The open source control plane for AI inference

Techniques and numbers for estimating system's performance from first-principles

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Open Source framework for voice and multimodal conversational AI

A Datacenter Scale Distributed Inference Serving Framework

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Lightweight coding agent that runs in your terminal

Open Source Continuous Inference Benchmark Research Platform — Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究…

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

CrowdSec - the open-source and participative security solution offering crowdsourced protection against malicious IPs and access to the most advanced real-world CTI.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

[mirror] Go on Mobile

ecspresso is a deployment tool for Amazon ECS

Extensible security first OAuth 2.0 and OpenID Connect SDK for Go.

A curated collection of publicly available resources on how technology and tech-savvy organizations around the world practice Site Reliability Engineering (SRE)

🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.

Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil…

A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search

Write HTML. Render video. Built for agents.

The best ChatGPT that $100 can buy.

A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do

A curated list of engineering blogs

An in-memory key:value store/cache (similar to Memcached) library for Go, suitable for single-machine applications.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

A cross-platform protocol library to communicate with iOS devices

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"