### Clone and setup HoloDesktop CLI from source

Source: https://hub.hcompany.ai/holo-desktop-cli/getting-started/quickstart

Commands to clone the repository, install dependencies, and verify the installation using uv.

```bash
git clone https://github.com/hcompai/holo-desktop-cli
cd holo-desktop-cli
make setup
uv run holo --help
```

--------------------------------

### Verify HoloDesktop CLI installation

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-as-skill

Example task string to verify that the host correctly identifies and utilizes the installed skill.

```text
Use HoloDesktop CLI to open TextEdit and write a short note saying the HoloDesktop CLI skill is installed.
```

--------------------------------

### Start a session response

Source: https://hub.hcompany.ai/computer-use-agents/n8n

Example response received after successfully creating a session, containing the session ID.

```json
{
  "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "status": {"status": "pending", "steps": 0},
  "agent_view_url": "https://platform.hcompany.ai/agents/sessions/a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "latest_answer": null
}
```

--------------------------------

### Install the client

Source: https://hub.hcompany.ai/computer-use-agents/quickstart

Install the necessary client library or CLI tool for your preferred environment.

```bash
pip install "hai-agents[cli]"
```

```bash
# no install needed, the API is plain HTTP
```

```bash
pip install hai-agents
```

```bash
npm install hai-agents
```

--------------------------------

### Install OpenAI Client

Source: https://hub.hcompany.ai/quickstart

Install the official OpenAI client library for your preferred language.

```bash
pip install openai
```

```bash
npm install openai
```

--------------------------------

### Task Prompt Examples

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-from-cli

Examples of well-defined versus vague task strings for the agent.

```bash
holo run "Open Calendar, show today's events, and report each event with its time and title. Do not create or edit anything."
```

```bash
holo run "What's on today?"
```

--------------------------------

### Example skill path

Source: https://hub.hcompany.ai/holo-desktop-cli/reference/paths-and-files

Path for the expense-report example skill.

```text
~/.holo/skills/expense-report/SKILL.md
```

--------------------------------

### Initiate browser profile upload examples

Source: https://hub.hcompany.ai/computer-use-agents/browser-profiles/initiate-upload

Examples for initiating a profile upload using cURL, Python, and TypeScript.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/browser-profiles/initiate-upload \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

upload = client.browser_profiles.initiate_browser_profile_upload()
print(upload.profile_id, upload.upload_url)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const upload = await client.browserProfiles.initiateBrowserProfileUpload();
console.log(upload.profileId, upload.uploadUrl);
```

--------------------------------

### Install the desktop driver

Source: https://hub.hcompany.ai/computer-use-agents/desktop/local-control

Install the required desktop driver package via pip.

```bash
pip install "hai-agents[desktop]"
```

--------------------------------

### Install HoloDesktop CLI

Source: https://hub.hcompany.ai/holo-desktop-cli/getting-started/quickstart

Use these commands to install the CLI on your respective operating system.

```bash
curl -fsSL https://install.hcompany.ai/install.sh | bash
```

```powershell
irm https://install.hcompany.ai/install.ps1 | iex
```

--------------------------------

### Verify CLI Installation

Source: https://hub.hcompany.ai/holo-desktop-cli/getting-started/quickstart

Check that the CLI is correctly installed and available in your PATH.

```bash
holo --help
```

--------------------------------

### Create an environment

Source: https://hub.hcompany.ai/computer-use-agents/environments/create

Examples for initializing a new environment using different interfaces.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/environments \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "id": "wide-browser",
    "kind": "web",
    "start_url": "https://www.google.com",
    "mode": {"type": "visual", "width": 1920, "height": 1080}
  }'
```

```python
from hai_agents import Client

client = Client()

environment = client.environments.create_environment(
    id="wide-browser",
    start_url="https://www.google.com",
    mode={"type": "visual", "width": 1920, "height": 1080},
)
print(environment.id)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const environment = await client.environments.createEnvironment({
  kind: "web",
  id: "wide-browser",
  startUrl: "https://www.google.com",
  mode: { type: "visual", width: 1920, height: 1080 },
});
console.log(environment.id);
```

--------------------------------

### Complete browser profile upload examples

Source: https://hub.hcompany.ai/computer-use-agents/browser-profiles/complete-upload

