Claude Code mod: generate sound effects from text prompts with a local Stable Audio model (sa3.cpp). No API, no Python.

Search your Mac by what's in your files: photos, PDFs, recordings, videos and code. On-device, built on Google DeepMind's EmbeddingGemma 2.

Performance benchmarkin of LLM Inference admission control policies.

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

The local-first task board for you and your AI agents. Claude & Cursor work on it over MCP, the built-in assistant asks before changing anything, and it all stays on your machine.

State recoverability, crash reconciliation, and selective undo for autonomous AI agents.

A high-throughput and memory-efficient inference and serving engine for LLMs

Kiro Crew fork with the Claude Code ACP backend re-enabled for self-hosted LLM routers (9router, any Anthropic-compatible endpoint). No Kiro account, no Bedrock — your models, your hardware.

ggml speech-to-text inference for 16+ model families

A free, open source, and extensible speech-to-text application that works completely offline.

Official inference framework for 1-bit LLMs

Analytical benchmark connecting pipeline parallelism and KV cache management: bubble-time overlap for disaggregation, prefix reuse tax of PP stages, and tiering speedup across NVLink, InfiniBand, a…

Post-training with Tinker

Nimbus: a fictitious SaaS website. Starting point for the Voice Agents bootcamp build (add your own voice agent on top).

A Practitioner handbook for production llm serving.

A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes.…

Reviews for the Journal of Open Source Software

GPU Engineering for AI Systems

🚀 Production-ready AI agents framework. Fork → Deploy → Ship in minutes. Multi-agent patterns, FastAPI backend, observability with Opik. Built with Google ADK or Langgraph. MIT License.

AirPods liberated from Apple's ecosystem.

Agent Skills to empower developers building AI applications with Weaviate.

Fast and streamable Excalidraw MCP App

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Automated validation toolkit for tabular ML models in finance and regulated domains.

Data Engineering Zoomcamp is a free 9-week course on building production-ready data pipelines. Join the course here 👇🏼

Official repository of the Manning book - Fight Fraud with Machine Learning - by Ashish Ranjan Jha

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.