- 1.
Quickly sandbox your AI agent.
- 2.
- 3.
Docker Sandbox Kit Specification v3 - the kit descriptor grammar, the OCI artifact, the build frontend, and the conformance suites
- 4.
Application Kernel for Containers
- 5.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
- 6.
A compute toolkit for the web with the depth of Plan 9 from Bell Labs
- 7.
Monkey patch, test, and trace Python by attaching bindings to call sites, without modifying the code being observed. Built on wrapt.
- 8.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
- 9.
A Bun CLI that ingests Claude Code and Codex session transcripts, generates LLM-powered daily summaries, and serves a browsable web UI for your engineering journal.
- 10.
Autonomous CTF solver that races multiple AI models in parallel. 1st place BSidesSF 2026.
- 11.
Sandbox your local AI agents so they can read/write only what they need
- 12.
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
- 13.
A fully procedural first-person jungle in Three.js. Zero external art assets - every texture, mesh and sound generated in code.
- 14.
Deploy an AI-generated backend for every user.
- 15.
Find the test that's leaking before the one that fails
- 16.
Minimal WebGL Library
- 17.
Rhai - An embedded scripting language for Rust.
- 18.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
- 19.
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
- 20.
Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
- 21.
ggml speech-to-text inference for 16+ model families
- 22.
Tiny, fast, Linux-compatible sandboxes. Powered by WebAssembly.
- 23.
WebKit compiled to WebAssembly: a full browser engine running inside a browser tab, rendering to canvas, networking over Wisp.
- 24.
(Still experimental) Real Goroutines for Python 3.13t+ free-threaded.
- 25.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
- 26.
A flight-compliant WebAssembly interpreter.
- 27.
A native macOS UI for Apple's platform
- 28.
A data-structure parameterization system written for embedding context in JSON objects
- 29.
The programming language for agents
- 30.
an implementation of the ideas in Erik Meijer's "Guardians of the Agents: Formal Verification of AI Workflows" (Communications of the ACM, January 2026)
- 31.
Political Compass for AI
- 32.
MDN's prototype MCP server
- 33.
Cross-platform WebDriver server for Tauri applications (Linux, macOS, Windows)
- 34.
fast ast walk
- 35.
Your CLI home video recorder 📼
- 36.
Turn a terminal session into a good-looking animated GIF. A vhs wrapper with an attractive default look.
- 37.
Python library for running a MicroPython sandbox using WebAssembly
- 38.
Sandboxed tools and JS runtime for AI agents
- 39.
Finds potential accessibility gaps, files GitHub issues to track them, and attempts to fix them with Copilot.
- 40.
- 41.
Thin Python wrapper of quickjs-ng
- 42.
Observable Plot charts for Datasette Agent
- 43.
An LLM-powered agent for Datasette
- 44.
Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows.
- 45.
Data collection and analysis for a PyCon talk on GitHub Actions security across Python packages.
- 46.
PyPI downloads analytics dashboard
- 47.
A tool for measuring Python class cohesion.
- 48.
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
- 49.
- 50.
Code that accompanies the paper release for "LLMs Corrupt Your Documents When You Delegate"
- 51.
Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.
- 52.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
- 53.
- 54.
- 55.
- 56.
PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.
- 57.
A fast, helpful, and open-source document parser
- 58.
Experiments with GitHub event data
- 59.
A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.
- 60.
This is a collection of the best SVG images of pelicans riding bicycles.
- 61.
Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.
- 62.
An embeddable, portable, branchable virtual machine to safely run Agents locally.
- 63.
A friendly library for working with PDFs
- 64.
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
- 65.
The best-benchmarked open-source AI memory system. And it's free.
- 66.
CLI tool for saving a faithful copy of a complete web page in a single HTML file (based on SingleFile)
- 67.
- 68.
Fast, accurate & comprehensive text measurement & layout
- 69.
JSONata for Python
- 70.