Examples showing how to finalize a profile upload using cURL, Python, and TypeScript.

```bash
curl -X POST "https://agp.eu.hcompany.ai/api/v2/browser-profiles/a1b2c3d4-5678-90ab-cdef-1234567890ab/complete-upload" \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "acme-prod-login",
    "browser_name": "chromium",
    "browser_version": "131",
    "labels": {"team": "qa"}
  }'
```

```python
from hai_agents import Client

client = Client()

profile = client.browser_profiles.complete_browser_profile_upload(
    profile_id="a1b2c3d4-5678-90ab-cdef-1234567890ab",
    name="acme-prod-login",
    browser_name="chromium",
    browser_version="131",
    labels={"team": "qa"},
)
print(profile.id)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const profile = await client.browserProfiles.completeBrowserProfileUpload({
  profileId: "a1b2c3d4-5678-90ab-cdef-1234567890ab",
  name: "acme-prod-login",
  browserName: "chromium",
  browserVersion: "131",
  labels: { team: "qa" },
});
console.log(profile.id);
```

--------------------------------

### List Vaults API Examples

Source: https://hub.hcompany.ai/computer-use-agents/vaults/list

Examples for retrieving vault configurations using cURL, Python, and TypeScript.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/vaults?limit=50&offset=0" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.vaults.list_vaults(limit=50, offset=0)
for vault in page.vaults:
    print(vault.id, vault.name)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.vaults.listVaults({ limit: 50, offset: 0 });
for (const vault of page.vaults) {
  console.log(vault.id, vault.name);
}
```

--------------------------------

### Install the browser driver

Source: https://hub.hcompany.ai/computer-use-agents/browser/local-control

Install the necessary package to enable browser control capabilities.

```bash
pip install "hai-agents[browser]"
```

--------------------------------

### Update a skill examples

Source: https://hub.hcompany.ai/computer-use-agents/skills/update

Examples showing how to update a skill using cURL, Python, and TypeScript.

```bash
curl -X PUT https://agp.eu.hcompany.ai/api/v2/skills/extract-table-data \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "extract-table-data",
    "description": "Extract data from HTML tables: updated with CSV output support.",
    "body": "When you encounter an HTML table, extract all rows into JSON or CSV format based on the user request."
  }'
```

```python
from hai_agents import Client

client = Client()

skill = client.skills.update_skill(
    name_="extract-table-data",
    name="extract-table-data",
    description="Extract data from HTML tables: updated with CSV output support.",
    body="When you encounter an HTML table, extract all rows into JSON or CSV format based on the user request.",
)
print(skill.description)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const skill = await client.skills.updateSkill({
  name: "extract-table-data",
  body: {
    name: "extract-table-data",
    description: "Extract data from HTML tables: updated with CSV output support.",
    body: "When you encounter an HTML table, extract all rows into JSON or CSV format based on the user request.",
  },
});
console.log(skill.description);
```

--------------------------------

### Start Nimbus Development Environment

Source: https://hub.hcompany.ai/holo-desktop-cli/examples/claude-code-ui-qa

Commands to initialize the environment and start the development server for the Nimbus application.

```bash
uv sync
cd examples/software_qa/nimbus-desk
npm install
npm run dev
```

--------------------------------

### Install llama.cpp on macOS

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/run-a-local-model-server

Use Homebrew to install the llama.cpp server package.

```bash
brew install llama.cpp
```

--------------------------------

### List browser profiles API examples

Source: https://hub.hcompany.ai/computer-use-agents/browser-profiles/list

Examples for retrieving browser profiles using cURL, Python, and TypeScript SDKs.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/browser-profiles?limit=10&offset=0" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.browser_profiles.list_browser_profiles(limit=10, offset=0)
for profile in page.profiles:
    print(profile.id, profile.name)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.browserProfiles.listBrowserProfiles({ limit: 10, offset: 0 });
for (const profile of page.profiles) {
  console.log(profile.id, profile.name);
}
```

--------------------------------

### List schedules API examples

Source: https://hub.hcompany.ai/computer-use-agents/schedules/list

Examples for retrieving a list of schedules using different programming languages.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/schedules" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.schedules.list_schedules()
for schedule in page.items:
    print(schedule.id, schedule.name, schedule.paused)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.schedules.listSchedules();
for (const schedule of page.items) {
  console.log(schedule.id, schedule.name, schedule.paused);
}
```

--------------------------------

### Retrieve an environment

Source: https://hub.hcompany.ai/computer-use-agents/environments/retrieve

Examples for fetching environment details using different client implementations.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/environments/h/browser" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

environment = client.environments.get_environment("h/browser")
print(environment)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const environment = await client.environments.getEnvironment({ id: "h/browser" });
console.log(environment);
```

--------------------------------

### Skill installation directory

Source: https://hub.hcompany.ai/holo-desktop-cli/examples/expense-report-automation

The destination path where the bundled expense report skill is installed.

```text
~/.holo/skills/expense-report/
```

