The cost efficiency of S3 with the speed of local RAM. A multi-tenant vector and full-text search engine featuring a tiered RAM → NVMe → S3 architecture for microsecond latency on top of object sto…

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Portable , scalable , secure AI Agents

A highly performant cache for very small data

🪇 Minimal terminal spinners for Rust

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

Kronos: A Foundation Model for the Language of Financial Markets

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

AI-first knowledge base and startup OS

Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

Memory Intelligence Agent

A flexible commandline tool for template rendering. Supports lots of local and remote datasources.

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-st…

A TurboQuant inference server

Python module for parsing semi-structured text into python tables.

VSCode Remote Development: Open any folder on a remote machine using SSH.

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech interaction with a lightweight, pure-Python, production-rea…

A PyTorch-based Speech Toolkit

The Official Implementation of "Explaining the Reasoning of Large Language Models Using Attribution Graphs"

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

A community-maintained Python framework for creating mathematical animations.

A fast multimodal LLM for real-time voice

Model Context Protocol (MCP) server that enables AI agents to create rich, real-time visualizations using A2UI. Supports configurable canvas sizes optimized for TV/Chromecast casting.

The SDK for A2UI protocol.

PersonaPlex on Apple Silicon: an MLX port of NVIDIA’s full-duplex speech-to-speech model with realtime local/web modes and offline WAV inference.