Stars
Use your Mac trackpad as a weighing scale
🏋 Modern open-source fitness coaching platform. Create workout plans, track progress, and access a comprehensive exercise database.
Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!
Low-code tool for automating actions on real time data | Stream processing for the users.
A handheld Linux terminal using Raspberry pi Zero 2W as Core with 4" 720X720 TFT display
🌐 The Internet Computer! Free, Open-Source, and Self-Hostable.
Implementation of the Monkey interpreter from Thorsten Ball's book "Writing an Interpreter in Go" written in Swift.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…
Fancy stream processing made operationally mundane
Fast, modern and advanced photo management suite. Runs as a Nextcloud app.
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
Runtime protection for AI agents and copilots - inspect prompts, validate tool calls, and block threats in real time.
🦜🔗 Build context-aware reasoning applications
An LLM playground you can run on your laptop
[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators
Running large language models on a single GPU for throughput-oriented scenarios.
PyGWalker: Turn your dataframe into an interactive UI for visual analysis
Given an existing docker container, prints the command line necessary to run a copy of it.
Hypermodern Python Cookiecutter
A toolkit for developing and comparing reinforcement learning algorithms.
A toolbox 🧰 for Jupyter notebooks 📙: testing, experiment tracking, debugging, profiling, and more!
SadServers: Linux & DevOps Troubleshooting Scenarios SaaS
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
API, Integration, E2E Testing Agent for Developers that actually work. Generate tests, mocks/stubs for your APIs!