# Documentation

> Each link below is the page's Markdown rendering; drop the `.md` suffix for the HTML page. The complete documentation as one file is at https://www.hyperagent.com/llms-full.txt.

- [Learn Hyperagent](https://www.hyperagent.com/docs.md): Core concepts and reference for working with Hyperagent.

- **Get started**
- [Start here](https://www.hyperagent.com/docs/get-started.md): Agents carry the job, threads hold the work, and everything they learn stays with them.
- [Your first thread](https://www.hyperagent.com/docs/get-started/your-first-thread.md): Do real work in five minutes with nothing configured.
- [Your first agent](https://www.hyperagent.com/docs/get-started/your-first-agent.md): Turn a job worth repeating into a teammate.
- [Teach it something](https://www.hyperagent.com/docs/get-started/teach-it-something.md): Save your first memory and feel the product learning with you.
- [Put it where you work](https://www.hyperagent.com/docs/get-started/put-it-where-you-work.md): Move the agent to Slack, a schedule, or your inbox, so the work starts without you.

- **Platform**
- Agents
  - [Agents](https://www.hyperagent.com/docs/concepts/agents.md): Shape a job once, then hand it to an agent: a teammate that runs it with its own tools and knowledge, wherever the work shows up.
  - [Configuration](https://www.hyperagent.com/docs/concepts/agents/configuration.md): Set up each part of an agent — its brief, autonomy, knowledge, integrations, doorways, and tools.
  - [Activity](https://www.hyperagent.com/docs/concepts/agents/activity.md): The agent's own thread history: every run it has done, live and interactive alike, with search and filters, each row opening the thread behind it.
  - [Models and compute](https://www.hyperagent.com/docs/concepts/agents/models.md): Choose from a wide model catalog and match reasoning, speed, and cost to the size of the job.
  - [Knowledge access](https://www.hyperagent.com/docs/concepts/agents/knowledge-access.md): What an agent can reach and where its new knowledge is saved: read scope, attachment and discovery, save destination, knowledge profiles, and what changes in a workspace.
- Threads
  - [Threads](https://www.hyperagent.com/docs/concepts/threads.md): A thread is one piece of work kept together: the conversation, the agent's workspace, and everything it produced. Threads are isolated by default and connected on purpose.
  - [What's in a thread](https://www.hyperagent.com/docs/concepts/threads/whats-in-a-thread.md): How a thread brings context, tools, connected apps, controls, and finished outputs together so an agent can complete a piece of work.
  - [Thread settings](https://www.hyperagent.com/docs/concepts/threads/thread-settings.md): Every dial for one conversation in one place: the model and how hard it thinks, subagents, execution mode and turn timeout, tools, appearance, the run's cost, and what it proposes to keep.
  - [How context gets into a thread](https://www.hyperagent.com/docs/concepts/threads/loading-context.md): What the agent starts a run with, what surfaces as the conversation moves, and what it fetches on demand: memories, skills, files, tool results, and integration data.
  - [Thread Context Document](https://www.hyperagent.com/docs/concepts/threads/thread-context.md): The agent's working memory for a run: the facts, corrections, decisions, and plan it keeps in a document you can read while it works.
  - [Run, stop, and fork a thread](https://www.hyperagent.com/docs/concepts/threads/running.md): A run is the agent working through your request. It keeps going after you leave, ends when the work is done or when you stop it, and can be forked from any point without losing the original.
- Invocations
  - [Invocations](https://www.hyperagent.com/docs/concepts/agents/invocations.md): Choose where a named agent shows up and what can start its work: time, channels, systems, or another agent.
  - [Schedules](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules.md): Put an agent on a recurrence: define the work, control its threads and write access, deliver the result, and review every run.
  - [Live Mode](https://www.hyperagent.com/docs/concepts/agents/invocations/live-mode.md): Keep an agent on a checklist so it watches for changes on its own and only pings you when something needs attention.
  - [Slack](https://www.hyperagent.com/docs/concepts/agents/invocations/slack.md): Connect Slack, deploy an agent to your workspace, and work with it in channels and DMs.
  - [Telegram](https://www.hyperagent.com/docs/concepts/agents/invocations/telegram.md): Bring your agent into Telegram: the bot connection, account pairing, group authorization, and how media and replies flow both ways.
  - [Email](https://www.hyperagent.com/docs/concepts/agents/invocations/email.md): Give an agent its own email address: control who may send, turn messages into threaded work, and let the agent reply or deliver updates.
  - [Webhooks](https://www.hyperagent.com/docs/concepts/agents/invocations/webhooks.md): Trigger an agent with an HTTP POST: configure the prompt and thread, secure the endpoint, and understand the asynchronous response.
  - [MCP clients](https://www.hyperagent.com/docs/concepts/agents/invocations/mcp-server.md): Connect Claude Code, Claude, Cursor, or another MCP client so it can start work with your Hyperagent agents.
  - [Other agents](https://www.hyperagent.com/docs/concepts/agents/invocations/other-agents.md): Let one named agent hand specialist work to another, with controls on who can call it and what each agent can do.
- Knowledge
  - [Knowledge](https://www.hyperagent.com/docs/knowledge.md): The facts, methods, and reference material agents can use across work, and the controls that decide where each belongs.
  - [Memories](https://www.hyperagent.com/docs/concepts/memories.md): What an agent knows about you and your work, kept as small standing records it can retrieve in future runs.
