Havuz

Self-hosted ebook library that runs on object storage - a Cloudflare Worker over R2, or a Node server over a directory. No database.

The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.

Deanonymize anyone based on their public commenting or posting history & pattern.

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports f

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound.

AI builder operating system. Turn Claude Code from a per-session tool into a workspace that remembers, maintains itself, and never goes stal

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat, Dream consolidation and calendar-l

Put the world's best AI agents to work. One workspace for all of them -- Claude Code, Codex, Gemini, Grok and more, running side by side on

原生 macOS Git 客户端，以 Agent 驱动仓库管理、审阅与协作。

Self-hosted private chat channel between you and your AI companion — PWA, Claude Code, or any LLM.

Han: AI skills and agents for "Solo" product engineers and small teams

mission control for agent skills

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal.

Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.

A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

Paced resonance breathing in your terminal

1Password for coding agents: find, use, and save secrets without exposing them

Open standard for software intent in the AI agent era.

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

The graph based agentic IDE

LLM-ready reasoning surface over logs

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, C

Mine your Claude Code and Codex logs into a local you.md agent profile.

Native deterministic engine and read-only MCP server for engineering decisions.

Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

A production-oriented Go framework for distributed applications with explicit lifecycle, transport, governance, observability, and contract-

Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

Local-first Markdown workspace and AI game design assistant for game development teams

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live s

[ICML 2026] Autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.

Google Health CLI — one command-line tool for the Google Health API. Includes AI agent skills.

Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.

A cron that remembers what it did — a CLI job scheduler with persistent run history, captured stdout/stderr, and a live terminal dashboard.

Repo dependency analyzer with **blast-radius impact scoring** for AI-assisted development.

Search WeChat public account articles by keyword via Sogou WeChat Search. Returns structured JSON — no API key required.

macOS 本地服务与批处理任务的指挥台：一键启动、实时监测、日志与进程溯源。零依赖 Python 后端 + 原生前端。

Monitored public GitHub Actions builds for iptvorganization TV Mobile and Leanback APKs

A local-first, long-term memory for anything you'd otherwise forget.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluatio

Local-first AI coding quotas and ship status, on your menu bar, iPhone, Watch and an ESP32 desk display.

Evidence-grounded cryptographic inventory and post-quantum migration planning for software repositories. Local static analysis, zero mandato

Spotify player for the terminal. With reactive themes.

A focused GitHub desktop workspace for notifications, issues, pull requests, Actions, repository discovery, and an optional repository-aware

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

README-first, evidence-backed analysis for understanding public GitHub repositories before adoption.

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Automated quality checks that nudge AI coding agents toward better habits

Local, zero-dependency dashboard for Claude Code: live token usage and context, lost-session recovery, full-text search, and approve tool ca