atmosfar
Follow
Stars
a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)
Adds ability to download models from IKEA website
Open source video conferencing app powered by LiveKit. Built with Django and React.
Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file
A local music player app designed to capture the nostalgic essence of the iconic iPod Classic.
A Senspin music streaming client compatible with ARMv6 devices like the RPi Zero W using the sendspin-cpp library
ggml speech-to-text inference for 16+ model families
Peer authenticated WebRTC. A WebRTC-based clone of magic-wormhole.
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…
Open-source e-reader firmware
A self-hosted travel/trip planner with real-time collaboration, interactive maps, PWA support, SSO, budgets, packing lists, and more.
Monorepo for @juicesharp/rpiv-* Pi plugins (lockstep versions, single install, single publish pipeline)
Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery
Minimal MCP server for Vikunja (server-side filtering, no fluff)
🛠️ Awesome tools & guides for harness engineering.
Practical local LLM recipes and benchmarks for RTX 5060 Ti setups
Restore a truncated mp4/mov. Improved version of ponchio/untrunc
Zero-config AI agent written in pure Go. Enforced ephemeral subagents keep your model smart and your context tiny. From tiny local models to frontier LLMs.
Linux & Powershell scripts to easily set up and run the Qwen 3.5 series locally on Windows and Linux with llama.cpp.