--------------------------------

### Install workspace dependencies

Source: https://hub.hcompany.ai/holo-desktop-cli/examples/expense-report-automation

Run this command from the holo-desktop-cli directory to install all required workspace groups.

```bash
uv sync --all-groups
```

--------------------------------

### Install hai-agents SDKs

Source: https://hub.hcompany.ai/computer-use-agents/sdks

Commands to install the required packages for CLI, Python, or TypeScript environments.

```bash
pip install "hai-agents[cli]"
```

```bash
pip install hai-agents
```

```bash
npm install hai-agents
```

--------------------------------

### Set default browser profile examples

Source: https://hub.hcompany.ai/computer-use-agents/browser-profiles/set-default

Examples showing how to set a browser profile as default using cURL, Python, and TypeScript.

```bash
curl -X PUT "https://agp.eu.hcompany.ai/api/v2/browser-profiles/a1b2c3d4-5678-90ab-cdef-1234567890ab/default" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

profile = client.browser_profiles.set_default_browser_profile(
    profile_id="a1b2c3d4-5678-90ab-cdef-1234567890ab",
)
print(profile.is_default)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const profile = await client.browserProfiles.setDefaultBrowserProfile({
  profileId: "a1b2c3d4-5678-90ab-cdef-1234567890ab",
});
console.log(profile.isDefault);
```

--------------------------------

### Install HoloDesktop CLI into hosts

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-mcp

Commands to install the MCP server into specific hosts or all detected hosts.

```bash
cd /path/to/your/claude-code-workspace
holo install claude-code
```

```bash
holo install cursor
```

```bash
holo install
```

--------------------------------

### Install HoloDesktop CLI skill

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-as-skill

Commands to install the skill into a specific workspace or all detected supported hosts.

```bash
cd /path/to/your/claude-code-workspace
holo install claude-code
```

```bash
holo install
```

--------------------------------

### Trigger a schedule API examples

Source: https://hub.hcompany.ai/computer-use-agents/schedules/trigger

Examples for triggering a schedule using cURL, Python, and TypeScript clients.

```bash
curl -X POST "https://agp.eu.hcompany.ai/api/v2/schedules/9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f/trigger" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

run = client.schedules.trigger_schedule("9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f")
print(run.status, run.session_id)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const run = await client.schedules.triggerSchedule({ scheduleId: "9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f" });
console.log(run.status, run.sessionId);
```

--------------------------------

### Install Agent Skills in Claude Code

Source: https://hub.hcompany.ai/computer-use-agents/coding-skills

Register the marketplace and install the skill using the built-in /plugin command.

```bash
/plugin marketplace add hcompai/computer-use-agents-demos
/plugin install hai-agents@hai-skills
```

--------------------------------

### Verify HoloDesktop CLI installation

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-mcp

Use these commands to list installed hosts and re-register a specific host ID if the CLI is not detected.

```bash
holo install list
```

```bash
holo install <host-id>
```

--------------------------------

### List schedule runs API examples

Source: https://hub.hcompany.ai/computer-use-agents/schedules/runs

Examples for fetching schedule run history using cURL, Python, and TypeScript clients.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/schedules/9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f/runs" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.schedules.list_schedule_runs("9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f")
for run in page.items:
    print(run.scheduled_for, run.status, run.session_id)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.schedules.listScheduleRuns({ scheduleId: "9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f" });
for (const run of page.items) {
  console.log(run.scheduledFor, run.status, run.sessionId);
}
```

--------------------------------

### Example Task Definitions

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-mcp

Comparison of well-defined and vague task prompts for the MCP tool.

```text
Open Slack in the Acme workspace and send a DM to Sarah Chen saying "on my way". Return "sent" after the message appears.
```

```text
Tell Sarah.
```

--------------------------------

### Create a vault request examples

Source: https://hub.hcompany.ai/computer-use-agents/vaults/create

Examples for creating a vault using cURL, Python, and TypeScript. Ensure the service account token is sent over HTTPS.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/vaults \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "prod-1password",
    "provider_config": {"provider": "onepassword", "op_vault_id": "abcd1234efgh5678"},
    "token": "ops_eyJ..."
  }'
```

```python
from hai_agents import Client, OnePasswordConfig

client = Client()

vault = client.vaults.create_vault(
    name="prod-1password",
    provider_config=OnePasswordConfig(op_vault_id="abcd1234efgh5678"),
    token="ops_eyJ...",
)
print(vault.id)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const vault = await client.vaults.createVault({
  name: "prod-1password",
  providerConfig: { opVaultId: "abcd1234efgh5678" },
  token: "ops_eyJ...",
});
console.log(vault.id);
```

