Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Autonomous AI development loop for Claude Code with intelligent exit detection

VCR - python decorator for capturing and simulating network communication

The Art of Debugging Open Book

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Unified web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.

A library that provides an embeddable, persistent key-value store for fast storage.

Universal Python binding for the LMDB 'Lightning' Database

Python fast on-disk dictionary / RocksDB & SpeeDB Python binding

The best ChatGPT that $100 can buy.

An Intelligent Python Code Quality Analyzer

OCI registry client - managing content like artifacts, images, packages

Running a LLM on the ESP32

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

A local sandbox for your AI agents

An Obsidian theme inspired by the beautifully-designed app, Things.

A high-throughput and memory-efficient inference and serving engine for LLMs

A Model Context Protocol (MCP) server for Kubernetes. Install: npx kubectl-mcp-server or pip install kubectl-mcp-server

The AI Browser Automation Framework

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Run Claude Code on OpenAI models

Collection of publicly available libraries

A plugin to edit and view Excalidraw drawings in Obsidian

Executable GenAI prompt templates

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

🦎 a tool to build and deploy software on many servers 🦎