Agent skill

Notte

by Bitterbot-AI in Bitterbot-AI/bitterbot-desktop

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.

MITAuto-check passedProductivity & Automation

Install Notte

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/notte .claude/skills/notte && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .claude/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/notte .agents/skills/notte && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .agents/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/notte .cursor/skills/notte && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .cursor/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Bitterbot-AI/bitterbot-desktop.git --path skills/notte

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/notte .gemini/skills/notte && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .gemini/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/notte .github/skills/notte && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .github/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Bitterbot-AI/bitterbot-desktop notte --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/notte .opencode/skills/notte && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "notte" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/notte into .opencode/skills/notte/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notte", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: notte
GitHub stars: 2.5k
Token cost: ~2.8k tokens
SKILL.md length: 764 words
Files: 1
Skills in repo: 17
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

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.

Works in 3 steps: Functions — deploy a browser automation… → Vault-backed login — passwords auto-fill… → Stealth sessions — residential proxies +…
Tasks that involve Browser automation
SKILL.md covers Functions — deploy a browser…, When to use Notte vs the…, Setup and Quick start, plus 10 more sections
Calls brew, curl and go; reaches api.notte.cc and github.com; needs NOTTE_API_KEY and TOTP_BASE32_SECRET

What it does

Notte is an agent skill from Bitterbot-AI/bitterbot-desktop. 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.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Browser automation, Scheduled and recurring tasks and Serverless. It works with Firecrawl. The repository describes itself as: Bitterbot - a mesh of agents that turns shared experience into collective capability. The licence is MIT.

When your agent uses it

Tasks that involve Browser automation
Tasks that involve Scheduled and recurring tasks
Tasks that involve Serverless

Example prompts

“/notte”

Requirements

Python 3
A credential in NOTTE_API_KEY
A credential in TOTP_BASE32_SECRET

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit cd4562a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- brew
- curl
- go
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- api.notte.cc
- github.com
- news.ycombinator.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- NOTTE_API_KEY
- TOTP_BASE32_SECRET
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Notte loads about 2.8k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~82
When it runs · the whole SKILL.md, loaded when a task matches: ~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Bitterbot-AI/bitterbot-desktop at commit cd4562a, republished under its MIT licence (© Bitterbot-AI). 764 words, ~2,838 tokens.

Download SKILL.mdSave it as .claude/skills/notte/SKILL.md (or your agent's skills folder).

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

Notte

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

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.
Vault-backed login — passwords auto-fill on matching URLs without ever entering the model's context.
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.

bash

# 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

bash

# 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

bash

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')) — both are accepted.

docs/tools/browser-login.md recommends manual login because automated logins trigger anti-bot defenses and can lock the account. Notte fixes this: store credentials in a vault and the browser auto-fills on matching URLs. The agent never sees the password.

bash

notte vaults create --name "myservice"
notte vaults credentials add --vault-id <vault-id> \
  --url "https://myservice.com" \
  --email "user@example.com" \
  --password "..." \
  --mfa-secret "<TOTP_BASE32_SECRET>"   # optional TOTP

notte sessions start
notte page goto "https://myservice.com/login"
# Credentials auto-fill from the matching vault entry.

This unblocks autonomous flows during dream cycles where there's no user available to log in manually.

Agent runtime (delegate the whole task)

For multi-step goals, hand the task to a Notte agent:

bash

notte agents start --task "Find the cheapest non-stop SFO→CDG flight on Sep 14 and return the URL"
notte agents status
notte agents replay     # session recording / step trace

Agents are cheaper than authoring step-by-step CLI calls when the task has many branches.