Drop-in replacement for Requests. Automatic HTTP/1.1, HTTP/2, and HTTP/3. WebSocket, and SSE included. WASI Supported.
- 71.
Fyn is a fork of uv for fast Python package management, dependency resolution, virtual environments, and pyproject.toml workflows.
- 72.
Traccar reverse geocoding service
- 73.
Distributed Python made simple.
- 74.
- 75.
Running a big model on a small laptop
- 76.
- 77.
A fast parser, formatter, static analyzer, and language server for SQLite SQL.
- 78.
Lightpanda: the headless browser designed for AI and automation
- 79.
Snapshotable WebAssembly interpreter from scratch. Includes a time travel debugger
- 80.
Documentation that simply works
- 81.
Open-source Agent Operating System
- 82.
Python bindings for Luau
- 83.
A small, fast, and embeddable programming language based on Lua with a gradual type system.
- 84.
argparse + https://usage.jdx.dev/
- 85.
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.
- 86.
- 87.
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
- 88.
- 89.
Lightweight Django middleware for APM-style request profiling (DB vs App time, query count)
- 90.
The control room for your Django app
- 91.
Give your agents the power of the Hugging Face ecosystem
- 92.
A tool for analyzing the size of compiled Go binaries, offering cross-platform support, detailed breakdowns, and multiple output formats.
- 93.
- 94.
Ultra-lightweight, zero dependency, semantic HTML, CSS, JS UI library. ~10KB min+gz.
- 95.
A lightweight, lightning-fast, in-process vector database
- 96.
A port of Descent to Three.js.
- 97.
SeaweedFS is a distributed storage system for object storage (S3), file systems, and Iceberg tables, designed to handle billions of files with O(1) disk access and effortless horizontal scaling.
- 98.
SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agents' security awareness during realistic, multi-turn workplace tasks.
- 99.
python sqlite driver
- 100.
A secure Python sandbox, written in Rust, for code written by AI.
- 101.
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
- 102.
Claude Opus 4.6 wrote a dependency-free C compiler in Rust, with backends targeting x86 (64- and 32-bit), ARM, and RISC-V, capable of compiling a booting Linux kernel.
- 103.
A file server that supports static serving, uploading, searching, accessing control, webdav...
- 104.
tinyproxy - a light-weight HTTP/HTTPS proxy daemon for POSIX operating systems
- 105.
- 106.
🔒🐧 Run command in a secure native sandbox (zero deps)
- 107.
HTTP proxy that injects 3rd party credentials into requests
- 108.
Binary package factory
- 109.
Easy Linux virtual machine on MacOS to sandbox LLM agents.
- 110.
My collection of Claude skills
- 111.
Lightweight WASM-based Linux VM for AI agents - run shell commands in an isolated Alpine Linux environment
- 112.
A Python sandbox using Wasmtime
- 113.
- 114.
Flux 2 image generation model pure C inference
- 115.
Sandbox for Agents
- 116.
One from scratch browser built by one human and one agent, working hand in hand
- 117.
Cowork-like experience in the browser using filesystem api
- 118.
State-of-the-art 2D and 3D Face Analysis Project
- 119.
Scalable real-time messaging server in a language-agnostic way. Self-hosted alternative to Pubnub, Pusher, Ably, socket.io, Phoenix.PubSub, SignalR. Set up once and forever.
- 120.
A radically modular HTML/CSS rendering engine
- 121.
Random digital audio effects
- 122.
Zero heap allocation HTTP server using OxCaml. v experimental!
- 123.
A fast TCP/UDP tunnel over HTTP
- 124.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
- 125.
A Claude Code plugin + Agent Skill + MCP Server for analyzing Federal Election Commission (FEC) campaign finance filings.
- 126.
Optimized string search routines for Rust.
- 127.
A single page printable calendar
- 128.
μSQLite library module for MicroPython
- 129.
- 130.
Brython (Browser Python) is an implementation of Python 3 running in the browser
- 131.
The verification layer for coding agents
- 132.
