Stars
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Specula: A framework for finding deep bugs in system code using TLA+
A Rust document retrieval using embeddings. (Llama.cpp + libsql)
Platform for evaluating reinforcement learning (RL) algorithms on a physical Atari system.
ONNXRuntime-based inference backend for the SmolVLA
Measure Make, Bazel, Scons, Ninja, etc. Are project claims true?
A web app for rapidly prototyping AI agents and the lightweight web UIs that wrap them—build flows, preview interactions, and share agent-driven experiences without lock-in.
A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.
obuzek / llm-second-brain
Forked from IBM/lm-deskThe LM Desk project is a central entrypoint for configuring a set of awesome tools that will power your desktop productivity using generative AI. This is a project-of-projects that brings together …
Smalltalk-80 bare metal implementation for the Raspberry Pi
Port of MIT's xv6 OS to the Nezha RISC-V board with Allwinner D1 SoC
Emacs as your personal AI assistant. Use LLMs such as ChatGPT or LLaMA for text generation or DALL-E and Stable Diffusion for image generation. Also supports speech input / output.
PCB design for Acorn Archimedes RP2040-based podule
pmacct is a small set of multi-purpose passive network monitoring tools [NetFlow IPFIX sFlow libpcap BGP BMP RPKI IGP Streaming Telemetry].
I/O Riot is a tool for logging, replaying, and benchmarking I/O on Linux
Secure execution VM executing human-like language (no-code) to operate on data and advanced cryptographic operations.
lispers.net code for the world's most feature-rich implementation of the Locator/ID Separation Protocol (LISP)
mhsys / mh
Forked from glguida/mhMH: a microkernel for fun and experimenting!
A small self-contained alternative to readline and libedit