Show full SKILL.md (309 more words)Show less

Stealth flags worth knowing

Flag	Effect
`--proxy`	Route through Notte's residential proxy pool
`--proxy-country <c>`	ISO country code (`us`, `gb`, `fr`, `de`, …)
`--solve-captchas`	Auto-solve reCAPTCHA / hCaptcha / Cloudflare turnstile
`--user-agent <ua>`	Pin a specific UA string
`--cdp-url <url>`	Bring-your-own remote browser (e.g. Lightpanda)
`--headless=false`	Required when `--cdp-url` points to Lightpanda Cloud

Page actions (cheat sheet)

bash

notte page click "@B3" | "#submit-button"
notte page fill "@I1" "hello"        # add --enter to submit
notte page check "#tos"
notte page select "#country" "France"
notte page upload "#file" --file ./report.pdf
notte page download "@L5"
notte page eval-js 'document.title'
notte page screenshot
notte page wait 500
notte page press "Enter" | "Escape" | "Tab"
notte page scroll-down [px] | scroll-up [px]

Navigation: goto, back, forward, reload, new-tab, switch-tab, close-tab.

Structured extraction

bash

notte page scrape --instructions "Every job posting: title, company, location, salary range" -o json
notte page scrape --instructions "Article body and author" --only-main-content

Note: for routine single-page extraction without auth or anti-bot needs, web_fetch (with Firecrawl) is the lighter path. Use notte page scrape when extraction lives behind login or after a multi-step navigation.

MCP path (no install required)

Notte ships an MCP server (notte-mcp). It can be called through the existing mcporter skill without installing the Notte CLI:

bash

NOTTE_API_KEY=... mcporter call --stdio "uv run --with notte-mcp python -m notte_mcp.server" \
  notte_scrape url=https://example.com instructions="Extract pricing tiers"

Use the CLI by default — the MCP path is mainly useful inside flows already orchestrating MCP calls.

Live viewer (debugging)

bash

notte sessions start -o json | jq -r '.viewer_url'
# or
notte sessions viewer

Environment variables

Variable	Purpose
`NOTTE_API_KEY`	API key (alternative to `notte auth login`)
`NOTTE_SESSION_ID`	Default session for `page` commands
`NOTTE_API_URL`	Override API endpoint
`NOTTE_MCP_SERVER_PROTOCOL`	`stdio` or `sse` (only for the MCP server)

Tips

Always observe before click / fill / scrape. Element IDs come from observe output.
After every navigation, observe again — IDs are scoped to the current DOM snapshot.
Stop sessions you start. notte sessions stop -y skips the prompt. Idle sessions cost API budget.
Lightpanda + --cdp-url requires --headless=false. Otherwise the CDP server returns 500.
@B3 clicking the wrong element? Fall back to a Playwright selector.
Modals blocking clicks? notte page press "Escape" then notte page wait 500.

Troubleshooting

Symptom	Fix
Site keeps blocking / shows captcha	Restart with `--proxy --solve-captchas`
Empty / partial scrape	Add `notte page wait 1000` then re-`observe` before `scrape`
`@B3` clicks the wrong thing	Use a Playwright selector (`button:has-text('Submit')`)
Lightpanda CDP returns 500	Add `--headless=false` to `sessions start`
Agent stuck on a captcha	Stop session, restart with `--solve-captchas`
401 / auth errors	Re-run `notte auth login` or set `NOTTE_API_KEY`

Files

Just SKILL.md in skills/notte of Bitterbot-AI/bitterbot-desktop.

Open the folder on GitHubat commit cd4562a

Compare with similar skills

Notte next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Notte compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Notte this skillBitterbot-AI/bitterbot-desktop	2.5k	—	~2.8k	Automated safety check: Pass	MIT	yesterday
Minimal Web Baas DemoTencentCloudBase/CloudBase-AI-Toolkit	1.1k	1 repos	~2.2k	Automated safety check: Pass	MIT	today
Scrapingbee CLIScrapingBee/scrapingbee-cli	108	—	~3.2k	Automated safety check: Notes	MIT	2 days ago
Agents SDKhodgef/apiker	127	3 repos	~3k	Automated safety check: Pass	MIT	1 mo ago
Firecrawl Interact Integrationfirecrawl/firecrawl	190k	1 repos	~731	Automated safety check: Pass	ISC	today
NubaseOtterMind/Nubase	623	—	~2.2k	Automated safety check: Notes	Apache-2.0	11 days ago