--------------------------------

### List webhooks examples

Source: https://hub.hcompany.ai/computer-use-agents/webhooks/list

Retrieve a list of webhooks using cURL, Python, or TypeScript.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/webhooks" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.webhooks.list_webhooks()
for webhook in page.items:
    print(webhook.id, webhook.url)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.webhooks.listWebhooks();
for (const webhook of page.items) {
  console.log(webhook.id, webhook.url);
}
```

--------------------------------

### Create a schedule

Source: https://hub.hcompany.ai/computer-use-agents/schedules/create

Examples for creating a new schedule using cURL, Python, and TypeScript.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/schedules \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "morning-market-scan",
    "description": "Weekday scan of new Paris listings",
    "timing": {"expression": "0 9 * * 1-5", "timezone": "Europe/Paris"},
    "session_request": {
      "agent": "h/web-surfer-flash",
      "messages": [
        {"type": "user_message", "message": "Scan new apartment listings in Paris 11e and summarize the top five"}
      ]
    }
  }'
```

```python
from hai_agents import Client

client = Client()

schedule = client.schedules.create_schedule(
    name="morning-market-scan",
    description="Weekday scan of new Paris listings",
    timing={"expression": "0 9 * * 1-5", "timezone": "Europe/Paris"},
    session_request={
        "agent": "h/web-surfer-flash",
        "messages": [
            {"type": "user_message", "message": "Scan new apartment listings in Paris 11e and summarize the top five"}
        ],
    },
)
print(schedule.id, schedule.next_run_times[0])
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const schedule = await client.schedules.createSchedule({
  name: "morning-market-scan",
  description: "Weekday scan of new Paris listings",
  timing: { expression: "0 9 * * 1-5", timezone: "Europe/Paris" },
  sessionRequest: {
    agent: "h/web-surfer-flash",
    messages: [
      { type: "user_message", message: "Scan new apartment listings in Paris 11e and summarize the top five" },
    ],
  },
});
console.log(schedule.id, schedule.nextRunTimes[0]);
```

--------------------------------

### Install Agent Skills in Hermes

Source: https://hub.hcompany.ai/computer-use-agents/coding-skills

Clone the repository and copy the skill folder into the ~/.hermes/skills directory.

```bash
git clone https://github.com/hcompai/computer-use-agents-demos
mkdir -p ~/.hermes/skills
cp -r computer-use-agents-demos/skills/hai-agents ~/.hermes/skills/hai-agents
```

--------------------------------

### Override agent configuration for a single session

Source: https://hub.hcompany.ai/computer-use-agents/sessions/overview

Examples of applying overrides to a web-surfer agent to change its start URL using various interfaces.

```bash
hai run "Summarize the top discussion right now" \
  --agent h/web-surfer-flash \
  --override 'agent.environments[kind=web].start_url=https://news.ycombinator.com'
```

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/sessions \
  -H "Authorization: Bearer $HAI_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "agent": "h/web-surfer-flash",
    "messages": [{"type": "user_message", "message": "Summarize the top discussion right now"}],
    "overrides": {"agent.environments[kind=web].start_url": "https://news.ycombinator.com"}
  }'
```

```python
session = client.sessions.create_session(
    agent="h/web-surfer-flash",
    messages="Summarize the top discussion right now",
    overrides={"agent.environments[kind=web].start_url": "https://news.ycombinator.com"},
)
```

```typescript
const session = await client.sessions.createSession({
  body: {
    agent: "h/web-surfer-flash",
    messages: "Summarize the top discussion right now",
    overrides: { "agent.environments[kind=web].start_url": "https://news.ycombinator.com" },
  },
});
```

--------------------------------

### GET /api/v2/sessions/quota

Source: https://hub.hcompany.ai/computer-use-agents/sessions/overview

Get the current session quota.

```APIDOC
## GET /api/v2/sessions/quota

### Description
Get the current quota.

### Method
GET

### Endpoint
/api/v2/sessions/quota
```

--------------------------------

### Launch a fresh Chrome instance

Source: https://hub.hcompany.ai/computer-use-agents/browser/profiles

Start a new Chrome instance with a dedicated user-data directory to create a clean profile.

```bash
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
  --user-data-dir="$HOME/agent-profile"
```

```bash
google-chrome --user-data-dir="$HOME/agent-profile"
```

--------------------------------

### Run MCP server

Source: https://hub.hcompany.ai/holo-desktop-cli/reference/cli

Starts the stdio MCP server, typically invoked by an MCP host.

