-
Microsoft
- https://ismaelmejia.com/
- @iemejia
Highlights
Stars
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
Local hero demo of Microsoft WorkIQ: Ask (mailbox), WebIQ (web search), and Tools (Outlook Drafts) - maps your Uber receipts and plans next year's trip.
Tunnelmole - Connect to local servers from anywhere
Audio Plugin for Audio to MIDI transcription using deep learning.
Crabbox: warm a box, sync the diff, run the suite.
Claude support for Apple Foundation Models
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A very fast, portable and hackable fuzzy finder.
MCP Server and CLI for Apache Spark History Server. Debug Spark applications from AI agents, scripts, or the terminal.
The lance extensions for DuckDB enable reading and writing of lance tables.
Spark integrations for working with Lance datasets
A smarter cd command. Supports all major shells.
A collection of guides and examples for the Gemma open models from Google.
Skills for the Gemma and model/agent interactions
AppImage Package Manager: AppImage sandboxing, local and system installation, update all AppImages, an extensible database of AppImages and portable apps, lists for AppImages and other GNU/Linux bi…
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Fast recursive detection and cleaning of rust projects with interactive TUI and filters. Find rust projects anywhere that meet conditions like "last used more than 3 days ago" or "freable size > 1G…
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
Fabric data agent community website
💬 A proposal for a web API for prompting browser-provided language models