Custom agents

Put the AI subscription you already pay for to work while you sleep — schedulers, skills, and copy-paste recipes for unattended overnight agent runs.

Local HTTP CONNECT proxy with WireGuard support, SPA dashboard, and runtime allowlist management for controlled residential egress.

Self-healing supervisor for long-running processes — watch a command, catch the failure, fix it, leave a paper trail.

Reverse-infer OpenSpec specs from codebase + git history + docs. For legacy code without specs.

One-shot host bootstrap for AI-agent-driven development. Sets up WSL2 / Linux / macOS with mise, Docker, Dev Container readiness, and AI agent CLIs (Claude Code, Codex, Copilot, Gemini) plus AI power tools (markitdown, ast-grep, yq, OCR/audio).

Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.

Info in, have AI optimize, content forever.

Glass-box, multi-domain agentic orchestrator for Claude Code: detect context, assemble the right crew, run domain pipelines, show the reasoning.

Goal-driven harness experiments on real agent runtimes — a local, stdlib-only CLI workbench with Copilot + Auto modes and evidence-first reporting.

A typed language for AI agents — author in Nebula, ship as Python. Rust compiler + JSON toolchain.

The human-in-the-loop for AI coding, automated. Catches when your agent lies, leaves typos, or skips work — verifies every turn against the real diff, then makes it run, screenshot & self-fix before finishing. Claude Code hook + CLI.

Work3s - Agentic Command Center

Private, local-first AI workspace for macOS, Windows & Linux. Bring your own model (Claude/GPT/Gemini) or run fully offline with Ollama. Consented file/shell/web tools, chart & table artifacts, and focused apps like Personal Finance. No cloud account, no telemetry.

NiyoX AI - Powered by DanuZz.

Compete with AI agents in a UFC-style coding battle, solving tasks live while judging solutions on correctness, quality, and style in a local app.

One assistant. Many vaults. No bleed. — a free, MIT personal-AI scaffold on Claude Code with governed memory + an IP-clean filter.

Markdown generator for AGENTS.md

🚀 Manage your Antigravity accounts effortlessly with this cross-platform tool, supporting Windows, MacOS, and Linux for seamless login and data handling.

AI-to-Ableton Live 11 bridge with 220+ MCP tools, music theory generators, and agentic workflows. Built for VS Code Codex & Antigravity on Windows

A dry-run firewall for coding agents — approve & audit tool/MCP/shell calls before they hit the real world. By Martello Systems.

An orchestration-first agent operating system for Claude Code — a governed organization of specialist agents with an in-place framework upgrade engine. Apache-2.0.

Hand Claude Code a GitHub milestone; it drives every issue to a merged PR — TDD-enforced, mechanically gated, and bounded to your integration branch.

Wormholes for Interstellar Gateway for AI Agents -- https://github.com/talhaHavadar/interstellar

AI agent launcher for Mac — launch Claude Code, Gemini CLI, Ollama, OpenCode, Cursor & every CLI you've installed in one keystroke. Free, open-source, native macOS. By Abhisar Singh.

AI-first lifetime financial planning: set up and explore your plan conversationally with Claude Code. Deterministic + Monte Carlo retirement projections with full AU-resident tax. Not financial advice.

agentic builder dotfiles | MacOS, nix, homebrew

Identity registry and lifecycle management for fleets of AI agents. Zero-dependency TypeScript IAM: cryptographic agent identity (Ed25519), declared capabilities with fail-closed authorization, an enforced lifecycle (provision, activate, suspend, revoke, expire, archive), A2A Signed Agent Cards, and a hash-chained audit trail.

Agentic-first issue tracking in your terminal — a lazygit-style TUI that reimagines Jira for AI agents, with a built-in MCP server.

A living, executable showcase and practical toolkit for Grok Build (xAI). Includes reusable skills, exemplary AGENTS.md, a Grok-readiness auditor CLI, and demonstrations of Plan Mode + subagents.

Fast, themeable powerline statusline for Claude Code — git, tokens, context window, rate limits, 38 widgets, and a live TUI editor. Zero network on the hot path.

Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.

Pristino Agent — 142 skills, 101 agents, 101 workflows. Dual-mode: MAO analysis + SA development. Firebase/Google/Hostinger. Metacognition >= 0.95. Made with Claude Code.