  - Skills
    - [Skills](https://www.hyperagent.com/docs/concepts/skills.md): A reusable method you teach once so agents do specific work the way your team does it.
    - [Call APIs from a skill](https://www.hyperagent.com/docs/concepts/skills/apis-and-credentials.md): Make a skill that calls an external API work reliably, with scripts and safely held credentials.
    - [Edit and import skills](https://www.hyperagent.com/docs/concepts/skills/skills-edit-and-import.md): Bring an existing method into Hyperagent from a file or documentation, and keep it current.
  - [Documents and tables](https://www.hyperagent.com/docs/knowledge/documents-and-tables.md): Reference material an agent reads and maintains: documents for writing that grows, tables for records with typed columns, shared across threads.
- Learning
  - [Learning](https://www.hyperagent.com/docs/learning.md): How agents get better at your work: they propose what they picked up from a run, you accept or dismiss it, and what you keep becomes standing knowledge.
  - [Manage learning behavior](https://www.hyperagent.com/docs/learning/manage-learning-behavior.md): Decide how much your agent can change on its own: propose and wait for you, save without asking, or nothing at all.
  - [Manage Learnings](https://www.hyperagent.com/docs/learning/manage-suggestions.md): Review and approve new learnings your agent proposes.
  - [Give feedback to your agent](https://www.hyperagent.com/docs/learning/give-feedback.md): Teach the agent on purpose instead of waiting for it to notice.
  - [Rubrics and evaluations](https://www.hyperagent.com/docs/learning/rubrics-and-evaluations.md): Define what good looks like, score real work against it.
- Tools
  - [Tools](https://www.hyperagent.com/docs/tools.md): Built-in capabilities agents use to research, operate sites, compute, and create finished work.
  - [Research](https://www.hyperagent.com/docs/tools/research.md): How an agent finds things out: web search with a Standard or Exa provider, cited answers and deep reports, lookalike discovery, verified datasets, and search across your own threads.
  - [Browser](https://www.hyperagent.com/docs/tools/browser.md): Use a live browser to navigate sites, complete forms, work behind logins, hand control to a person, and capture evidence.
  - [Code and files](https://www.hyperagent.com/docs/tools/data-and-code.md): Analyze data, update many files, work with websites and repositories, and produce finished outputs using a private computer.
  - [Webpages and slides](https://www.hyperagent.com/docs/tools/webpages-and-slides.md): Publish reports, dashboards, and presentations as versioned artifacts with public URLs, plus early-alpha interactive HyperApps.
  - [Media generation](https://www.hyperagent.com/docs/tools/media-generation.md): Everything an agent can create as media: images, short video with native audio, speech, transcripts, avatar videos, and maps.
- Integrations: Connect Hyperagent to your tools
  - [Integrations](https://www.hyperagent.com/docs/integrations.md): The apps and services Hyperagent agents can connect to, and how to connect them.
  - [Custom MCP](https://www.hyperagent.com/docs/integrations/custom-mcp.md): Connect an internal or vendor MCP server so an agent can use its tools.
  - [Slack](https://www.hyperagent.com/docs/integrations/slack.md): Connect Slack, deploy an agent to your workspace, and work with it in channels and DMs.
  - [HubSpot](https://www.hyperagent.com/docs/integrations/hubspot.md): Connect HubSpot so your agents can read and update contacts, companies, deals, and tickets.
  - [Databricks](https://www.hyperagent.com/docs/integrations/databricks.md): Find the credentials you need to connect your Databricks workspace.
- Workspaces
  - [Workspaces](https://www.hyperagent.com/docs/concepts/teams.md): A shared workspace that scopes a set of agents, skills, and memories, with governance that lets many people use what a few maintain.
  - [Workspace agents](https://www.hyperagent.com/docs/concepts/teams/team-agents.md): Choose the best way to share your agents with your team.
  - [Workspace skills](https://www.hyperagent.com/docs/concepts/teams/team-skills.md): Share reusable methods with a Workspace, choose which account runs them, and decide when to use the shared source or fork it.
  - [Workspace memories](https://www.hyperagent.com/docs/concepts/teams/team-memories.md): How a workspace agent's learning becomes shared context
  - [Workspace roles](https://www.hyperagent.com/docs/concepts/teams/members.md): Choose by what each person needs to do: run, maintain, or administer agents.
  - [Command Center](https://www.hyperagent.com/docs/concepts/command-center.md): The cockpit for running many agents at once: catch what's waiting on you, see what's running, and track cost and quality across the fleet, then drill into the one that needs you.
  - [Inbox](https://www.hyperagent.com/docs/concepts/teams/inbox.md): Review questions, approvals, mentions, and failing schedules from your agents in the current workspace.
  - [Create a workspace and add people](https://www.hyperagent.com/docs/concepts/teams/create-a-team.md): Make a shared workspace, invite people by email or a shared link, assign the role each person needs, and manage membership as it changes.
  - [What's private and what's shared](https://www.hyperagent.com/docs/concepts/teams/whats-private.md): Understand Personal, workspace Owner oversight, channel visibility, and the audience for documents and other outputs.
- [Library](https://www.hyperagent.com/docs/concepts/library.md): Where thread artifacts stay organized and ready to reuse.
- Migrate: Import your existing agents into Hyperagent.
  - [Migrate from OpenClaw to Hyperagent](https://www.hyperagent.com/docs/migrate/openclaw.md): Migrate your OpenClaw agent in minutes using the import wizard.

