An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.

A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in che…

Machinen

A minimal 2d/3d game framework for @ziglang.

Publishes government content on GOV.UK

Compile Zod schemas into zero-overhead validation functions at build time. Works with Vite, webpack, esbuild, Rollup, etc

Local LLM-assisted text completion for Qt Creator.

A cosy home for your LLMs.

Use for testing CI

llama.cpp's official website

Brand assets for llama.app / llama.cpp

Build and install script for llama.app

github action to speedup building using ccache

self-hosted GHA runners in containers

verl Zero-Mismatch Dense/MoE HuggingFace Rollout

Multimodal RL training framework for diffusion & omni models

VLA training framework of Volcano Engine

Provide performance insight capabilities for RL frameworks.

Open MinT training runtime on veRL

A set of examples based on verl for end-to-end RL training recipes.

External training/inference backend plugin for various hardware platform

verl Ascend specific recipe

A unified framework for building, running, and training general agents at scale.

Vue.js grammar for tree-sitter

LLM inference in C/C++

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.

Eden source repository

Secure (with AEAD) version of USTP, called USTP-Secure (ustps://)

kubernetes in apple container based on kind