Menlo Research

jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

model-catalog

llama.cpp

LLM inference in C/C++

flashinfer

FlashInfer: Kernel Library for LLM Serving

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

verifiers-deepresearch

Verifiers for LLM Reinforcement Learning

open_asr_leaderboard

searxng-docker-for-mcp

The docker-compose files for setting up a SearXNG instance with docker.

prompt-experiments

crawl4ai

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

visual-thinker

robotics-sim

cua

c/ua is the Docker Container for Computer-Use AI Agents.

cortex.llamacpp

cortex.llamacpp is a high-efficiency C++ inference engine for edge computing. It is a dynamic library that can be loaded by any server at runtime.

cortex.cpp

Local AI API Platform

litellm

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

IsaacSimZMQ

Isaac SIM extension for communication with external application via ZMQ

Isaac-GR00T

NVIDIA Isaac GR00T N1

JanCode

Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.

verl-deepresearch

verl: Volcano Engine Reinforcement Learning for LLMs

ichigo-demo

models

Models support in Jan and Cortex

unitree_sdk2

Unitree robot sdk version 2. https://support.unitree.com/home/zh/developer

research

robotics-morph

Adaptive control for cross embodiment of robot arm manipulation

mujoco-wasm

Multi-Joint dynamics with Contact. A general purpose physics simulator.

ReZero

libccd

Library for collision detection between two convex shapes

robotics-portal

A simulation platform running entirely on your browser.

OpenCrawl

🌐 OpenCrawl: An ethical, high-performance web crawler built for scale A powerful web crawling library that respects robots.txt and rate limits while leveraging Kafka for high-throughput data processing. Built with ethics and efficiency in mind.