# H Tech Hub ## Docs - [About the Models API](https://hub.hcompany.ai/about-the-models-api.md): OpenAI-compatible access to the Holo Vision-Language Models for computer use. - [Agent loop](https://hub.hcompany.ai/agent-loop.md) - [API reference](https://hub.hcompany.ai/api-reference.md): Endpoint, authentication, conventions, and the Holo-specific request surface. - [Create an agent](https://hub.hcompany.ai/computer-use-agents/agents/create.md): Create a reusable agent in your own catalog. - [Delete an agent](https://hub.hcompany.ai/computer-use-agents/agents/delete.md): Remove an agent from your catalog. - [List agents](https://hub.hcompany.ai/computer-use-agents/agents/list.md): Discover available agents from your catalog and the H preset catalog. - [Agents](https://hub.hcompany.ai/computer-use-agents/agents/overview.md): An agent is a reusable configuration that defines what an AI agent can do. - [Patch an agent](https://hub.hcompany.ai/computer-use-agents/agents/patch.md): Change individual fields of an agent without resending the full object. - [Retrieve an agent](https://hub.hcompany.ai/computer-use-agents/agents/retrieve.md): Get the full specification of a single agent. - [Update an agent](https://hub.hcompany.ai/computer-use-agents/agents/update.md): Replace the configuration of an agent in your catalog. - [Complete a profile upload](https://hub.hcompany.ai/computer-use-agents/browser-profiles/complete-upload.md): Finalize a browser profile after its archive is uploaded. - [Delete a browser profile](https://hub.hcompany.ai/computer-use-agents/browser-profiles/delete.md): Remove a browser profile. - [Get the default browser profile](https://hub.hcompany.ai/computer-use-agents/browser-profiles/get-default.md): Fetch your default profile for a browser. - [Initiate a profile upload](https://hub.hcompany.ai/computer-use-agents/browser-profiles/initiate-upload.md): Get a presigned URL to upload a browser profile archive. - [List browser profiles](https://hub.hcompany.ai/computer-use-agents/browser-profiles/list.md): Browse your organization's browser profiles. - [Retrieve a browser profile](https://hub.hcompany.ai/computer-use-agents/browser-profiles/retrieve.md): Fetch a browser profile by id. - [Set the default browser profile](https://hub.hcompany.ai/computer-use-agents/browser-profiles/set-default.md): Mark a profile as your default for its browser. - [Unset the default browser profile](https://hub.hcompany.ai/computer-use-agents/browser-profiles/unset-default.md): Clear the default flag on a profile. - [Configure the browser](https://hub.hcompany.ai/computer-use-agents/browser/configuration.md): Define a Browser environment: its fields, modes, and actions. - [Run the agent in your own browser](https://hub.hcompany.ai/computer-use-agents/browser/local-control.md): Let an agent drive Chrome on your own machine. - [Bring your own browser profile](https://hub.hcompany.ai/computer-use-agents/browser/profiles.md): Start a browser session from saved cookies and storage. - [Route the browser through a proxy](https://hub.hcompany.ai/computer-use-agents/browser/proxy.md): Egress the browser through an H-managed proxy or one you operate. - [Changelog](https://hub.hcompany.ai/computer-use-agents/changelog.md): Notable changes to the Computer-Use Agents API and SDKs. - [Build with coding assistants](https://hub.hcompany.ai/computer-use-agents/coding-skills.md): Install the hai-agents skill so Claude Code, Cursor, and other assistants know the H APIs and help you build use cases. - [Give an agent custom tools](https://hub.hcompany.ai/computer-use-agents/custom-tools.md): Extend the agent's toolbox with functions from your own code: the agent calls them, the SDK executes them, the run continues with the result. - [Run the agent on your own desktop](https://hub.hcompany.ai/computer-use-agents/desktop/local-control.md): Let an agent drive the mouse, keyboard, and screen on your own machine. - [Create an environment](https://hub.hcompany.ai/computer-use-agents/environments/create.md): Create a reusable environment in your own catalog. - [Delete an environment](https://hub.hcompany.ai/computer-use-agents/environments/delete.md): Remove an environment from your catalog. - [List environments](https://hub.hcompany.ai/computer-use-agents/environments/list.md): Discover