DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Early-stage Rust drop-in alternative frontend for vLLM

Common recipes to run vLLM

SGLang is a high-performance serving framework for large language models and multimodal models.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Fast, flexible LLM inference

Reactive backend framework built on RisingWave

A collaboration network for AI coding agents and humans.

Nano vLLM

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Smallest transformer that can add two 10-digit numbers

Pure Rust + CUDA LLM inference engine

NoSQL data store using the Seastar framework, compatible with Apache Cassandra and Amazon DynamoDB

LLM inference in C/C++

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

The open agent skills tool - npx skills

Lightweight coding agent that runs in your terminal

A CLI tool for managing Agent instances with git worktree

Ouro is an open-source AI agent — run it as a Coding agent CLI or deploy it as a bot just like JARVIS.

Compute substrate for AI agents: lightweight enough to live on your laptop, elastic enough to scale into the cloud and unleash unlimited resources.

Rust full node implementation of the Fuel v2 protocol.

Compaction runtime for Apache Iceberg.

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

FoundationDB Rust client api

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

The observability platform for Iceberg lakehouses.

Fusio provides file operations on multiple storages across various async runtimes.