Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

GoAccess is a real-time web log analyzer and interactive viewer that runs in a terminal in *nix systems or through your browser.

Fast, secure, efficient backup program

An extension of Karpathy's LLM Wiki pattern: atom layer, topic-branches, two-layer Lint. Distilled from running the pattern end-to-end.

The open-source AI voice studio. Clone, dictate, create.

The open-source AI voice studio. Clone, dictate, create.

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Interactive 3D cell architecture gallery built with React and Three.js

Pretrain a model on ciphered text so only you can use it

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil…

Build your Personal AI Computer. Own your intelligence.

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil…

Production-ready platform for agentic workflow development.

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

mactop - Apple Silicon Monitor Top

The open-source app everyone uses to manage agents at work

The open-source app everyone uses to manage agents at work

🚿 Sanitising your documents, one threat at a time. — Content Disarm & Reconstruction Software

DocLang spec and reference toolkit

DocLang spec and reference validator

Full Transformer into a custom chip. microGPT in RTL, generating names on a Virtex-5 FPGA at ~56k tokens/second.

Gemma open-weight LLM library, from Google DeepMind

A fast, helpful, and open-source document parser

A fast, helpful, and open-source document parser

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative)

Ultra-lightweight C++ inference engine for BitMamba-2 (1.58-bit SSM). Runs 1B models on consumer CPUs at 50+ tok/s using <700MB RAM. No heavy dependencies.

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

DFlash: Block Diffusion for Flash Speculative Decoding

Academic Research Skills for Claude Code: research → write → review → revise → finalize