mit-licensed
Secure, ephemeral browsing in a disposable VM (macOS only).
Bromure is a native macOS app that runs every browser session inside a lightweight, disposable Linux virtual machine using Apple's Virtualization.framework. The browser and your Mac don't share an operating system, a filesystem, or even a kernel. When you close the window, the VM is destroyed -- cookies, history, malware, trackers, all of it. Gone.
Exploring memory safety that's easier to use.
A programming language that is higher level than Rust but lower level than Go. Someday, anyways.
Related contents:
Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.
Related contents:
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini CLI, Codex, Copilot, and Antigravity.
Solves context rot — the quality degradation that happens as Claude fills its context window.
One tool to manage every AI agent's skills. The universal skill manager for AI coding agents.
Stop juggling skill directories across Claude Code, Codex, OpenClaw, and other AI agents. agent-skill-manager (asm) gives you a single TUI and CLI to install, search, audit, and organize all your agent skills — everywhere.
A Virtual File System for Node.js. Provides an in-memory fs-compatible API with mount points, overlay mode, symlinks, module loading hooks, and custom storage providers.
Related contents:
A Claude Code plugin that shows what's happening — context usage, active tools, running agents, and todo progress. Always visible below your input.
An Open-Source Asynchronous Coding Agent. Open-source framework for building your org's internal coding agent.
Elite engineering orgs like Stripe, Ramp, and Coinbase are building their own internal coding agents — Slackbots, CLIs, and web apps that meet engineers where they already work. These agents are connected to internal systems with the right context, permissioning, and safety boundaries to operate with minimal human oversight.
Open SWE is the open-source version of this pattern. Built on LangGraph and Deep Agents, it gives you the same architecture those companies built internally: cloud sandboxes, Slack and Linear invocation, subagent orchestration, and automatic PR creation — ready to customize for your own codebase and workflows.
Related contents:
An open-source, self-hosted AI code review bot. Deploy to Vercel, connect a GitHub App, and get on-demand PR reviews powered by Claude.
TypeScript CLI Framework for Bun.
A TypeScript-first, Bun-native CLI framework with composable modules.
Most CLI tools in the JavaScript ecosystem are either minimal arg parsers that leave you wiring everything together, or heavyweight frameworks that bring more complexity than you need. Crust sits in the sweet spot: more structured than a bare parser, lighter than a full framework, and designed so you only pull in what you actually use.
The batteries-included agent harness.
The easiest way to start building agents and applications powered by LLMs—with built-in capabilities for task planning, file systems for context management, subagent-spawning, and long-term memory. You can use deep agents for any task, including complex, multi-step tasks.
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.
Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring up prompts, tools, and context management yourself, you get a working agent immediately and customize what you need.
Related contents:
Oxyde ORM is a type-safe, Pydantic-centric asynchronous ORM with a high-performance Rust core designed for clarity, speed, and reliability.
Inspired by the elegance of Django’s ORM, Oxyde focuses on explicitness over magic, providing a modern developer-friendly workflow with predictable behavior and strong typing throughout.
Claude Code skills that build complete Godot 4 projects from a game description.
You describe what you want. An AI pipeline designs the architecture, generates the art, writes every line of code, captures screenshots from the running engine, and fixes what doesn't look right. The output is a real Godot 4 project with organized scenes, readable scripts, and proper game architecture. Handles 2D and 3D, runs on commodity hardware.
Use any icon (100,000+) from Iconify, for TailwindCSS.
Next Generation Visual Programming System.
Unit is a General Purpose Visual Programming Language and Environment built with a primary focus on Developer Experience.
It is heavily inspired by Live, Data Flow, Reactive, Functional and Object Oriented Programming paradigms. Formally, units are Multi Input Multi Output (MIMO) Finite State Machines (FSM). A program in Unit is represented as a Graph.
Local Twitter/X bookmark organizer with AI categorization and mindmap visualization.
Siftly turns your Twitter/X bookmarks into a searchable, categorized, visual knowledge base — running entirely on your machine. No cloud, no subscriptions, no browser extensions required. Everything stays local except the AI API calls you configure.
AI agents running research on single-GPU nanochat training automatically.
The idea: give an AI agent a small but real LLM training setup and let it experiment autonomously overnight. It modifies the code, trains for 5 minutes, checks if the result improved, keeps or discards, and repeats. You wake up in the morning to a log of experiments and (hopefully) a better model.
Related contents:
Agent Memory That Learns.
Hindsight™ is an agent memory system built to create smarter agents that learn over time. Most agent memory systems focus on recalling conversation history. Hindsight is focused on making agents that learn, not just remember.
An agentic skills framework & software development methodology that works.
Superpowers is a complete software development workflow for your coding agents, built on top of a set of composable "skills" and some initial instructions that make sure your agent uses them.
Related contents:
your repository becomes your agent. The Open Standard for Git-Native AI Agents. The open standard for defining, versioning, and running AI agents natively in git.