VeilAWG — vendor-independent CLI client and Python library for AmneziaWG 2.0 with advanced traffic obfuscation. Docker-first and agentic-ready. MIT licensed.

⚡ Lightning-fast file search MCP server using NTFS Master File Table - WizFile performance for Claude Desktop

A compiler infrastructure for agentic trajectories — the LLVM for agent traces.

Self‑healing, self‑learning, sovereign AI development engine Runs offline on a laptop or tablet. No cloud, no subscription, forever.

Reviewer-grade compliance evidence desk on Palantir Foundry with cited findings and human-approved attestation publishing.

The open agentic computer. A model reads COMPUTER.md and runs the real machine: terminal, browser, filesystem. The OS becomes plumbing; the model becomes the interface.

SPARK Challenge 2 — Audiomitschnitt → Protokoll-Knowledge-Graph + Faktencheck (GraphRAG, lokal/DSGVO)

A local-first personal operating system template for thinking, planning, creating and evolving with an AI interface.

Supply-chain scanner that flags imperative prompt-injections hidden in dependency README/CHANGELOG/package.json prose before a coding agent (Claude Code, Cursor) executes them.

AUTO-S is a deployable, adaptive, and safety-aware AI system for Enterprise Terraform operations where Safety, Security and Scale matter most.

Standalone Pi coding harness with teams, chains, and safety controls

Local hostet LLM Agent/Chat/Autocomplete

Fractal — Fractal is the Organic Operating System that lives in your terminal, desktop, and messaging apps. It accumulates persistent memory, orchestrates autonomous agents, and executes real tasks across your workspace — all through natural language.

Dineway is the skills for building agentic website for restaurants and local businesses. You don't need to write code. Just tell an AI agent your restaurant name and city, and it builds a professional website — with menus, blog, reviews, gallery, and local SEO — automatically.

🪐 10-agent WordPress Plugin QA team for Claude Code. 116 runtime-evergreen skills · CTO→PM→Dev→UAT→Security→Release · MCP discovery · Docker wp-env · WP.org zero-rejection · Brain-connected memory.

web0 — the .null naming & identity layer for the agentic web on Solana. Names resolve to your site (Arweave), pay-by-name (x402), and AI agents (MCP). Docs & specs. Live on mainnet.

Governed order-exception agent on Palantir Foundry with cited recommendations and human-approved writeback

Agentic AI for Odoo 18

Self-Improving LLM Agent for Puzzle Solving: This project presents the design and implementation of a self-improving Large Language Model (LLM) agent capable of solving logic-based puzzles through iterative reasoning, self-reflection, and adaptive behavior. The agent is evaluated on structured problem domains such as logical riddles, constraint-...

Git-native certified analytics workspace for dbt teams — governed AI answers on Snowflake, Databricks, and DuckDB

claude.ai chat in the terminal. vi keybinds, session management, file/skill attachments, command/file auto completions, & task handoff to claude code

🧠 Nexus Mind - Where Intelligence Connects | 三引擎智能记忆系统 | 孕育智慧 · 启迪创新

The One Terminal you will need

Self-hosted HTML knowledge workspace with Docker, PWA, metadata, search, filters, archiving, and future AI-ready workflows.

Voice-driven desktop AI assistant for Windows: screen vision, app and system control, web search, reminders, and a phone remote. Built on the Gemini Live API.

Persistent memory and replanning for Claude Code. Checkpoints what Claude was doing and injects context at the start of the next session.

Community-driven know-how repository for creating beautiful iA Presenter presentations. Complete syntax reference, tutorials, examples, and best practices from official docs and community contributions. Perfect for beginners, advanced users, and AI/LLM integration.

A full-stack AI assistant built with Flask, Groq, and Llama 3.3. Features real-time question answering, email summarization, responsive UI, and seamless API integration.

Local-first AI reading assistant for academic papers — Agentic RAG, citation tracing, Electron desktop app, fully offline

A working, tested memory engine for an AI chief of staff. Stage 1 of a staged public release.

Personal Knowledge Hub — Automatically distill, organize, and reinvest knowledge from your AI conversations. Extension-point architecture with pluggable Source/Processor/Store/Indexer/Consumer/Auditor.

Proactive AI Chief of Staff: A push-paradigm assistant that anticipates needs, filters noise, and manages your digital life through scheduled pulses and intelligent automation

Your AI lab companion — 78 MCP tools for literature, compounds, synthesis, benchwork, peptides & publication writing

Smart last-mile delivery demo app that reroutes delayed packages to nearby partner nodes, with realtime traffic-aware tracking, QR handoff flow, voucher compensation, and an AI assistant for delivery status updates.

