Official inference framework for 1-bit LLMs

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

Useful n8n resources: list of community nodes and tutorials

A MCP server for our beloved terminal multiplexer tmux.

Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.

Enterprise-grade React Native framework for microservice apps. Brownfield friendly, 200KB bundles, AWS-ready infrastructure.

An example Hono MCP server using Streamable HTTP

Run Claude Agent (Claude Code) in a sandbox, control it via websocket

TypeScript SDK for agent portability, discovery and trust based on ERC-8004.

Simple web API for extracting images/audio from video and converting audio/video/image files with ffmpeg.

Fully elastic, MongoDB API compatible distributed JSON document database with compute-storage separation and robust ACID transactions.

Render a LynxJS bundle in your React Native application.

🙌 OpenHands: AI-Driven Development

Create copilot usage reports as job summaries, and much more!

Delivery infrastructure for agentic apps - Plano is an AI-native proxy and data plane that offloads plumbing work, so you stay focused on your agent's core logic (via any AI framework).

Run Claude Code on OpenAI models

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

🐝 AI-powered browser assistant ("Cline for web browsing")

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Overview of alternative open source front-ends for popular internet platforms (e.g. YouTube, Twitter, etc.)

Generative Emoji for the rest of us.

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

The fastest way to build robust AI agents

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

🦙 echoOLlama: A real-time voice AI platform powered by local LLMs. Features WebSocket streaming, voice interactions, and OpenAI API compatibility. Built with FastAPI, Redis, and PostgreSQL. Perfect…

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

React hooks done right, for browser and SSR.

An open-source starter kit based on Midday.

A typescript package to execute JavaScript and TypeScript code in a webassembly quickjs sandbox