```bash
holo mcp
```

--------------------------------

### List environments using various clients

Source: https://hub.hcompany.ai/computer-use-agents/environments/list

Examples of how to fetch the list of environments using cURL, Python, and TypeScript.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/environments" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.environments.list_environments()
print(page.items)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.environments.listEnvironments();
console.log(page.items);
```

--------------------------------

### List Skills API Requests

Source: https://hub.hcompany.ai/computer-use-agents/skills/list

Examples of how to retrieve the skill catalog using different programming interfaces.

```bash
curl "https://agp.eu.hcompany.ai/api/v2/skills" \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

page = client.skills.list_skills()
for skill in page.items:
    print(skill.name)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const page = await client.skills.listSkills();
for (const skill of page.items) {
  console.log(skill.name);
}
```

--------------------------------

### GET /api/v2/sessions/{id}/resources/{bucket}/{key}

Source: https://hub.hcompany.ai/computer-use-agents/sessions/overview

Get a resource from a specific session.

```APIDOC
## GET /api/v2/sessions/{id}/resources/{bucket}/{key}

### Description
Get a session resource.

### Method
GET

### Endpoint
/api/v2/sessions/{id}/resources/{bucket}/{key}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the session.
- **bucket** (string) - Required - The bucket name.
- **key** (string) - Required - The resource key.
```

--------------------------------

### MCP server configuration examples

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-mcp

JSON configuration structures for file-backed hosts and hosts requiring environment variables.

```json
{
  "mcpServers": {
    "holo": {
      "type": "stdio",
      "command": "/absolute/path/to/holo",
      "args": ["mcp"]
    }
  }
}
```

```json
{
  "mcpServers": {
    "holo": {
      "type": "stdio",
      "command": "/absolute/path/to/holo",
      "args": ["mcp"],
      "env": {
        "HAI_AGENT_RUNTIME_BASE_URL": "http://localhost:8000/v1",
        "HAI_AGENT_RUNTIME_MODEL": "Hcompany/Holo-3.1-35B-A3B"
      }
    }
  }
}
```

--------------------------------

### Run a basic desktop session script

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/embed-with-python

Initializes the agent runtime and executes a task using the Python client.

```python
import asyncio

from holo_desktop.agent_client import AgentApiClient, SpawnConfig, ensure_running
from holo_desktop.agent_client.requests import build_session_request


async def main() -> None:
    daemon = await ensure_running(SpawnConfig(port=18795))
    try:
        async with AgentApiClient(daemon.base_url, daemon.token) as client:
            request = build_session_request(
                task="Open TextEdit and write a short note saying HoloDesktop CLI is embedded",
                max_steps=10,
                max_time_s=120,
            )
            session_id = await client.create_session(request)
            stream = client.stream(session_id)

            async for event in stream.events():
                print(event.type)

            print(stream.answer)
    finally:
        await daemon.aclose()


asyncio.run(main())
```

```bash
python your_script.py
```

--------------------------------

### Monitor session progress and completion

Source: https://hub.hcompany.ai/computer-use-agents/observe-and-steer

Demonstrates how to start a session and use status, changes, and completion methods to track agent activity.

```python
from hai_agents import Client

client = Client()

session = client.start_session(
    agent="h/web-surfer-flash",
    messages=[{"type": "user_message", "message": "Find the top story on Hacker News"}],
)

session.status()               # cheap liveness snapshot
session.changes(from_index=0)  # new events + final answer, long-polled
session.get()                  # the full Session resource

result = session.wait_for_completion()  # block until terminal, then read the answer
print(result.status, result.answer)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const session = await client.startSession({
  agent: "h/web-surfer-flash",
  messages: [{ type: "user_message", message: "Find the top story on Hacker News" }],
});

await session.status();                  // cheap liveness snapshot
await session.changes({ fromIndex: 0 }); // new events + final answer, long-polled
await session.get();                     // the full Session resource

const result = await session.waitForCompletion(); // block until terminal, then read the answer
console.log(result.status, result.answer);
```

--------------------------------

### Connect HoloDesktop CLI to local server

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/run-a-local-model-server

Point the CLI to the local model server URL.

```bash
holo run "Open TextEdit and write a short note saying HoloDesktop CLI is installed" \
  --base-url http://localhost:8080/v1 \
  --model holo3-1-35b
```

```bash
holo run "Open TextEdit and write a short note saying HoloDesktop CLI is installed" \
  --base-url http://localhost:8000/v1 \
  --model holo3-1-35b
```

--------------------------------

### Configure MCP server environment

Source: https://hub.hcompany.ai/holo-desktop-cli/reference/environment-variables

Example configuration for integrating HoloDesktop CLI as an MCP server with custom runtime variables.

```json
{
  "mcpServers": {
    "holo": {
      "command": "holo",
      "args": ["mcp"],
      "env": {
        "HAI_AGENT_RUNTIME_BASE_URL": "http://localhost:8000/v1",
        "HAI_AGENT_RUNTIME_MODEL": "Hcompany/Holo-3.1-35B-A3B"
      }
    }
  }
}
```