Modern JavaScript runtime in Python, powered by V8 and bridged by Rust
- 133.
A minimalist text editor that lives in URL
- 134.
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
- 135.
Swift-JustHTML a Swift port of EmilStenstrom/justhtml by implementing 100% html5 spec compliant parsing of html documents in pure Swift
- 136.
weird LLM-translated mutant smb server experiment / bad idea
- 137.
A pure Python HTML5 parser that just works. No C extensions to compile. No system dependencies to install. No complex API to learn.
- 138.
AXe is a CLI tool for interacting with Simulators using Apple's Private Accessibility APIs.
- 139.
Migrate a project from Poetry/Pipenv/pip-tools/pip to uv package manager
- 140.
An example of using uv in Docker images
- 141.
Minimal CLI coding agent by Mistral
- 142.
Local-first development platform
- 143.
Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown
- 144.
The original ABC language (Python's predecessor), from 1991
- 145.
- 146.
A dynamic library providing Virtualization-based process isolation capabilities
- 147.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
- 148.
Ruby 3.4.7/4.0.0 port to Cosmopolitan Libc - Actually Portable Ruby
- 149.
An open-source database of AI models.
- 150.
Orchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for.
- 151.
HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex
- 152.
HLS.js is a JavaScript library that plays HLS in browsers with support for MSE.
- 153.
Embeddable v86 virtual machines
- 154.
WebAssembly (Wasm) arch support for the Linux kernel
- 155.
- 156.
An experiment in durability
- 157.
- 158.
A GitHub Action that runs a command in a gVisor sandbox
- 159.
Gemini CLI Tips and Tricks
- 160.
Leash by StrongDM - take your AI agents for a walk
- 161.
Welcome to your Hackable Conference Badge
- 162.
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
- 163.
Ham exam practice app
- 164.
A Swift package for parsing iWork Keynote, Pages, and Numbers documents
- 165.
- 166.
The best ChatGPT that $100 can buy.
- 167.
Tauri binding for Python through Pyo3
- 168.
Code and data for the paper "Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)" (https://arxiv.org/abs/2510.05016).
- 169.
An agentic skills framework & software development methodology that works.
- 170.
RSS reader for macOS and iOS.
- 171.
CRDTs based on Yrs.
- 172.
WebSocket Connector for pycrdt
- 173.
Useful extensions to the standard Python datetime features
- 174.
A docker container that jails an LLM CLI like codex, gemini, or claude code.
- 175.
- 176.
SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.
- 177.
A single-node analytical database engine with geospatial as a first-class citizen
- 178.
JavaScript/TypeScript-native, low-boilerplate, object-capability RPC system
- 179.
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- 180.
HTTP(s) request filter for processes
- 181.
Extract and compare system prompts and tools from different Claude Code versions
- 182.
Running TCP/IP over SWD lines
- 183.
DSPY on action with OpenSource LLMs.
- 184.
A platform for hosting interactive workshop environments in Kubernetes, or on top of a local container runtime.
- 185.
Under 1KB each! Super Tiny Icons are miniscule SVG versions of your favourite website and app logos
- 186.
- 187.
tfw when you when your lid when uhh angle your lid sensor
- 188.
zero-dependency image processing library
- 189.
An implementation of Django's EmailBackend compatible with sendgrid-python v5+
- 190.
A collection of Dev Container Features managed by Dev Container spec maintainers. See https://github.com/devcontainers/feature-starter to publish your own
- 191.
- 192.
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
- 193.
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
- 194.
Renderer for the harmony response format to be used with gpt-oss
- 195.
[ICLR2026] Test-Time Scaling with Reflective Generative Model
- 196.
Go sqlite3 http vfs: query sqlite databases over http with range headers
- 197.
MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seamless integration with existing OpenAI SDK clients while leveraging the power of local ML inference.
- 198.
slime is an LLM post-training framework for RL Scaling.
- 199.
Ever used asyncio and wished you hadn't? A tiny (~400 lines) event loop for Python.
- 200.
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.