The fastest image difference tool in the world (Zig port of odiff)
Chat-driven TUI where the AI ships React/Ink components that run in a sandbox
Minimal Codex/OpenAI native tools for Pi: Codex image_generation, view_image, apply_patch
A transport for pino that sends messages to Loki
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
WASI threads proposal implementation in JavaScript
CRoaring official port for NodeJS
Reusable Elench desktop shell packaged behind a public domain API.
Claude Code task tools for Codex, including review and delegated subtasks.
An [MCP](https://modelcontextprotocol.io) server that lets AI assistants generate wireframes programmatically. Returns editable Wiretext URLs or renders ASCII art directly.
Agent adapters for thread-phase — wraps hermes, openclaw, anthropic, codex, claude-code, pi behind a uniform AgentAdapter protocol. Agent SDKs are optional peer deps; install only what you use.
MCP server for [Lace](https://inlace.co). Connects your coding agent to approved product decisions so it can see exactly what needs to change and ship the fix.
Find missing Codex CLI chats for the current directory and print resume commands.
The Codex SDK for JavaScript/Typescript. It provides generated types and convenient ways to access the graphql api.
High performance (de)compression in an 8kB package
Independent OpenClaw plugin for the Codex App Server protocol
Run a function with the possibility to interrupt it from another thread
Lodestar (夜航星) — IM-native frontend for Codex via Feishu Card Kit streaming
HTTP/WebSocket server that wraps Claude Code, Codex, and OpenCode as backend processes
Run the local Codex app bridge from a phone or browser URL.
AI tool management and prompt templates plugin for VibeControls Agent — manage AI tools, prompt templates with variables (Bun runtime)
This package contains the source code for tools used for building and testing the React components for the [Cloudscape Design System](https://cloudscape.design/).
Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference