Glove documentation

Glove is a set of TypeScript primitives for building agent harnesses: coding agents, personal assistants, support desks, voice agents, research tools, whole workforces. Glove Foundry turns harnesses into a running system. Kuiper runs that system in production. Most of what an agent needs already exists as a primitive. These docs are organised so you find it before you build it.

Three layers, each wrapping the one inside it. Glove is the harness around a model, Foundry turns harnesses into a running system, and Kuiper runs that system in production. Each name is a part you would otherwise build yourself; click one for its primitives.

Start here

Build it up, layer by layer

One agent, eight steps. Each step adds one part of a harness and shows the primitive for it in a few lines, so by the end you have used most of Glove and know where everything else goes.

  1. 01A loop and a toolLoop · Tools
  2. 02Show your workSurface
  3. 03Control what it seesContext
  4. 04Make it rememberState
  5. 05Give it a workspaceWorkspace
  6. 06Split the workTeam
  7. 07Make it a systemIdentity · Time · Arrival · Oversight · Access
  8. 08Put it in productionRun · Keep · Reach · Watch

Foundry or glove-core?

Both run the same 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 writeWith Foundry you get
Many users, each with their own agentYour own instance table and lookupPersisted agent instances created from one definition
Several threads per userStore keys and routingFirst-class conversations per instance
An API other services can callAn HTTP server and run trackingTyped client, REST API, OpenAI-compatible endpoints
Work that happens laterA job queue and cronSchedules, sleep and spawn as built-in agent tools
Events from Slack, email or webhooksWebhook handlers and dispatchTransmissions, playbooks and auto-provisioned agents
Human sign-off on risky actionsA pause/resume mechanismExpiring approval records with approve/deny APIs
To see what happenedLoggingA run inspector and WebChat at localhost:4141
Somewhere to run itA Dockerfile, a server and a volumeKuiper deploys the folder as it is
A UI that renders inside the chatBoth: 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. Tools move from one to the other unchanged.

I want to…

GoalReadPackage
See everything that already exists before I build somethingPrimitives mapall
Build a coding agentCoding agent blueprintglove-core · glove-execution
Build a personal assistant that works while I'm awayPersonal agent blueprintglove-foundry · glove-memory
Run many durable agents with an HTTP API, a dashboard and schedulesFoundry tutorialglove-foundry
Deploy my agent and keep it runningDeploy on Kuiperglove-foundry · Kuiper
Talk to my agent from any OpenAI SDK or chat UIOpenAI-compatible APIglove-foundry
Have a human approve risky actions before they runApprovals & steeringglove-foundry · glove-core
Wake an agent on a cron, after a delay, or when a webhook arrivesPlaybooks, schedules & sleepglove-foundry
Connect an agent to Telegram, Slack, email or a ticket systemApps & transmissionsglove-foundry
Add a chat agent to my existing Next.js appQuickstartglove-react · glove-next
Run an agent in a script, CLI or backend serviceServer-side agentsglove-core
Let tools render UI and wait for the user mid-conversationDisplay stackglove-core · glove-react
Keep current state in front of the model without rewriting the promptControl what it seesglove-core
Remember people, facts and past sessionsMemoryglove-memory
Build an agent that pursues an objective and collects what it is missingGoal-oriented agentsglove-memory · glove-facts
Produce PDFs, spreadsheets, slides and images as filesWorking environmentglove-working-environment
Replace 50 tool definitions with one code-eval toolCode executionglove-js · glove-python · glove-lisp
Browse websites, write code and run servers in a sandboxBrowsers & sandboxesglove-execution
Use tools from MCP servers (Notion, Gmail, Linear…)MCPglove-mcp
Make cheap, fast typed decisions (triage, routing, filtering)Classifier modelsglove-classifier
Build a voice agentVoice agent blueprintglove-voice · glove-voice-s2s · glove-realtime
Generate and review images or video as a directed workflowImage workflowsglove-image · glove-video
Have agents message and delegate to each otherSplit the workglove-core · glove-mesh

Learn by example

For LLMs and coding agents

Point your coding agent at these before it writes Glove code. They lead with the same parts and primitives as these pages, so the agent reaches for what exists instead of rebuilding it.

  • /llms.txt: the mental model, the primitives map and an index of every page.
  • /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 skills for Glove, Foundry and deploying on Kuiper.
  • kuiper.sh/llms.txt: everything Kuiper does, for deploying what you build.