Stars
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
Can my eBPF tool actually run? If not, what exactly needs to change?
Define a Go struct. Get a CLI that an agent can discover, call, sandbox, and debug. Flags, env vars, config files, validation, JSON Schema, MCP, structured errors, and WASM. Built on Cobra.
The best-benchmarked open-source AI memory system. And it's free.
Library for reducing tail latency in RAM reads
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Distributed inference for mobile, desktop and server.
Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.
wh1te4ever / super-tart-vphone
Forked from JJTech0130/super-tarttart, but with custom AVPBooter ROM, serial I/O, DFU mode, GDB debugging (port 8000), SEP debugging (port 8001), and panic halting. See help menus for `tart create` and `tart run` for more info. Re…
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
The Jieba Chinese Word Segmentation Implemented in Rust
High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
Stealthy Linux Kernel Rootkit for modern kernels (6x)
Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
Chronos: Pretrained Models for Time Series Forecasting
Minimal plugin that lets Claude Code call you on the phone.
DFlash: Block Diffusion for Flash Speculative Decoding
Android kernel exploit for CVE-2025-38352, previously exploited in-the-wild. Targets vulnerable x86_64 Linux kernels v5.10.x.