--------------------------------

### Create a skill using various clients

Source: https://hub.hcompany.ai/computer-use-agents/skills/create

Examples of how to create a new skill using cURL, the Python SDK, or the TypeScript SDK.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/skills \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "extract-table-data",
    "description": "Extract structured data from HTML tables into JSON.",
    "body": "When you encounter an HTML table, extract all rows and columns into a JSON array of objects. Each object should use the table headers as keys.",
    "source": "https://github.com/myorg/skills"
  }'
```

```python
from hai_agents import Client

client = Client()

skill = client.skills.create_skill(
    name="extract-table-data",
    description="Extract structured data from HTML tables into JSON.",
    body="When you encounter an HTML table, extract all rows and columns into a JSON array of objects. Each object should use the table headers as keys.",
    source="https://github.com/myorg/skills",
)
print(skill.name)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const skill = await client.skills.createSkill({
  name: "extract-table-data",
  description: "Extract structured data from HTML tables into JSON.",
  body: "When you encounter an HTML table, extract all rows and columns into a JSON array of objects. Each object should use the table headers as keys.",
  source: "https://github.com/myorg/skills",
});
console.log(skill.name);
```

--------------------------------

### Configure authentication and local runtime

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/embed-with-python

Authenticate via CLI or configure specific model settings during runtime initialization.

```bash
holo login
```

```python
daemon = await ensure_running(
    SpawnConfig(
        port=18795,
        model="Hcompany/Holo-3.1-35B-A3B",
        base_url="http://localhost:8000/v1",
    )
)
```

--------------------------------

### Install Claude Code integration

Source: https://hub.hcompany.ai/holo-desktop-cli/reference/paths-and-files

Command to install the Claude Code integration within the current workspace.

```bash
holo install claude-code
```

--------------------------------

### Create a local desktop agent

Source: https://hub.hcompany.ai/computer-use-agents/desktop/local-control

Define an agent with the environment kind set to 'desktop' and host set to 'user_device'.

```python
from hai_agents import Client

client = Client()

agent = client.agents.create_agent(
    name="local-desktop",
    description="Drives the desktop on my own machine.",
    environments=[
        {
            "id": "my-laptop",
            "kind": "desktop",
            "host": "user_device",
        }
    ],
)
```

--------------------------------

### Access Log Directories

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/debug-failed-run

Locate startup and per-run event logs for troubleshooting.

```text
~/.holo/logs/
```

```text
~/.holo/runs/
```

--------------------------------

### Install Agent Skills in Cursor

Source: https://hub.hcompany.ai/computer-use-agents/coding-skills

Clone the repository and copy the skill folder into the project's .cursor/skills directory.

```bash
git clone https://github.com/hcompai/computer-use-agents-demos
mkdir -p .cursor/skills
cp -r computer-use-agents-demos/skills/hai-agents .cursor/skills/hai-agents
```

--------------------------------

### Retrieve a session using various clients

Source: https://hub.hcompany.ai/computer-use-agents/sessions/retrieve

Examples for fetching session details using CLI, cURL, Python, and TypeScript.

```bash
hai sessions get a1b2c3d4-e5f6-7890-abcd-ef1234567890
```

```bash
curl https://agp.eu.hcompany.ai/api/v2/sessions/a1b2c3d4-e5f6-7890-abcd-ef1234567890 \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

session = client.sessions.get_session("a1b2c3d4-e5f6-7890-abcd-ef1234567890")
print(session.status.status, session.latest_answer)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const session = await client.sessions.getSession({
  id: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
});
console.log(session.status.status, session.latestAnswer);
```

--------------------------------

### Make First API Request

Source: https://hub.hcompany.ai/quickstart

Initialize the client with the custom base URL and send a text completion request.

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.hcompany.ai/v1/",
    api_key=os.environ.get("HAI_API_KEY"),
)

response = client.chat.completions.create(
    model="holo3-1-35b-a3b",
    messages=[{"role": "user", "content": "In one sentence, what is a computer-use agent?"}],
)

print(response.choices[0].message.content)
```

