turbo-fieldfare
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
Clawk – Give coding agents a disposable Linux VM, not your laptop
GigaToken: ~1000x faster Language model tokenization
Ctrlb-decompose: Strip the noise from logs before sending to LLMs
Jamesob's guide to running SOTA LLMs locally
Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload
FableCut – A browser video editor AI agents can drive (zero deps)
Distill and serve small models with frontier quality for half the cost
Train and run transformers directly on Apple's Neural Engine
Claude is just Mr. Meeseeks
Scan your AI agents for dangerous capabilities
Open-source memory for coding agents, synced over SSH
Fractal – recursive agent loops for complex, multi-step work
Coding Tools MCP (v0.2.2):Give any AI chat or agent a pair of hands on your code
Nous – give GTM agents one context graph across your tools
Ratel, give agents unlimited tools and skills without context bloat
Fortress – a stealth Chromium so your agents stop getting blocked
A local merge queue for parallel Claude Code agents