available environments. - [Environments](https://hub.hcompany.ai/computer-use-agents/environments/overview.md): The surfaces an agent perceives and acts upon. - [Patch an environment](https://hub.hcompany.ai/computer-use-agents/environments/patch.md): Change individual fields of an environment without resending the full spec. - [Retrieve an environment](https://hub.hcompany.ai/computer-use-agents/environments/retrieve.md): Get the full specification of an environment. - [Update an environment](https://hub.hcompany.ai/computer-use-agents/environments/update.md): Replace the configuration of an environment in your catalog. - [Handle API errors](https://hub.hcompany.ai/computer-use-agents/errors.md): How Computer-Use Agents report errors, and what to do about them. - [Computer-Use Agents](https://hub.hcompany.ai/computer-use-agents/introduction.md): Launch your first computer-use agent. - [Run agents over MCP](https://hub.hcompany.ai/computer-use-agents/mcp.md): Run and manage H agents from any MCP host, no HTTP or SDK code. - [Parallelize work with subagents](https://hub.hcompany.ai/computer-use-agents/multi-agent.md): Let one manager agent split a task and delegate the pieces to specialist subagents. - [Run agents from n8n](https://hub.hcompany.ai/computer-use-agents/n8n.md): Run Computer-Use Agents from an n8n workflow over plain HTTP. - [Watch and steer sessions](https://hub.hcompany.ai/computer-use-agents/observe-and-steer.md): Watch a run, intervene while it works, keep the conversation going, and read how it ended. - [Plans and limits](https://hub.hcompany.ai/computer-use-agents/plans-and-limits.md): Plans, token and concurrency allowances, and how to manage your subscription. - [Quickstart](https://hub.hcompany.ai/computer-use-agents/quickstart.md): Create your first agent session in under 5 minutes. - [Create a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/create.md): Register a cron schedule that starts a session on each fire. - [Delete a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/delete.md): Remove a schedule and stop future fires. - [List schedules](https://hub.hcompany.ai/computer-use-agents/schedules/list.md): Browse your organization's schedules. - [Run sessions on a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/overview.md): Run a session on a recurring cron cadence. - [Pause a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/pause.md): Stop future fires without deleting the schedule. - [Resume a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/resume.md): Restart a paused schedule. - [Retrieve a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/retrieve.md): Fetch a schedule by id. - [List schedule runs](https://hub.hcompany.ai/computer-use-agents/schedules/runs.md): Browse a schedule's fire history. - [Trigger a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/trigger.md): Fire a schedule once, immediately. - [Update a schedule](https://hub.hcompany.ai/computer-use-agents/schedules/update.md): Change a schedule's name, timing, or session template. - [Build with the SDKs](https://hub.hcompany.ai/computer-use-agents/sdks.md): Typed Python and TypeScript clients, plus the CLI. - [Cancel a session](https://hub.hcompany.ai/computer-use-agents/sessions/cancel.md): Stop a running session. - [Get session changes](https://hub.hcompany.ai/computer-use-agents/sessions/changes.md): Long-poll for real-time session updates. - [Create a session](https://hub.hcompany.ai/computer-use-agents/sessions/create.md): Launch a new agent run. - [List events](https://hub.hcompany.ai/computer-use-agents/sessions/events.md): Paginated list of session events. - [Session feedback](https://hub.hcompany.ai/computer-use-agents/sessions/feedback.md): Submit feedback on a session or individual event. - [Force an answer](https://hub.hcompany.ai/computer-use-agents/sessions/force-answer.md): Ask the agent to emit a final answer on its next step. - [List sessions](https://hub.hcompany.ai/computer-use-agents/sessions/list.md): Browse your sessions with filtering, sorting, and pagination. - [Sessions](https://hub.hcompany.ai/computer-use-agents/sessions/overview.md): A session represents a single execution of an agent. - [Pause a session](https://hub.hcompany.ai/computer-use-agents/sessions/pause.md): Halt