Havuz

Screenshot clipboard paste fix for Claude Code, Codex & Cursor — works on macOS, SSH remote, WSL2. Tiny background daemon (9 MB RAM, 0% CPU)

Open-source Legal AI workspace for evidence-grounded legal drafting, matter analysis and verifiable answers.

Self-hosted Instagram comment-to-DM automation on the official Meta API. Deploy your own on Cloudflare's free tier — no scraping, no subscri

CLI for the Gumroad API

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, sa

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

WebOS TV client for your self-hosted Immich photo and video server

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Generate AI music from your terminal — Suno v5.5 with tags, exclude, vocal control, and all generation features

A collection of free AI coding tools! :copilot:

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

Unofficial Rust CLI/library and local Whisper-compatible REST shim for Codex Desktop ASR using local ChatGPT auth

Visualize your project's feature logic as a semantic flow graph — not call graphs, not import maps. AI writes the data, you see the story.

Self hosted Wiki + Jira-style AI native issue tracker on Cloudflare Workers

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects t

A powerful command-line interface for Redmine, with first-class AI agent capabilities via Skills and MCP integration.

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

Let any MCP AI agent drive your real Chrome. Copy one prompt to pair — no confirmation page, no pairing code. 100% local.

End-to-end Langfuse workshop using a TypeScript Agent to teach the AI engineering loop: tracing, prompt management, monitoring, datasets, ex

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant S

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

Test React Native with Vitest - against real React Native, or a fast mock. One plugin, zero config.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

Codex skill for converting raster logos into smooth minimal SVG plus standalone HTML previews.

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

Convert Tabbit browser’s internal API into OpenAI and Anthropic Claude-compatible interfaces for seamless multi-account AI service integrati

Official benchmark reproduction code for the SAG paper

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks (NeurIPS 2026 Evaluations and Datasets Track)

One-command installer for all AI Marketing Hub tools: Claude SEO, Claude Blog, Skill Forge, WP MCP Ultimate

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

Fast file copy engine for Python. Streams over SSH, skips content it has already sent, and reads in block order to keep disks at sequential

Self-hosted OpenAI-compatible API proxy for Google Gemini — authenticated via OAuth 2.0 + PKCE, no paid API key required. Built with Bun + H

An extremely fast GitHub for pull request review: PRs open in 20 ms. Keyboard-first, macOS and Linux, CLI for coding agents.

Self-hosted 多用户 WeChat / 微信 AI 智能体控制台，支持 Web 管理、Docker部署、MCP、Skills、记忆、定时任务、沙盒执行和长期运行，支持分享AI Bot给团队成员。

Script terminal sessions in TypeScript, render reproducible MP4/GIF/SVG/HTML with Bun

AI agent skills manager for Claude Code, Cursor, Codex and more — install, sync, and manage skills from one desktop app.

Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/dir

A Linux CLI utility that transparently routes all system traffic through the Tor network using nftables. It enables rapid IP rotation and ea

The capability harness for AI agents. Skills over SDKs.

Tasks, notes, calendar, money and mail for your household — one Docker container, one SQLite file per family, words encrypted in the browser

Windows PowerShell toolkit for AI agents: Microsoft 365 (mail, calendar, Teams, SharePoint, OneDrive) via Work IQ + Microsoft Graph, Outlook

Self-hosted AI marketing platform. Like Google Pomelli, but open source, model-agnostic, and actually ships to your social media.

Ландшафт технологий 1С. Интерактивная карта экосистемы: 200+ инструментов, 6 осей фильтрации, граф связей, схема-постер и маршруты освоения

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

AI-powered codebase-to-Wiki generator. One command turns any repo into a structured Wiki with Mermaid diagrams, diff-aware sync, and 75+