Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONLess than 10 stars, 5+ commits in the last 30 days — projects made with care.
Swift Tokenizers is a high-performance Swift wrapper around Hugging Face's Rust tokenizers crate, focused solely on tokenization without Hub dependencies. It supports macOS, iOS and Linux, offering encoding, decoding, streaming detokenization, chat templates and tool calling.
Generalized ADCS is a Python framework for SmallSat attitude determination and control, offering modular 6-DOF dynamics, estimation, control, and sensor/actuator modeling for research and flight software.
AssayCurveFit is a specialized tool for bioassay curve fitting, designed to analyze dose-response data and model biological activity curves.
Drowse is a local workbench for mechanistic interpretability of large language models, offering a dashboard, Python API, and OpenAI/Ollama-compatible server for activation steering, concept probes, manifolds, SAEs, and Jacobian lenses.
FragmentColor is a cross-platform GPU abstraction for Rust, JS, Python, Swift, and Kotlin. It simplifies shader workflows using WGSL/GLSL across Vulkan, Metal, DirectX, and WebGPU.
A GPU-resident runtime for TensorRT image-to-image video models, enabling high-performance video upscaling by keeping raw frames on the GPU from decode to encode.
Ansible roles for deploying a self-hosted AI/LLM stack on Proxmox, covering model serving, RAG, agents, and LLM application platforms.
NexusLink is an MCP plugin designed for Unreal Engine that exposes editor context, assets, and runtime states of UE projects to AI clients.
LeRobot is an open-source PyTorch library for real-world robotics, offering hardware-agnostic control, standardized dataset formats, and state-of-the-art policies like SmolVLA and world models for training and deployment.
FAME3R is a Python package providing a random forest model for predicting phase 1 and phase 2 sites-of-metabolism in small organic molecules, with models available for non-commercial research.
Premove ITN is an open-source, context-aware inverse text normalization tool for English voice-agent transcripts. It converts spoken ASR output into canonical written forms using a generate-score-decode pipeline with DeBERTa contextual scoring.
A high-performance Rust library for tropical matrix multiplication, featuring SIMD and CUDA backends, multiple semirings, and Python/PyTorch bindings for AI and graph applications.
ferrite is a Rust-native inference engine for GLM-5.3-Flash, featuring PDAF disaggregation, composable TP/CP/DCP parallelism, and exact MHC. It supports GatedDeltaNet and DSA sparse attention with CUDA kernels for sm_100a.
A local multimodal LLM plugin for Unreal Engine 5 providing offline inference for text, speech-to-text, and text-to-speech.
Batchalign3 is a TalkBank audio and ML pipeline for producing and enriching CHAT transcripts, covering ASR, forced alignment, neural morphotagging, translation and utterance segmentation. It ships a CLI, Python package, PyO3 bridge, React dashboard and an experimental Tauri desktop shell.
Finite state and Constraint Grammar based morphological analysers, proofing tools, and language resources for the Komi-Zyrian language, part of the GiellaLT project.
Open-source Finnish language resources and tools built on finite state transducers and Constraint Grammar, providing morphological analysers, spell checkers, and proofing tools for desktop and mobile platforms.
Lociant is a local AI runtime for edge devices like Android phones and Rockchip boards. It enables local model inference via GGUF/llama.cpp, exposes device capabilities as MCP tools, and provides an OpenAI-compatible control API for external orchestration.
aiueos is a capability-secure operating system designed for AI agents, featuring a C-free bare-metal kernel profile and Wasm component execution.
SparkLang is an MIT-licensed language and runtime for plain .spark files: dry-run-first CLI, compile/bytecode dumps, IDE language ops, playbooks, model lab ops, and optional live gateway, voice, browser and CUDA surfaces.
Strata is a native machine learning and linear algebra library written in Mojo, offering scikit-learn-compatible estimators, dense/sparse matrix containers, zero-copy serialization, and composable pipelines with SIMD and LAPACK acceleration.
UL-SMF is a KV cache compression framework for long-context Transformer inference, claiming up to 384x compression via FSQ and 16D latent mapping. The core compression logic requires a proprietary closed-source binary.
HermesMade provides six CLI tools addressing common AI user pain points: censorship risk analysis, model quality monitoring, API cost optimization, local LLM deployment, code inspection, and task cost estimation.
flybrain-sdk is a CPU-first Python SDK for small connectome simulations, with no CUDA requirement. It offers NumPy LIF dynamics, stimulate/action APIs, checkpoints, game and audio demo kits, and on-demand MaleCNS and FlyWire model downloads.
