RTX 4090 (sm_89) Linux port of NInfer for Qwen3.6-27B

High-performance single-GPU inference for selected model checkpoints and GPUs.

Meta-Framework of Spatiotemporal Composability

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

DeepSeek Harness: Everything is a Plugin.

Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache

ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants

Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.

Run huge MoE models from a swarm of peers, with the colibri engine. Pure C.

Local-first voice-to-text for pi, using Whisper-style backends to dictate coding prompts directly into the editor.

Monorepo for @juicesharp/rpiv-* Pi plugins (lockstep versions, single install, single publish pipeline)

Safe push-to-talk dictation for Pi with pluggable transcription backends

OCR model that handles complex tables, forms, handwriting with full layout.

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (for example, RadixAttention, Cache-aware scheduling)

TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.

A hive mind communication platform

Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

A full featured, powerful, and efficient AI Agentic Harness/Desktop Agent app designed from the ground up with local inference on consumer hardware in mind. It evolves, grows, and gets smarter as y…

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.

Mixxx is Free DJ software that gives you everything you need to perform live mixes.

Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

The most RAM efficient harness