Similar skills

Minimal Web Baas Demo
TencentCloudBase/CloudBase-AI-Toolkit
Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS).
1.1k GitHub starsUsed in 1 repo~2.2k tokens
Productivity & AutomationAuto-check passed
Scrapingbee CLI
ScrapingBee/scrapingbee-cli
Fetch and read any web page, search the web, crawl a site, or pull structured data out of pages.
108 GitHub stars~3.2k tokensUpdated 2 days ago
Productivity & AutomationAuto-check: notes
Agents SDK
hodgef/apiker
Build AI agents on Cloudflare Workers using the Agents SDK. An agent skill from hodgef/apiker.
127 GitHub starsUsed in 3 repos~3k tokens
Backend & APIsAuto-check passed
Firecrawl Interact Integration
firecrawl/firecrawl
Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.
190k GitHub starsUsed in 1 repo~731 tokens
Data & AnalyticsAuto-check passed
Nubase
OtterMind/Nubase
A skill your agent uses when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets…
623 GitHub stars~2.2k tokensUpdated 11 days ago
Backend & APIsAuto-check: notes
X Bookmarks
sharbelxyz/x-bookmarks
Fetch, summarize, and manage X/Twitter bookmarks via bird CLI or X API v2.
289 GitHub stars~2k tokensUpdated 7 mo ago
Productivity & AutomationAuto-check: notes

Questions about Notte

What does Notte do?

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. Notte is an agent skill from Bitterbot-AI/bitterbot-desktop. 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.

When should I use Notte?

Notte fits situations like: tasks that involve Browser automation; tasks that involve Scheduled and recurring tasks; tasks that involve Serverless.

How do I install Notte in Claude Code?

Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a claude-code`. Or copy the skill folder (skills/notte in Bitterbot-AI/bitterbot-desktop) into .claude/skills/notte in your project. Claude Code loads it when a task matches its description.

How do I install Notte in Codex?

Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a codex`. Or copy the skill folder (skills/notte in Bitterbot-AI/bitterbot-desktop) into .agents/skills/notte in your project. Codex loads it when a task matches its description.

Can I use Notte in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Bitterbot-AI/bitterbot-desktop --skill notte -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/notte, .gemini/skills/notte, .github/skills/notte and .opencode/skills/notte in your project.

What does Notte need to run?

Going by SKILL.md and its folder, Notte needs the command-line tools its instructions call (brew, curl, go and jq) and credentials named NOTTE_API_KEY and TOTP_BASE32_SECRET. Our summary lists: Python 3; A credential in NOTTE_API_KEY; A credential in TOTP_BASE32_SECRET.

Does Notte access the network?

SKILL.md names 3 domains. In commands or code: api.notte.cc, github.com and news.ycombinator.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Notte safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Notte use?

Notte is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Notte use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Notte?

Skills that share tags, products or a category with Notte: Minimal Web Baas Demo (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars), Scrapingbee CLI (ScrapingBee/scrapingbee-cli, 108 stars), Agents SDK (hodgef/apiker, 127 stars) and Firecrawl Interact Integration (firecrawl/firecrawl, 190k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Notte?

Bitterbot-AI (a GitHub organization) maintains it in Bitterbot-AI/bitterbot-desktop, which has 2,467 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.

Source: Bitterbot-AI/bitterbot-desktop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Notte

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Notte

Functions — deploy a browser flow as a callable API

When to use Notte vs the bundled tools

Setup

Quick start

Vault-backed login (the biggest UX win over the bundled browser)

Agent runtime (delegate the whole task)

Stealth flags worth knowing

Page actions (cheat sheet)

Structured extraction

MCP path (no install required)

Live viewer (debugging)

Environment variables

Tips

Troubleshooting

Files

Compare with similar skills

Similar skills

More from Bitterbot-AI/bitterbot-desktop

Related

Questions about Notte