llms.txt
# 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): Get your first useful result, make it better, and turn it into work you can repeat.
- [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**
- Workspaces
- [Workspaces](https://www.hyperagent.com/docs/concepts/teams.md): Give your team a shared place to work with agents, maintain useful context, and follow the results.
- [Shared Agents & Context](https://www.hyperagent.com/docs/concepts/teams/shared-agents-and-context.md): Share agents and methods with your team, keep the right context available, and choose who can use and maintain it.
- Rooms
- [Rooms](https://www.hyperagent.com/docs/concepts/rooms.md): A room is a shared conversation where teammates and agents work together. Create one, bring in the right people and agents, and decide how each agent takes part.
- [Working in a room](https://www.hyperagent.com/docs/concepts/rooms/working-in-a-room.md): Post a task, follow agents as they take turns, react and reply in threads, and review the room's shared notes and Canvas.
- [Automate a room](https://www.hyperagent.com/docs/concepts/rooms/automate-a-room.md): Let external events and recurring schedules start work in a room, so results arrive where the team already works.
- [Manage a room](https://www.hyperagent.com/docs/concepts/rooms/manage-a-room.md): Find and star rooms, join the ones you need, change a room's settings, leave or archive it, and check what its agents cost.
- [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.
- [Library](https://www.hyperagent.com/docs/concepts/library.md): Where thread artifacts stay organized and ready to reuse.
- [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.
- 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): Follow your agent’s work, refine the result, and keep the job moving.
- [What's in a thread](https://www.hyperagent.com/docs/concepts/threads/whats-in-a-thread.md): Where your agent carries out a task, whether the work starts with a message, a schedule, a webhook, or another agent.
- [Thread context](https://www.hyperagent.com/docs/concepts/threads/loading-context.md): What the model can work with in a thread, how information enters its context, and what changes as the work continues.
- [Thread settings](https://www.hyperagent.com/docs/concepts/threads/thread-settings.md): Adjust the model, parallel work, permissions, and tools for one conversation. Review its usage and suggested learning.
- 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.
- [Have your agents work together](https://www.hyperagent.com/docs/concepts/agents/invocations/other-agents.md): Let one agent ask another for help, and control which agents can work together.
- 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 research 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): Create images, videos, narration, transcripts, and maps in a conversation.
- 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.
- [Google Drive](https://www.hyperagent.com/docs/integrations/google-drive.md): Connect Google Drive so agents can search, read, and organize files and documents.
- [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.
- 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.
- **Guides**
- [Turn a thread into an agent](https://www.hyperagent.com/docs/guides/turn-a-thread-into-an-agent.md): Save what worked in a thread as an agent you can bring new jobs to.
- [Spend less on recurring work](https://www.hyperagent.com/docs/guides/save-on-recurring-work.md): Build a reliable workflow, save it in skills, and use a lower-cost model to run it again.
- [Make your agent’s good work repeatable](https://www.hyperagent.com/docs/guides/where-instructions-belong.md): Stop repeating the same corrections. Give your agent a method it can use on the next job.
- [Teach your agent how you work](https://www.hyperagent.com/docs/guides/teach-your-agent-how-you-work.md): Turn your process, judgment, and quality standards into a skill your agent can use on new jobs.
- [How to run client work in Hyperagent](https://www.hyperagent.com/docs/guides/client-work.md): Workspaces, access, billing, and handover: a practical setup guide for AI agencies and consultancies.
- 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**
- Plans: How plans work and how to manage yours
- [Plans](https://www.hyperagent.com/docs/billing/plans.md): How the free allowance and paid plans work, what each includes, and how to connect a ChatGPT subscription.
- [Start working with Hyperagent for free](https://www.hyperagent.com/docs/billing/plans/free-plan.md): Start working with Hyperagent for free. See what's included, check your usage, and know when your allowance resets.
- [Connect your ChatGPT subscription](https://www.hyperagent.com/docs/billing/plans/connect-chatgpt-subscription.md): Use your ChatGPT subscription to run supported GPT models in Hyperagent. Connect your account and choose what happens when you reach a usage limit.
- [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.
- 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.
- [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: Keyboard shortcuts, troubleshooting, supported models and integrations, and data reference
- [Supported models](https://www.hyperagent.com/docs/reference/supported-models.md): Compare supported models, context windows, reasoning effort, and inference speeds.
- [Supported integrations](https://www.hyperagent.com/docs/reference/supported-integrations.md): Browse the supported apps and services your agent can connect to.
- [Keyboard shortcuts](https://www.hyperagent.com/docs/reference/keyboard-shortcuts.md): Twenty useful shortcuts for finding conversations, working with agents, and reviewing results.
- [Troubleshooting](https://www.hyperagent.com/docs/reference/troubleshooting-faq.md): Find what to check when work stops, an app connection fails, an automation stays silent, or your account looks wrong.
- [Data deletion](https://www.hyperagent.com/docs/reference/data-deletion.md): How to delete your Hyperagent account and the data associated with it.
- [Changelog](https://www.hyperagent.com/docs/changelog.md): Product and documentation updates for Hyperagent.
