Bird frame for Raspberry Pi or your homelab - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. On an e-ink panel, a TV, or any screen.

Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative a…

Augmented Qualitative Data Analysis — local-first QDA tool with AI augmentation via Ollama

Free and open-source qualitative data analysis software.

MiniMax H3 inference engine for Mac computers

AirLLM 2.8T LLM inference with single 4GB GPU

A community-maintained Python framework for creating mathematical animations.

A Python library for the processing of QDPX and QDA-XML files

Statistical Rethinking Course 2026

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

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

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.

The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Everything I know about running LLMs locally

ActivityPub-federated video streaming platform using P2P directly in your web browser

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Offline GUI-tool to convert common subtitle files (such as created by Whisper AI) to interview transcripts for qualitative data analysis. Supported import file formats are SRT, VTT, TXT, JSON and T…

Local-first Video Knowledge Base. Index your video library with multi-modal analysis (YOLO, DeepFace, Whisper), search semantically via natural language, Docker-ready.

Shadow any website for offline viewing, with the JavaScript stripped out

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Emergence World: A world designed to reveal what no benchmark can: emergent intelligence.

Continuous memory + self-improvement for AI agents. Learns how you work, recalls it automatically, no commands. Claude Code & Codex.