a running session without losing state. - [Get quota](https://hub.hcompany.ai/computer-use-agents/sessions/quota.md): Check your concurrent session quota. - [Get resource](https://hub.hcompany.ai/computer-use-agents/sessions/resources.md): Access session-owned resources like screenshots and files. - [Resume a session](https://hub.hcompany.ai/computer-use-agents/sessions/resume.md): Continue a paused session. - [Retrieve a session](https://hub.hcompany.ai/computer-use-agents/sessions/retrieve.md): Get full details of a single session. - [Send messages](https://hub.hcompany.ai/computer-use-agents/sessions/send-messages.md): Chat with a running agent. - [Share a session](https://hub.hcompany.ai/computer-use-agents/sessions/share.md): Make a session publicly accessible or revoke access. - [Get session status](https://hub.hcompany.ai/computer-use-agents/sessions/status.md): Lightweight polling endpoint for session progress. - [Send tool results](https://hub.hcompany.ai/computer-use-agents/sessions/tool-results.md): Answer the agent's pending custom tool calls. - [Create a skill](https://hub.hcompany.ai/computer-use-agents/skills/create.md): Create a reusable skill in your catalog. - [Delete a skill](https://hub.hcompany.ai/computer-use-agents/skills/delete.md): Remove a skill from the catalog. - [List skills](https://hub.hcompany.ai/computer-use-agents/skills/list.md): Browse your skill catalog. - [Skills](https://hub.hcompany.ai/computer-use-agents/skills/overview.md): A skill is a reusable instruction fragment an agent can draw on. - [Patch a skill](https://hub.hcompany.ai/computer-use-agents/skills/patch.md): Change individual fields of a skill without resending the full object. - [Retrieve a skill](https://hub.hcompany.ai/computer-use-agents/skills/retrieve.md): Get the full details of a skill. - [Update a skill](https://hub.hcompany.ai/computer-use-agents/skills/update.md): Edit a skill's content. - [Get typed answers](https://hub.hcompany.ai/computer-use-agents/structured-output.md): Get the agent's final answer as typed, schema-validated data instead of free-form text. - [Create a vault](https://hub.hcompany.ai/computer-use-agents/vaults/create.md): Register a secrets provider for your organization. - [Delete a vault](https://hub.hcompany.ai/computer-use-agents/vaults/delete.md): Remove a vault config. - [Check health](https://hub.hcompany.ai/computer-use-agents/vaults/health.md): Probe a vault's provider connection. - [List vaults](https://hub.hcompany.ai/computer-use-agents/vaults/list.md): Browse your organization's vault configs. - [Vaults](https://hub.hcompany.ai/computer-use-agents/vaults/overview.md): Let an agent sign in to the sites and services it works on, without passing secrets through the API. - [Retrieve a vault](https://hub.hcompany.ai/computer-use-agents/vaults/retrieve.md): Fetch a vault config by id. - [Rotate the token](https://hub.hcompany.ai/computer-use-agents/vaults/rotate-token.md): Replace a vault's stored service account token. - [Update a vault](https://hub.hcompany.ai/computer-use-agents/vaults/update.md): Change a vault config's name or provider settings. - [Create a webhook](https://hub.hcompany.ai/computer-use-agents/webhooks/create.md): Register a URL to receive signed event notifications. - [Delete a webhook](https://hub.hcompany.ai/computer-use-agents/webhooks/delete.md): Remove a webhook. - [List event types](https://hub.hcompany.ai/computer-use-agents/webhooks/events.md): List the webhook event types you can subscribe to. - [List webhooks](https://hub.hcompany.ai/computer-use-agents/webhooks/list.md): Browse your organization's webhooks. - [Get notified with webhooks](https://hub.hcompany.ai/computer-use-agents/webhooks/overview.md): Receive signed HTTP notifications when your sessions change status. - [Ping a webhook](https://hub.hcompany.ai/computer-use-agents/webhooks/ping.md): Send a signed test event and see how your endpoint responds. - [Retrieve a webhook](https://hub.hcompany.ai/computer-use-agents/webhooks/retrieve.md): Fetch a single webhook by id. - [Rotate a webhook secret](https://hub.hcompany.ai/computer-use-agents/webhooks/rotate.md): Replace the signing secret without missing a verification. - [Update a webhook](https://hub.hcompany.ai/computer-use-agents/webhooks/update.md): Change