Tag

iii

Provides a shared runtime that composes, extends, and observes services in real time by modeling capabilities as discoverable workers, functions, and triggers. It collapses separate integration surfaces (queues, cron, HTTP, observability) into one live catalog so agents and services can call and trace each other immediately.

Sim

Lets teams build, deploy, and manage AI agents from chat, visual workflows, code, knowledge bases, tables, and more than a thousand integrations.

Fli

Provides programmatic access to Google Flights via a Python library, CLI, and an MCP server — enabling assistants and apps to search flights with filters (time windows, cabin, stops, airlines) by reverse‑engineered API rather than HTML scraping.

Rowboat

Connects to Gmail, Calendar, and meeting notes to build a local, Obsidian-compatible Markdown graph it acts on — drafting emails, briefs, and decks. Memory accumulates instead of resetting each session; runs on local or hosted models, extensible via MCP.

UI-TARS Desktop

Drives your computer from natural language: a vision-language model reads raw screenshots and works the mouse and keyboard like a person, controlling any GUI app without APIs or accessibility hooks. Local or remote operator modes on Windows and macOS.

Verifiers: Environments for LLM Reinforcement Learning

Bundles a dataset, an interaction harness, and rubric-based reward functions into one RL environment for training and evaluating LLMs — also usable as an eval, synthetic-data pipeline, or agent harness for any OpenAI-compatible endpoint.

UI-TARS

Reads GUI screenshots and directly outputs desktop, mobile, and browser actions — clicking, typing, navigating — as one end-to-end vision-language model rather than a modular pipeline. Scores 84.8% on WebVoyager and 42.5% on OSWorld.

AI_NovelGenerator

Generates multi-chapter long-form novels with LLMs, automatically linking context and managing foreshadowing for global coherence. Features vector-based retrieval, character/state tracking and a GUI-driven pipeline; requires LLM/embedding API keys.

Cloudflare Agents

Runs stateful AI agents as Cloudflare Durable Objects — each keeps its own storage and lifecycle, hibernating when idle and waking on demand. Adds WebSocket state sync, type-safe RPC, resumable LLM streaming, MCP roles, and durable workflows.

vLLM Ascend Plugin

Provides a hardware plugin that runs vLLM on Huawei Ascend NPUs by mapping vLLM execution and memory management to the Ascend runtime. Key features: support for Transformer/MoE/embedding/multimodal models, official docs, CI-backed release branches and community maintenance.

Neuro SAN Studio

Hands-on studio to design, test and deploy declaratively configured multi-agent systems built on the Neuro SAN framework. Ships ready examples, an Agent Network Designer UI (nsflow), CLI tooling, and integrations with major LLMs and external tools for rapid prototyping.

Cua

Spins up sandboxed VMs and containers (macOS, Linux, Windows, Android) that an AI agent can fully control through one unified SDK, cloud or local, plus a benchmark suite and background drivers that automate native apps without grabbing the cursor.