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.hcompany.ai/v1/",
  apiKey: process.env.HAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "holo3-1-35b-a3b",
  messages: [{ role: "user", content: "In one sentence, what is a computer-use agent?" }],
});

console.log(response.choices[0].message.content);
```

```bash
curl https://api.hcompany.ai/v1/chat/completions \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "holo3-1-35b-a3b",
    "messages": [{"role": "user", "content": "In one sentence, what is a computer-use agent?"}]
  }'
```

--------------------------------

### Rotate webhook secret examples

Source: https://hub.hcompany.ai/computer-use-agents/webhooks/rotate

Examples for rotating a webhook secret using cURL, Python, and TypeScript. Ensure the new secret is stored securely upon receipt.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/webhooks/f47ac10b-58cc-4372-a567-0e02b2c3d479/rotate \
  -H "Authorization: Bearer $HAI_API_KEY"
```

```python
from hai_agents import Client

client = Client()

webhook = client.webhooks.rotate_webhook_secret(webhook_id="f47ac10b-58cc-4372-a567-0e02b2c3d479")
print(webhook.secret)  # store it now; it is never returned again
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const webhook = await client.webhooks.rotateWebhookSecret({ webhookId: "f47ac10b-58cc-4372-a567-0e02b2c3d479" });
console.log(webhook.secret); // store it now; it is never returned again
```

--------------------------------

### Create a custom environment

Source: https://hub.hcompany.ai/computer-use-agents/environments/overview

Create a reusable environment in the catalog by specifying an ID, kind, and display mode.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/environments \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "id": "wide-browser",
    "kind": "web",
    "mode": {"type": "visual", "width": 1920, "height": 1080}
  }'
```

```python
from hai_agents import Client

client = Client()

client.environments.create_environment(
    id="wide-browser",
    kind="web",
    mode={"type": "visual", "width": 1920, "height": 1080},
)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

await client.environments.createEnvironment({
  id: "wide-browser",
  kind: "web",
  mode: { type: "visual", width: 1920, height: 1080 },
});
```

--------------------------------

### Rotate Vault Token Examples

Source: https://hub.hcompany.ai/computer-use-agents/vaults/rotate-token

Examples for updating a vault's service account token using cURL, Python, and TypeScript. Ensure the request is sent over HTTPS as the token is transmitted in plaintext.

```bash
curl -X PUT https://agp.eu.hcompany.ai/api/v2/vaults/f47ac10b-58cc-4372-a567-0e02b2c3d479/token \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"token": "ops_newtoken..."}'
```

```python
from hai_agents import Client

client = Client()

client.vaults.rotate_vault_token(
    vault_id="f47ac10b-58cc-4372-a567-0e02b2c3d479",
    token="ops_newtoken...",
)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

await client.vaults.rotateVaultToken({
  vaultId: "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  token: "ops_newtoken...",
});
```

--------------------------------

### Run the expense report demo

Source: https://hub.hcompany.ai/holo-desktop-cli/examples/expense-report-automation

Executes the expense report automation task using the default configuration.

```bash
uv run holo-demo run expense_report
```

--------------------------------

### GET /api/v2/webhooks

Source: https://hub.hcompany.ai/computer-use-agents/webhooks/list

Retrieves a paginated list of webhooks for the organization.

```APIDOC
## GET /api/v2/webhooks

### Description
Returns a paginated list of your organization's webhooks. Signing secrets are never included.

### Method
GET

### Endpoint
https://agp.eu.hcompany.ai/api/v2/webhooks

### Parameters
#### Query Parameters
- **page** (integer) - Optional - Page number (1-based). Default: 1
- **size** (integer) - Optional - Items per page. Maximum: 1000. Default: 10
- **sort** (string) - Optional - Sort order. Options: `created_at`, `-created_at`. Default: `-created_at`

### Response
#### Success Response (200)
- **items** (array) - List of webhook objects
- **page** (integer) - Current page number
- **total** (integer) - Total number of webhooks

#### Response Example
{
  "items": [
    {
      "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
      "url": "https://example.com/hooks/h",
      "enabled_events": ["session.status_updated"],
      "description": "Production listener",
      "disabled": false,
      "last_delivery_status": "succeeded",
      "last_delivery_error": null,
      "last_delivery_at": "2026-07-03T08:30:00Z",
      "last_success_at": "2026-07-03T08:30:00Z",
      "consecutive_failures": 0,
      "created_at": "2026-06-11T15:04:05Z",
      "updated_at": "2026-06-11T15:04:05Z"
    }
  ],
  "page": 1,
  "total": 1
}
```

--------------------------------

### GET /api/v2/schedules

Source: https://hub.hcompany.ai/computer-use-agents/schedules/list

Retrieves a paginated list of organization schedules.