a webhook's URL, events, description, or disabled state. - [Document OCR](https://hub.hcompany.ai/document-ocr.md) - [Element localization](https://hub.hcompany.ai/element-localization.md) - [Glossary](https://hub.hcompany.ai/glossary.md) - [Architecture](https://hub.hcompany.ai/holo-desktop-cli/architecture.md): Understand how the HoloDesktop CLI client, runtime, model backend, and host integrations fit together. - [Find and fix a UI bug with Claude Code](https://hub.hcompany.ai/holo-desktop-cli/examples/claude-code-ui-qa.md): Use HoloDesktop CLI through MCP from Claude Code to test a running app, fix the source, and verify the UI. - [Automate an expense report from the CLI](https://hub.hcompany.ai/holo-desktop-cli/examples/expense-report-automation.md): Run HoloDesktop CLI directly from the command line to read receipts, update a spreadsheet, draft an email, and verify the result. - [Examples](https://hub.hcompany.ai/holo-desktop-cli/examples/index.md): Learn HoloDesktop CLI through complete workflows. - [Hosted or local models](https://hub.hcompany.ai/holo-desktop-cli/getting-started/hosted-or-local-models.md): Choose how HoloDesktop CLI calls a model backend for desktop tasks. - [Quickstart](https://hub.hcompany.ai/holo-desktop-cli/getting-started/quickstart.md): Install HoloDesktop CLI, connect a model, and run your first desktop task in minutes. - [Customize with skills, memories, and rules](https://hub.hcompany.ai/holo-desktop-cli/how-to/customize.md): Shape how HoloDesktop CLI behaves across every run with optional files in ~/.holo. - [Debug a failed run](https://hub.hcompany.ai/holo-desktop-cli/how-to/debug-failed-run.md): Use doctor, logs, permissions, and model checks to debug a HoloDesktop CLI run. - [Embed with Python](https://hub.hcompany.ai/holo-desktop-cli/how-to/embed-with-python.md): Use HoloDesktop CLI's Python agent client to run desktop sessions from your own code. - [Run a local model server](https://hub.hcompany.ai/holo-desktop-cli/how-to/run-a-local-model-server.md): Serve an H Company open-weight model locally with llama.cpp or vLLM, then connect HoloDesktop CLI. - [HoloDesktop CLI](https://hub.hcompany.ai/holo-desktop-cli/index.md): Use HoloDesktop CLI from your terminal, agent host, or Python code to delegate desktop work. - [Use HoloDesktop CLI as an ACP sub-agent](https://hub.hcompany.ai/holo-desktop-cli/integrations/use-acp.md): Delegate desktop tasks to HoloDesktop CLI from an Agent Client Protocol host over stdio. - [Use HoloDesktop CLI as a skill](https://hub.hcompany.ai/holo-desktop-cli/integrations/use-as-skill.md): Understand the HoloDesktop CLI skill that gets installed into supported agent hosts. - [Use HoloDesktop CLI from the terminal](https://hub.hcompany.ai/holo-desktop-cli/integrations/use-from-cli.md): Run desktop tasks directly from your terminal with holo run. - [Use HoloDesktop CLI as an MCP server](https://hub.hcompany.ai/holo-desktop-cli/integrations/use-mcp.md): Expose HoloDesktop CLI to MCP-capable hosts such as Claude Code, Cursor, Codex, Grok Build, and OpenCode. - [CLI reference](https://hub.hcompany.ai/holo-desktop-cli/reference/cli.md): Common HoloDesktop CLI commands and options. - [Environment variables](https://hub.hcompany.ai/holo-desktop-cli/reference/environment-variables.md): Environment variables used by HoloDesktop CLI and hai-agent-runtime. - [Paths and files](https://hub.hcompany.ai/holo-desktop-cli/reference/paths-and-files.md): Local files, logs, runtime cache, skills, and run artifacts used by HoloDesktop CLI. - [Security and privacy](https://hub.hcompany.ai/holo-desktop-cli/security-and-privacy.md): Understand what HoloDesktop CLI sends to H Company, what stays local, and how hosted and local model modes differ. - [H Tech Hub](https://hub.hcompany.ai/index.md) - [Models](https://hub.hcompany.ai/models.md): The Holo models served by the Models API: capabilities, pricing, and lifecycle. - [Create chat completion](https://hub.hcompany.ai/models-api/chat-completions.md): OpenAI-compatible chat completion with Holo-specific structured outputs and reasoning. - [List models](https://hub.hcompany.ai/models-api/list-models.md): Programmatic discovery of the served models, their capabilities, pricing, and deprecation dates. - [Quickstart](https://hub.hcompany.ai/quickstart.md)