Starred repositories
Systems language with linear types and capability-based security.
26m function call model that runs on incredibly small devices
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
MITIE: library and tools for information extraction
DFlash: Block Diffusion for Flash Speculative Decoding
Fast LLM speculative inference server for consumer hardware.
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
A ~9M parameter LLM that talks like a small fish.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
A declarative inline TUI rendering library for Rust, built on Ratatui
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
Fast, accurate & comprehensive text measurement & layout
SQLite VFS with sub-100ms cold JOIN queries from S3 + page-level compression and encryption
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
Based on The Minimalist Entrepreneur by Sahil Lavingia
Model-agnostic MoE compression automation: build calibration bundles, run REAP/quantization/benchmark/publish stages, and render auditable reports.
Running a big model on a small laptop
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).
GPU-accelerated terminal board that puts all your sessions on an infinite canvas
Dafny is a verification-aware programming language