Realiserad/fish-ai 563
Installing the package puts a command called fix on your path
QJHWC/PaperForge 638
PaperForge: a claim in the paper has to name the evidence behind it
qixucen/atom 661
Atom of Thoughts is three dependencies and one config file
pseudo-r/Public-ESPN-API 767
412 v2 routes counted from a WADL, not from live probes
proinsight-io/crewmeld 993
CrewMeld: AI employees, SOP canvases, and tool code that runs in a sandbox
pengzhangzhi/Open-dLLM 662
Open-dLLM: a 0.5B diffusion coder with the whole stack released
pegainfer-project/pegainfer 716
PegaInfer runs on Rust and CUDA, and still inherits NVIDIA Dynamo's package metadata
NucleoidAI/Nucleoid 772
Nucleoid: a declarative logic runtime that keeps assignments true
Nikita-Filonov/ai-review 585
AI Review: LLM Pull Request Comments Across Six Version Control Platforms
NicholasSpisak/second-brain 758
Second Brain: an LLM-maintained Obsidian wiki driven by four Agent Skills
NadirRouter/NadirClaw 661
NadirClaw: a self-hosted OpenAI-compatible proxy that routes prompts by predicted difficulty
ModelTC/LightCompress 750
LightCompress: A Compression Toolkit for LLMs, VLMs and Video Generators
mnemon-dev/mnemon 660
Mnemon: LLM-supervised persistent memory for AI agents, reviewed from the README
ml-explore/mlx-swift-lm 847
mlx-swift-lm: Running LLMs and VLMs on Apple Silicon from Swift
mixelpixx/Konnect 1,410
Konnect: a single Rust binary that turns KiCAD 10 into an MCP server
MindWorkAI/AI-Studio 571
MindWork AI Studio: A C# Desktop Shell for Local and Cloud LLMs
microsoft/vidur 709
Vidur: Simulating LLM Inference Without Booking a GPU
maze-agent/Maze 611