/notte

name: notte
description: Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron schedules.
homepage: https://notte.cc
metadata:
  {
    "bitterbot":
      {
        "emoji": "🥷",
        "requires": { "bins": ["notte"] },
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "tap": "nottelabs/notte-cli https://github.com/nottelabs/notte-cli.git",
              "formula": "notte",
              "bins": ["notte"],
              "label": "Install Notte CLI (brew)",
            },
            {
              "id": "go",
              "kind": "go",
              "module": "github.com/nottelabs/notte-cli/cmd/notte@latest",
              "bins": ["notte"],
              "label": "Install Notte CLI (go)",
            },
          ],
      },
  }

Notte

Hosted browser infrastructure with a CLI that does three things the bundled `browser` tool and Firecrawl cannot:

1. **Functions** — deploy a browser automation script as a serverless, API-callable endpoint with built-in cron scheduling. The natural fit for crystallized skills and dream-engine cycles. 2. **Vault-backed login** — passwords auto-fill on matching URLs without ever entering the model's context. 3. **Stealth sessions** — residential proxies + inline captcha solving, for sites where the bundled Chromium gets locked out.

Functions — deploy a browser flow as a callable API

Crystallized skills and dream-cycle automations both want the same thing: a stable, repeatable browser action the agent can call by name on a schedule. Notte Functions is exactly that.

# 1. Capture an agent's run as deterministic Python (or hand-write it).
notte agents workflow-code   # exports the latest agent's steps as Python
notte sessions workflow-code # or export from a CLI session

# 2. Deploy the script as a Function (one-shot — no servers, no infra).
notte functions create --file workflow.py
# → returns function_id

# 3. Run on demand, or schedule.
notte functions run                                # one-off
notte functions schedule-set --cron "0 */2 * * *"  # every 2h, matches dream cycles
notte functions runs                               # invocation history
notte functions fork                               # version forward without losing the original

# 4. Or invoke via HTTP from anywhere (skill scripts, gateway hooks, channels).
curl -X POST https://api.notte.cc/functions/{function_id}/runs/start \
  -H "Authorization: Bearer $NOTTE_API_KEY" \
  -d '{"url":"https://example.com","query":"laptop"}'

**Why this matters for Bitterbot:**

• A crystallized skill that ends in "open this URL and grab the data" can be backed by a Function — fast, deterministic, no LLM tokens per execution.
• Function `schedule-set` aligns directly with dream-engine cron triggers (every 2h consolidation, daily syncs, hourly monitors).
• `notte agents workflow-code` is structurally the same pattern as Bitterbot's dream engine crystallizing execution paths — the agent figures out the steps, then the deterministic Function takes over for production.
• Functions auto-inherit Notte's session capabilities: vault credentials, stealth proxies, captcha solving — without re-deploying anything.

When to use Notte vs the bundled tools

| Need | Use | | ---------------------------------------------------------------------------- | --------------------------------------------------------- | | Open a tab, click around, take a snapshot | **Bundled `browser` tool** (`src/browser/`) | | Pull a single page through a stealth fetch | **Firecrawl via `web_fetch`** (`docs/tools/firecrawl.md`) | | **Crystallize a recurring browser flow into a callable API endpoint** | **`notte functions`** | | **Schedule a browser flow on a cron (dream-cycle aligned)** | **`notte functions schedule-set`** | | Run a multi-step task on an authenticated site | **`notte` session** | | Log in without exposing the password to the LLM | **`notte` vault** | | The bundled browser is being challenged with captcha / Cloudflare / DataDome | **`notte`** (`--solve-captchas`, `--proxy`) | | Need a residential / geo-located IP | **`notte`** | | Hand a browsing goal to an agent and get a structured answer | **`notte agents`** |

`notte` does not replace the bundled browser. It's the deployment + infrastructure layer for browser flows that need to outlive a single agent run.

Setup

# Install (handled by the install metadata above).
brew tap nottelabs/notte-cli https://github.com/nottelabs/notte-cli.git && brew install notte
# or:
go install github.com/nottelabs/notte-cli/cmd/notte@latest

# Authenticate. Stores the API key in the system keyring.
notte auth login
# or: export NOTTE_API_KEY=...

Quick start

notte sessions start --proxy --solve-captchas
notte page goto "https://news.ycombinator.com"
notte page observe
notte page scrape --instructions "Top 10 story titles, points, and URLs as JSON"
notte sessions stop -y

`observe` returns interactive element IDs (`@B3`, `@I1`, `@L9`). Use those with `click` / `fill`, or fall back to Playwright selectors (`#submit`, `button:has-text('Submit')