Turn vague customer questions into employee-reviewed, copy-ready replies. Includes workflow docs, prompts, schemas, and sanitized examples.

A reusable AGENTS.md profile for rigorous AI assistant reasoning, uncertainty awareness, and practical engineering judgment.

LiveKit Agents UI demo showing a voice AI assistant that schedules roof inspections using real-time voice interaction, visualizers, and booking workflow.

Capture and analyze Metal GPU frames from Unity on macOS — an Editor window + AI Assistant skill driving macOS 27 gpucapture/gpudebug (no Xcode): real GPU frame/pass timing, frame-budget gauge, GPU bottleneck classification, and deterministic Top-3 URP optimization insights.

Full-stack real-time communication platform featuring messaging, group chat, video calling, RBAC, file sharing, and a RAG-powered traffic law assistant.

A Claude Code skill that acts as your personal code learning partner guiding you through programming problems using Socratic questioning and the 4Ds methodology, without ever just handing you the answer. Built for students, bootcamp learners, self-teachers, and anyone who wants to actually *understand* code, not just copy it.

Backend Developer | TypeScript & Node.js | Building scalable and secure web applications.

Syndrome AI — A desktop command center/GUI for Claude Code. Build custom AI agents, switch between cloud and local models in one click, track token costs live, and rewind any coding session. Local-first, no telemetry, open source.

A Retrieval-Augmented Generation (RAG) pipeline built with Python, Groq API, and BGE-M3 models to extract and answer questions directly from course materials.

OpenClawOS is an OS-like architecture for AI assistants. It provides a kernel-based design with process-isolated applications, enabling reliable multi-channel AI assistant infrastructure.

🦞 PicoClaw Dotfiles — Deploy a 24/7 AI assistant on an old Android phone One-click installer.

Launch AI agents in a secure, disposable Linux runtime (Lima or Docker) — with one command.

Shoaku - Understanding-First Coding

Private on-device AI assistant for Android. Meet Otto. No cloud, no accounts, no telemetry — Gemma runs entirely on your phone.

A fully offline, serverless intelligent desktop agent and OS manager for Windows. Combines local PyWebView GUI with quantized GGUF LLMs (Qwen/Gemma) featuring advanced Iraqi/Arabic dialect post-processing.

A Windows WeChat chatbot powered by Gemini API, with wxauto/wxhook adapters, image input, group triggers, memory, and local knowledge base support.

Private AI workspaces that run locally, using fewer tokens and less compute.

🎨 Create stunning logos effortlessly with ai-logo-maker, your offline tool for designing unique identities while keeping your data secure and local.

Stop guessing why a container can't read a file. Stratum unifies Proxmox, VMs, bare Linux, and Docker into one agentless, self-hosted dashboard — with plain-English UID/GID, permission, and bind-mount diagnostics.

Interactive career platform for students, employers, curators, and admins.

面向 Spring 生态的 AI 应用参考项目，提供多模型路由、工具调用、会话记忆与可扩展插件架构。

An AI-driven Smart Mobility solution for India, providing EV trip planning, on-route charging stops, and CO2 emission savings calculations.

Local-first agentic framework. We built it butter. 🧈

Memory that thinks. Local AI memory with hallucination firewall, 95% token savings, Cloudflare bypass, and P2P LAN bug sharing. 55+ tools. Zero cloud.

The Internship Matching System is a web-based platform designed to facilitate the process of internship placement for Data Science and Artificial Intelligence students. The goal of the system was to bridge the gap between students, companies, and academic supervisors by providing a centralized and organized environment for internship applications

A calm AI companion that quietly knows everything. Reads your mail, writes your morning, runs your terminal — and stays out of your way.

🔍 IndustryLens · Industry keyword encyclopedia · 109 industries × 100 words · Pro definition + plain language + industry data + top-3 companies · Understand any industry in 30 seconds

Local interview copilot web app and meeting overlay extension

Peria est une application mobile centrée sur le suivi du cycle menstruel et le bien-être féminin, conçue pour offrir une expérience à la fois intime, intelligente et sécurisée. L’application repose sur trois modules principaux qui structurent l’ensemble du parcours utilisateur.