Glove documentation

Glove is a family of TypeScript packages for building software that an AI agent operates. Pick the layer that matches what you are building — you can always move up a layer later without rewriting your tools.

Choose a path

Complete agent systemsGlove Foundry

A framework and runtime: file-routed agents, persisted instances and conversations, a run queue, a typed client, an OpenAI-compatible API, schedules, inbound integrations, approvals, and a built-in inspector and chat UI.

glove-foundry An agent inside your appThe Glove runtime

The agent loop as a library. You own the server, storage and UI; Glove gives you tools, a display stack that renders React mid-conversation, model adapters and context compaction.

glove-coreglove-reactglove-next One capabilityIndividual packages

Memory, voice, MCP, sandboxes, REPLs, image and video, classifiers and mesh each work on their own and mount onto any Glove agent — inside Foundry or not.

glove-memoryglove-mcpglove-voice…

Foundry or glove-core?

Both run the same agent loop and the same tools. The difference is how much of the surrounding system you want to build yourself.

You need…	With glove-core you write	With Foundry you get
Many users, each with their own agent	Your own instance table and lookup	Persisted agent instances created from one definition
Several threads per user	Store keys and routing	First-class conversations per instance
An API other services can call	An HTTP server and run tracking	Typed client, REST API, OpenAI-compatible endpoints
Work that happens later	A job queue and cron	Schedules, sleep and spawn as built-in agent tools
Events from Slack, email or webhooks	Webhook handlers and dispatch	Transmissions, playbooks and auto-provisioned agents
Human sign-off on risky actions	A pause/resume mechanism	Expiring approval records with approve/deny APIs
To see what happened	Logging	A run inspector and WebChat at localhost:4141
A UI that renders inside the chat	Both: the display stack is part of glove-core

Rule of thumb: if the agent is the product backend, start with Foundry. If the agent is one feature inside an app you already run, start with the quickstart.

How the layers stack

the Glove stacktext

your product          UI · auth · billing · your data
──────────────────────────────────────────────────────────────────────
glove-foundry         file routes · instances · conversations · apps
                      playbooks · schedules · approvals · HTTP + OpenAI API
                      inspector · WebChat · persistence adapters
──────────────────────────────────────────────────────────────────────
capability packages   memory · forms · goals · facts · working environment
                      JS/Python/Lisp REPLs · browsers & sandboxes · MCP
                      voice · realtime voice · image · video · mesh · classifiers
──────────────────────────────────────────────────────────────────────
glove-core            agent loop · tools · display stack · stores
                      model adapters (Anthropic, OpenAI, Gemini, OpenRouter…)

I want to…

Goal	Read	Package
Run many durable agents with an HTTP API, a dashboard and schedules	Foundry tutorial	`glove-foundry`
Talk to my agent from any OpenAI SDK or chat UI	OpenAI-compatible API	`glove-foundry`
Have a human approve risky actions before they run	Approvals & steering	`glove-foundry · glove-core`
Wake an agent on a cron, after a delay, or when a webhook arrives	Playbooks, schedules & sleep	`glove-foundry`
Connect an agent to Telegram, Slack, email or a ticket system	Apps & transmissions	`glove-foundry`
Add a chat agent to my existing Next.js app	Quickstart	`glove-react · glove-next`
Run an agent in a script, CLI or backend service	Server-side agents	`glove-core`
Let tools render UI and wait for the user mid-conversation	Display stack	`glove-core · glove-react`
Remember people, facts and past sessions	Memory	`glove-memory`
Build an agent that pursues an objective and collects what it is missing	Goal-oriented agents	`glove-memory · glove-facts`
Collect structured information over a conversation	Forms	`glove-memory`
Produce PDFs, spreadsheets, slides and images as files	Working environment	`glove-working-environment`
Replace 50 tool definitions with one code-eval tool	Code execution	`glove-js · glove-python · glove-lisp`
Browse websites, write code and run servers in a sandbox	Browsers & sandboxes	`glove-execution`
Use tools from MCP servers (Notion, Gmail, Linear…)	MCP	`glove-mcp`
Make cheap, fast typed decisions (triage, routing, filtering)	Classifier models	`glove-classifier`
Build a voice agent (STT → agent → TTS)	Voice pipeline	`glove-voice`
Use realtime speech-to-speech models or a live avatar	Realtime voice & avatars	`glove-voice-s2s`
Keep a voice agent fast while a heavier model does the tool work	Voice agent architectures	`glove-voice · glove-voice-s2s · glove-mesh`
Generate and review images or video as a directed workflow	Image workflows	`glove-image · glove-video`
Have agents message and delegate to each other	Mesh	`glove-mesh`

Learn by example

ShowcaseComplete applications

Travel planner, coding agent, voice coffee shop, a browser-and-sandbox operator, a brand workforce and more — read end to end.

Foundry exampleOperator

A Foundry agent that browses, writes code and keeps a server running in a persistent container.

GalleryImage & video galleries

Real generated work with the prompts, pipeline traces and spend behind every frame.

For LLMs and coding agents

Every page here is also available in machine-readable form. Point your coding agent at these before it writes Glove code.

/llms.txt — an index of every page with one-line summaries.
/llms-full.txt — the condensed Glove reference in one file.
/foundry/llms-full.txt — the complete Foundry reference: conventions, APIs, endpoints and built-in tools.
Agent skills — drop-in Claude Code skills for Glove and Foundry.