- **Account**
- Billing & Credits: Credits, plans, shared billing, usage, and invoices
  - [Billing and credits](https://www.hyperagent.com/docs/billing.md): How credits, billing periods, plan changes, and shared billing work, and where to find every live number in the product.
  - [Credits](https://www.hyperagent.com/docs/billing/credits.md): How credits work, what they pay for, when they expire, and what to do when your balance runs low.
  - Plans: How plans work and how to manage yours
    - [Plans](https://www.hyperagent.com/docs/billing/plans.md): How Hyperagent's monthly plans work, what each plan grants, and how to connect a ChatGPT subscription.
    - [Connect your ChatGPT subscription](https://www.hyperagent.com/docs/billing/plans/connect-chatgpt-subscription.md): Connect ChatGPT to Hyperagent with OAuth, choose fallback behavior, and see which usage is covered by ChatGPT or billed through Hyperagent.
    - [Manage your plan](https://www.hyperagent.com/docs/billing/plans/manage-plan.md): How to upgrade, downgrade, or cancel, when each change takes effect, how to manage your card, and what happens to the rest of a paid period.
  - [Shared Billing](https://www.hyperagent.com/docs/billing/shared-billing.md): Put multiple members on one organization payment method, manage membership, and understand how existing credits move.
  - [Usage and invoices](https://www.hyperagent.com/docs/billing/invoices.md): Choose the right view for account-level usage, costs across agents, detailed agent and thread spend, and billing history.
  - [Control your costs](https://www.hyperagent.com/docs/billing/control-costs.md): The two levers that shape what you spend in Hyperagent, which plan you pick and which model does the work.

- **Separator**
- Reference: Troubleshooting, data deletion, and model reference
  - [Troubleshooting FAQ](https://www.hyperagent.com/docs/reference/troubleshooting-faq.md): Short answers to the questions that show up most in community and support, with links to deeper docs.
  - [Troubleshoot a stuck run](https://www.hyperagent.com/docs/reference/runtime-limits.md): What to check when a run pauses, stops early, loses tool access, or fails to deliver.
  - [Data deletion](https://www.hyperagent.com/docs/reference/data-deletion.md): How to delete your Hyperagent account and the data associated with it.
  - [Models and compute](https://www.hyperagent.com/docs/reference/supported-models.md): Choose a model and configure reasoning, runtime, timeouts, and context compaction.
- [Changelog](https://www.hyperagent.com/docs/changelog.md): Product and documentation updates for Hyperagent.