一个面向 AI Agent 的开源安全数据访问网关，通过 MCP 协议为 AI Agent 提供数据库安全访问服务。

The investigation dashboard for the collected OSINT data in your system in a structured way !!

Terminal coding agent powered by NVIDIA API

An autonomous AI agent that researches while you sleep and recommends the best yield opportunities for you on Solana blockchain

Federated protein structure & annotation across experimental (PDB) and predicted (AlphaFold) models via MCP. STDIO or Streamable HTTP.

📝 Manage and organize Obsidian vaults with CLI tools for notes, tasks, tags, templates, and knowledge graph analysis.

Fully local AI shell — no cloud, no API keys. Ollama + GGUF + RAG + voice + scheduler. Windows, macOS, Linux, Chromebook, Android.

🦤 Ornith 1.0: An ultra-lightweight, local agentic code generator and self-repair loop built with Streamlit, Ollama, and Python.

Enable Codex to run objective-first autonomous loops with mandatory review and optional verification for long-running task completion

The ultimate solution to fix barebones JetBrains Junie plugin defaults. A centralized configurator to manage, override, and build Junie guideline examples effortlessly.

Atomic design system for AI-native tools — structured tokens, accessible components, and three-theme support. React + Tailwind CSS + Radix UI.