A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Doing simple retrieval from LLM models at various context lengths to measure accuracy

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

LLM inference in C/C++

Port of OpenAI's Whisper model in C/C++

GPU overclocking utility for Blackwell RTX 50-series on Linux

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Awesome list of add-ons, hooks, tools, skills, and resources for the pi coding agent (pi-mono).

Real-time code feedback for pi — LSP, linters, formatters, structural analysis

Awesome autocompletion, static analysis and refactoring library for python

a python refactoring library

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

MicroPython - a lean and efficient Python implementation for microcontrollers and constrained systems

A serverless worker to run LLMs in the cloud - using llama.cpp!

A serverless ollama worker for runpod.io

Software, firmware, and gateware for OrangeCrab ATE.

Jupyter Lite kernel for micropython and circuitpython

Collect, review, and upload redacted pi session files to a Hugging Face dataset

TinyML framework for motion recognition etc from accelerometer/gyro/IMU data

A modern take at a radio link simulator

Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Running Rust on the (Linux) Litex VexRiscv FPGA SOC

ABC-Bench is a benchmark for Agentic Backend Coding. It evaluates whether code agents can explore real repositories, edit code, configure environments, deploy containerized services, and pass exter…

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…