```APIDOC
## GET /api/v2/schedules

### Description
Returns a paginated list of your organization's schedules.

### Method
GET

### Endpoint
/api/v2/schedules

### Parameters
#### Query Parameters
- **page** (integer) - Optional - Page number (1-based). Default: 1
- **size** (integer) - Optional - Items per page. Maximum: 1000. Default: 10
- **sort** (string) - Optional - Sort order. Options: `created_at`, `-created_at`. Default: `-created_at`

### Response
#### Success Response (200)
- **items** (array) - List of schedule objects
- **page** (integer) - Current page number
- **total** (integer) - Total number of schedules

#### Response Example
{
  "items": [
    {
      "id": "9f8e7d6c-5b4a-4c3d-8e2f-1a0b9c8d7e6f",
      "name": "morning-market-scan",
      "description": "Weekday scan of new Paris listings",
      "timing": {"type": "cron", "expression": "0 9 * * 1-5", "timezone": "Europe/Paris"},
      "session_request": {
        "agent": "h/web-surfer-flash",
        "messages": [
          {"type": "user_message", "message": "Scan new apartment listings in Paris 11e and summarize the top five"}
        ],
        "max_time_s": 3600
      },
      "paused": false,
      "pause_note": null,
      "next_run_times": [
        "2026-07-06T07:00:00Z",
        "2026-07-07T07:00:00Z",
        "2026-07-08T07:00:00Z",
        "2026-07-09T07:00:00Z",
        "2026-07-10T07:00:00Z"
      ],
      "last_run_at": "2026-07-03T07:00:00Z",
      "created_at": "2026-06-20T12:00:00Z",
      "updated_at": "2026-07-03T07:00:00Z"
    }
  ],
  "page": 1,
  "total": 1
}
```

--------------------------------

### Start llama.cpp server

Source: https://hub.hcompany.ai/holo-desktop-cli/how-to/run-a-local-model-server

Launch the llama.cpp server with the specified model. The server defaults to port 8080.

```bash
llama-server -hf Hcompany/Holo-3.1-35B-A3B-GGUF
```

```bash
llama-server \
  --hf Hcompany/Holo-3.1-35B-A3B-GGUF \
  --n-gpu-layers 999 \
  --ctx-size 65536 \
  --batch-size 16384 \
  --ubatch-size 2048 \
  --flash-attn 1 \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  --image-min-tokens 1024 \
  --ctx-checkpoints 8 \
  --cache-ram 32768 \
  --kv-unified \
  --threads 16
```

--------------------------------

### GET /api/v2/sessions/{id}/events

Source: https://hub.hcompany.ai/computer-use-agents/sessions/overview

List events for a specific session.

```APIDOC
## GET /api/v2/sessions/{id}/events

### Description
List events for a session.

### Method
GET

### Endpoint
/api/v2/sessions/{id}/events

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the session.
```

--------------------------------

### Create an Agent

Source: https://hub.hcompany.ai/computer-use-agents/agents/create

Methods to initialize a new agent with a web browser environment.

```bash
curl -X POST https://agp.eu.hcompany.ai/api/v2/agents \
  -H "Authorization: Bearer $HAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-web-agent",
    "description": "Custom web researcher",
    "environments": [
      {
        "id": "browser",
        "kind": "web",
        "mode": {"type": "visual", "width": 1280, "height": 720},
        "start_url": "https://news.ycombinator.com"
      }
    ]
  }'
```

```python
from hai_agents import Client

client = Client()

agent = client.agents.create_agent(
    name="my-web-agent",
    description="Custom web researcher",
    environments=[
        {
            "id": "browser",
            "kind": "web",
            "mode": {"type": "visual", "width": 1280, "height": 720},
            "start_url": "https://news.ycombinator.com",
        }
    ],
)
print(agent.name)
```

```typescript
import { HaiAgentsClient } from "hai-agents";

const client = new HaiAgentsClient();

const agent = await client.agents.createAgent({
  name: "my-web-agent",
  description: "Custom web researcher",
  environments: [
    {
      id: "browser",
      kind: "web",
      mode: { type: "visual", width: 1280, height: 720 },
      startUrl: "https://news.ycombinator.com",
    },
  ],
});
console.log(agent.name);
```

--------------------------------

### Dry-run output example

Source: https://hub.hcompany.ai/holo-desktop-cli/examples/expense-report-automation

Expected output format when running a dry-run command.

```text
[dry-run] expense_report: would launch ['com.apple.finder', 'org.libreoffice.script', 'com.apple.mail']
[dry-run] expense_report: would focus 'org.libreoffice.script'
[dry-run] expense_report: output would go to runs/expense_report
```

--------------------------------

### Start ACP mode

Source: https://hub.hcompany.ai/holo-desktop-cli/integrations/use-acp

Command to initiate the HoloDesktop CLI in ACP mode.

```bash
holo acp
```