Coordinate AI coding agents in shared cubes. Works with Claude Code, Codex, and OpenCode.

Give any AI agent the ability to code

Enables AI assistants and autonomous agents to connect to social media accounts and manage, generate, schedule, upload media for, and publish content across Facebook Pages, YouTube, TikTok, Instagram, and X, plus maintain a content pipeline.

Enables people and AI agents to create, preview, publish, withdraw, and discover offers and requests across goods, services, trips, and delivery, with semantic matching and secure shared rooms for negotiation.

Enables AI agents to print HTML, web pages, PDFs, and images to local printers by bridging to an existing client over WebSocket, including previews, printer discovery, batch jobs, and customizable PDF/print settings.

Enables AI agents to open URLs in a persistent headless browser and interact with pages by clicking, typing, selecting, reading content, evaluating JavaScript, waiting for elements, and capturing screenshots.

Enables AI agents to run web searches and fetch page content by driving a real Chromium browser over CDP, so every request carries an existing profile's cookies, login state, and fingerprint. It also lets agents click elements, fill and submit forms, read the current tab, and check browser/CDP status, returning accurate results from logged-in pages without being treated as an anonymous crawler.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.

Deterministic, persistent 3D/2D spatial world model for AI agents with entity tracking, object permanence, movement simulation, and expected view frustum projection.

High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.

Enables LLM clients to inspect live game state and perform deterministic shop, inventory, backpack layout, and combat actions in a running game through a local bridge.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Enables LLM clients to perform sandboxed file operations, manage persistent notes, fetch live weather and Wikipedia summaries, calculate arithmetic safely, and retrieve current UTC time via a standalone tool server over stdio or HTTP.

Enables AI agents to connect to security cameras, detect objects with YOLOv8, recognize known faces, monitor restricted intrusion zones, capture annotated snapshots, and query a persistent SQLite event history.

Enables AI agents to read public marketplace listings—searching sources and fetching individual listings as structured JSON—through a self-hosted bridge that runs on a residential connection and fetches pages with a real Chromium browser, avoiding datacenter IP blocks. It is strictly read-only, reporting blocks, login walls and unavailable sources as explicit statuses instead of performing any account actions.

Enables AI assistants to look up credentials such as API keys, database URLs, and service tokens by account name, and to read inbox messages like notifications, alerts, and task assignments routed to the agent, all from self-hosted infrastructure.

Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati

A secure and scalable Git MCP server enabling AI agents to perform comprehensive Git version control operations via STDIO and Streamable HTTP.

Enables MCP-compatible clients to send prompts or conversations to Chinese LLM models, list available models with pricing, and compare responses from multiple models through an OpenAI-compatible API.

MCP server for the phlow agent runtime: bounded planner-coder-reviewer agent workflows.

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless buil

Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.