A git-native, framework-agnostic, open standard for defining AI agents. Version-controlled config that exports to Claude Code, OpenClaw, Lyzr Agent, Chimera, NanoBot, CrewAgent, and Agents SDK.
Design Terminal UIs. Visually.
A Figma-like visual editor for TUI applications. Drag-and-drop components, edit properties in real-time, and export to 6 frameworks with one click.
Free Open Source Video Downloader. The Most Powerful Automated Video Downloader
Download videos from YouTube, TikTok, Twitter, Instagram, Facebook, Twitch, Bilibili, and 1000+ other platforms with fast, high-quality up to 4K downloads, batch queues, and RSS auto-download automation.
Related contents:
ANSI art screensaver for macOS — streams art from 16colo.rs BBS archive packs.
Related contents:
🚀 Bulk download your iCloud Drive files and folders with a simple command line tool.
A robust Python utility for efficiently downloading files and folders from iCloud Drive, designed for bulk data recovery and migration. This tool helps users easily retrieve their data from iCloud Drive when Apple's native solutions are insufficient.
Related contents:
A macOS app that enhances control over Elgato lights, offering features beyond the standard Elgato Control Center software.
Related contents:
GDPR compliance auditor for cookie consent. CLI tool to scan websites for GDPR cookie consent compliance.
Open-source CLI that scans any website for GDPR compliance — detects dark patterns, scores 4 regulatory dimensions, and generates ready-to-share HTML reports.
Open-source EDR for AI agents. Monitor processes, files, network, and behavior of autonomous AI agents.
Aegis is an open-source endpoint detection and response (EDR) tool that monitors AI agent processes, file access, network activity, and behavioral anomalies in real time. Built with Electron 33, Svelte 5, and TypeScript, it provides the same class of oversight for autonomous AI agents that CrowdStrike provides for traditional endpoints. No telemetry. No cloud. Everything stays local.
Self host your own Vercel. The open-source, self-hosted deployment platform. Deploy, observe, and scale -- from a single binary.
Stop paying for 6 different SaaS tools. Temps replaces your deployment platform, analytics, error tracking, session replay, uptime monitoring, and transactional email -- all self-hosted, all in one binary.
A debugger for your CI pipeline.
Interactive CI pipeline debugger. Step through GitHub Actions workflows locally with Docker. Step through GitHub Actions workflows locally with Docker. Pause before each step, inspect the environment, drop into a shell, modify variables, re-run failed steps — without pushing and waiting.
🤖 Dependabot's core logic for creating update PRs.
Related contents:
Pure Go Redis test server, used in Go unittests.
Sometimes you want to test code which uses Redis, without making it a full-blown integration test. Miniredis implements (parts of) the Redis server, to be used in unittests. It enables a simple, cheap, in-memory, Redis replacement, with a real TCP interface. Think of it as the Redis version of net/http/httptest.
Personal ngrok alternative. Expose local ports to the internet with automatic HTTPS, an interactive TUI dashboard, and HTTP request inspection -- all through your own VPS.
Browser-based DevOps audit tools. No backend. No signup. Everything runs client-side.
Official inference framework for 1-bit LLMs.
bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU and GPU (NPU support will coming next).
A basic PHP admin panel ready for developing your projects.
Open-source PHP admin panel and dashboard built with Bootstrap 5 — relational CRUD generator, authentication, REST API, CLI, modular architecture, MySQL & SQLite.
Watch once. Then take the stage. A Teachable Desktop Agent.
Understudy is a teachable desktop agent. It operates your computer like a human colleague across GUI, browser, shell, files, and messaging. You demonstrate a task once, it learns the intent, remembers successful paths, and gradually upgrades to faster execution routes.
Understand how your team codes with AI. Coding Agent Analytics for Claude Code.
Rudel gives engineering leaders visibility into Claude Code usage across their team. Track productivity, quantify ROI, and surface quality signals, automatically.
Annotate plans. Not in the terminal. Visual Plan Review for Claude Code
Interactive Plan Review for coding agents. Mark up and refine plans visually, share for team collaboration. Works with Claude Code, OpenCode, and Pi. Annotate and review coding agent plans visually, share with your team, send feedback to agents with one click. Interactive Plan Review for AI Coding Agents. Mark up and refine your plans using a visual UI, share for team collaboration, and seamlessly integrate with Claude Code, OpenCode, Pi, and Codex.
practice makes claude perfect
Hide .env secrets from prAIng eyes.
secrets live in local encrypted stores (per project) and are injected directly into apps at runtime, never touching disk as plaintext.
Related contents:
Lab4PurpleSec is a modular Purple Team homelab combining a vulnerable Active Directory environment (GOAD), a Docker-based web DMZ, pfSense + Suricata, and a Wazuh SIEM. It provides a realistic, open-source training environment for web exploitation, pivoting, Active Directory attacks, and Blue Team detection.
Open Source Voice Cloning Desktop App Powered by Qwen3-TTS. Create natural-sounding speech from text with near-perfect voice replication.
The open-source voice synthesis studio. Clone voices. Generate speech. Build voice-powered apps. All running locally on your machine.
Voicebox is a local-first voice cloning studio with DAW-like features for professional voice synthesis. Think of it as a local, free and open-source alternative to ElevenLabs — download models, clone voices, and generate speech entirely on your machine.
Related contents:
An agent that grows with you.
Install it on a machine, give it your messaging accounts, and it becomes a persistent personal agent that grows with you — learning your projects, building its own skills, and reaching you wherever you are.
The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
Related contents:
- Episode du 7 avril @ Les Technos :fr:.
- Episode 661: Sink Your Claws In @ Linux Unplugged.
- Episode 668: --yolo @ Linux Unplugged.
- E357: Hermes Agent: Agents that grow with you @ Practical AI.
- Hermes Agent : veille technique auto-hébergée avec Matrix, FreshRSS et Firecrawl @ Cryptolab :fr:.
- Episode 677: We Got a Buzz @ Linux Unplugged.
High-Performance Data Grid for Vue, React, Angular, Svelte, and JavaScript. RevoGrid is a high-performance JavaScript Data Grid built for massive datasets. 60fps, 3x less memory
Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG.
RCLI is an on-device voice AI for macOS. A complete STT + LLM + TTS pipeline running natively on Apple Silicon — 38 macOS actions via voice, local RAG over your documents, sub-200ms end-to-end latency. No cloud, no API keys.
A general purpose, fast and lightweight editor with a keyboard-centric minimalistic user interface.
Built on LuaJIT and fully programmable using Lua or Moonscript.
Howl is a general purpose editor that aims to be both lightweight and fully customizable. It is built on top of the very fast LuaJIT runtime, and can be extended in either Lua or Moonscript. It has a minimalistic UI driven mainly by the keyboard.
Related contents:
Contracts before code. Tests as law. Agents that can't cheat.
Pact is a multi-agent software engineering framework where the architecture is decided before a single line of implementation is written. Tasks are decomposed into components, each component gets a typed interface contract, and each contract gets executable tests. Only then do agents implement -- independently, in parallel, even competitively -- with no way to ship code that doesn't honor its contract. Generates Python, TypeScript, or JavaScript.
Make your AI coding agent smarter. CLI proxy.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies.
rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, zero dependencies, <10ms overhead.
Related contents:
- RTK - Le proxy Rust qui vous fait économiser jusqu'à 90% de tokens @ Korben :fr:.
- #131: News Mai 2026, TypeScript 7 en beta, faux package TanStack et agent Cursor destructeur @ Double Slash :fr:.
- #375.src - RTK: Le coût du token, la nouvelle donne du Dev avec Patrick Szymkowiak @ ifttd :fr:.
- RTK reports huge token savings, but our cost benchmarks disagree @ Quesma.
curl-like access to AWS resources with AWS Signature Version 4 request signing.
Haptic feedback for the mobile web. Supports React, Vue, and Svelte.
Related contents:
Codemogger is a code indexing library and MCP server for AI coding agents.
Code indexing library for AI coding agents. Parses source code with tree-sitter, chunks it into semantic units (functions, structs, classes, impl blocks), embeds them locally, and stores everything in a single SQLite file with vector + full-text search.
Related contents:
🌳 Tiny & elegant JavaScript HTTP client based on the Fetch API.
Related contents:
The AI Operator Living in Your Web Page. JavaScript in-page GUI agent. Control web interfaces with natural language.
🪄One line of code, turns your website into an AI-native app. Users give natural language commands, AI handles the rest.
Touch-to-grab context tool for React Native UI changes.
Bridge the context gap: point at the exact native UI element, capture precise source context, and hand it to your coding agent without guesswork.
Boot a virtual iPhone (iOS 26) via Apple's Virtualization.framework using PCC research VM infrastructure.
Related contents:
macOS menu bar app that exposes Apple's on-device Foundation Models as an OpenAI-compatible local API. Zero cloud. Zero dependencies.
Related contents:
Let your AI go full send. Your home directory stays home.
Run Claude Code, Codex, or any AI coding agent in "yolo mode" without nuking your home directory.
Related contents:
Edit videos, right in your browser
An AI-native, open-source video editor and free alternative to CapCut. No uploads, no tracking — your media stays on your device.
Related contents:
Catch cloud waste before it ships. Shift-left cloud hygiene engine for AWS and Azure. Catch waste in CI - read-only, deterministic, zero telemetry.
Like tfsec for Terraform or trivy for containers — CleanCloud finds orphaned resources in AWS and Azure and enforces hygiene gates in your CI/CD pipeline before waste reaches production.
Related contents:
The Ultimate Information Gathering Toolkit. A Python-based toolkit for Information Gathering & Reconnaissance.
Argus is an all-in-one, Python-powered toolkit designed to streamline the process of information gathering and reconnaissance. It brings together a clean, intuitive interface and a wide range of reliable modules, allowing analysts to efficiently assess networks, web applications, and security environments with consistency and precision.