KiCAD MCP Server connects LLMs with KiCAD for AI-driven PCB design operations, enabling schematic editing, routing, and custom footprint generation via the Model Context Protocol.
Kitaru offers a framework-agnostic runtime for autonomous AI agents with durable execution via checkpointing, enabling replay and state preservation to avoid costly restarts on failures.
Knowledge Engine connects markdown wikis with Memvid’s sub-5ms semantic search using a dual-layer design, automatic sync, and entity extraction for AI-augmented knowledge work.
KohakuTerrarium offers a Python framework to build modular AI agents using a unique algebra for composing multi-agent pipelines, with session persistence and multi-runtime support.
KRR helps Kubernetes users optimize resource allocation by analyzing Prometheus metrics and generating actionable recommendations. This Python tool integrates with kube-prometheus-stack or Robusta’s embedded Prometheus.
kvcached provides a plugin cache layer for SGLang and vLLM Python LLM environments, easing deployment with PyPI and Docker support. Useful for optimizing LLM workflows.
LycheeMemory offers a lightweight semantic memory system for LLM agents, cutting token use by 71% and costs by 55% compared to native memory, with SQLite + LanceDB backend and REST/MCP APIs.
MAGI implements a multi-round debate protocol among three LLMs to match stronger models’ accuracy via iterative critique and voting. It offers fault tolerance, adaptive escalation, and persona presets.
Magika replaces magic-byte heuristics with a tiny deep learning model for file type detection, achieving ~99% accuracy across 200+ types with 5ms CPU inference.
A curated catalog of 20+ LLM agent frameworks and tools organized by agent type and capabilities. Understand architectural differences and trade-offs in LLM agent design.
A curated directory cataloging over 200 production-ready open-source AI projects across the machine learning stack, from training frameworks to self-hosted UIs.
Matrix-3D generates explorable 360-degree 3D worlds from text or images using panoramic video and 3D Gaussian splatting, optimized to run on 12-19GB VRAM consumer GPUs.
MeanVC enables real-time zero-shot voice conversion using mean flows and diffusion transformers for single-step inference, addressing latency bottlenecks in diffusion models.
MediaLyze is a read-only, self-hosted media library analyzer using FastAPI and React. It features incremental scanning with path+size+mtime hashing to avoid redundant scans.
Memary is an open-source memory layer for AI agents using knowledge graphs and recursive retrieval to efficiently store and query agent memories. It supports multi-agent setups and integrates with LlamaIndex and OpenAI.
Meta-Harness from Stanford IRIS Lab automates the search for optimal harness configurations around LLMs, evolving memory, retrieval, and context systems for better task-specific performance.
MiniStack offers 40+ AWS services emulated locally using real containers and a clever multi-tenancy model via AWS_ACCESS_KEY_ID, all on a single port with a tiny footprint.
MLE-Agent is a Python LLM agent framework that automates ML workflows, including autonomous Kaggle competitions and smart debugging with human-in-the-loop. Supports multiple LLMs and local RAG.
MotionCrafter jointly reconstructs 4D geometry and dense motion from monocular video using a unified 4D VAE, eliminating post-optimization. This Python framework offers training and visualization tools.
MultiWorld offers a unified framework for multi-agent multi-view video world modeling using a frozen VGGT backbone for implicit 3D understanding. It supports scalable multi-agent control and autoregressive inference.
