Distributed builds for Nix

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown files

Quickly create and run optimised Windows, macOS and Linux virtual machines

Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration

templating engine and static site generator using KDL

User-mode networking for unprivileged network namespaces

Nix binary cache proxy service -- with local caching and signing.

Nix binary cache implemented in rust (maintainer: @Mic92)

Fly

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

The agent that grows with you

An ahead-of-time JavaScript compiler

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

Rust client for Qdrant vector search engine

llama.cpp fork with additional SOTA quants and improved performance

Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Rust implementation of Tailscale (preview, experimental)

Lexicon as Programming Language: declare types in .lex, synthesize via Petri net reachability

Ad meliora.

Keep Your Claude Code Buddy Forever — permanent coding companion that survives every update

Make SSH apps, just like that! 💫

Tracing-based Nix evaluation cacher

Go SSR web framework — Preact templates, htmx interactions, Islands hydration. Built on net/http.

relational database stored 100% in a discord guild built with go

LLM inference in C/C++

A framework for building interactive multiplayer 3D websites.

rust bindings of snmalloc