Security firewall for agents

lowfat - slim your command output. strips noise, saves tokens.

Fast stackful fibers with a NUMA-aware work-stealing scheduler

Single file optical file transfer using a browser

An open-source database of AI models.

Framedex — a queryable knowledge base for your video archive

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

The only tool you need to know what is happening and how to fix it.

26m function call model that runs on incredibly small devices

Watch videos with friends using WebRTC, let the server do the pausing and seeking.

Embedding Vector Oriented Clustering

General-purpose MCP bridge for Ableton Live

Distribute and run transformer encoders with a single file.

💬 A proposal for a web API for prompting browser-provided language models

talkie is a vintage language model from 1930

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Desktop app to manage markdown knowledge bases

Tool to build & run portable, lightweight, self-contained virtual machines.

LLM inference in C/C++

Native space switching on macOS with no animation

Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.

Bayesian git bisect

Fast, accurate & comprehensive text measurement & layout

Slop Scoring to Stop Slop

JSONata query and transformation language - http://jsonata.org

Self-referential self-improving agents that can optimize for any computable task

Self-hosted, semantically-connected personal knowledge base