Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

A suite of MCP servers that enables an LLM to orchestrate specialized services to generate travel itineraries, find flights and accommodations, discover local events, analyze weather conditions and…

Contexts Optical Compression

Deepagents is an agent harness built on langchain and langgraph. Deep agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped …

Code and model to control the AH!

Simple, modern and fast file watching and code reload for Python, written in Rust

Turn docstrings into LLM-functions

AWS MCP Servers — helping you get the most out of AWS, wherever you use MCP.

A typeface for creating sparklines in text without code.

PyTorch building blocks for the OLMo ecosystem

Weighs the soul of incoming HTTP requests to stop AI crawlers

MCP server for fetch web page content using Playwright headless browser.

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.…

Real-time analytics on Postgres tables

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

A simple AI-powered Discord to answer questions based on a set of documents.

Warewulf is a stateless and diskless container operating system provisioning system for large clusters of bare metal and/or virtual systems.

A command-line Ollama client for scripting.

superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A CLI/TUI that simplifies launching VSCode projects, with a focus on dev containers

Machine learning model for predicting Ethereum priority fees using mempool and historical gas data.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

The Embedded, Distributed, Document DB

Native JVM WebAssembly runtime

An opinionated front-end starter kit for your "nobuild" application

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

An AI Hedge Fund Team

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.