Skip to content
Agents tracked: 444 Releases (7d): 644 Agent status: 3 with issuesSince last limit reset: Claude 31d · Codex 3d Updated Oct 23, 2026
AgentGid
✦ Ask

Web data for agents · by Notte Labs (nottelabs)

Notte

A cloud service for running headless browsers, AI browser agents and serverless browser scripts, with proxies, CAPTCHA handling, saved login profiles and a credential vault, driven by Python/TypeScript SDKs, a REST API, a CLI or an MCP server.

You get remote browsers that agents can log into and keep logged into, without running your own browser fleet, proxy pool or secret store.

APIFree tierCommercial OK

Open notte.cc ↗ agent.md

For your project

Official API
Official API · Free tier Per-API-key per-minute, per-hour and per-day windows on session start, agent start and prompt endpoints; window sizes depend on plan
“[API Reference](https://docs.notte.cc/api-reference/authentication): REST API endpoints and authentication.” notte.cc/llms.txt
Key
Needed
“For clients or scripts that use bearer authentication, create a [Notte API key](https://console.notte.cc/apikeys).” docs.notte.cc/mcp-server
Formats
JSON
Data download
Not stated
Price
Free tier · from $20/mo Free: $0, $10 credits granted once (no expiry), 5 concurrent browsers, 15-minute sessions; usage: sessions $0.01/hour, functions $0.05/hour, residential proxies $10/GB
“Developer For prototypes and early production workloads. $20 /mo $20 credits / mo” notte.cc/
License
Notte Terms of Service (not readable); SSPL-1.0 (nottelabs/notte repo) Hosted platform plans; the terms page could not be read
Commercial use
Commercial use OK
“Startup For teams scaling browser agents in production. $100 /mo $100 credits / mo” notte.cc/
Credit
Not stated
Embedding
Embedding unclear
Using the website
Free tier

Read on Notte's own pages on Oct 24, 2026 · license or terms · API docs · pricing. Check the license page before you ship.

For your agent

A request your code or agent can make (add your key):

https://api.notte.cc/openapi.json
  • Python 'from notte_sdk import NotteClient' with NOTTE_API_KEY as a Bearer key; hosted MCP at https://api.notte.cc/mcp (OAuth or Bearer key, /mcp/full for admin tools); CLI 'brew install notte'; agents should read https://notte.cc/skill.md first.
  • Keep NOTTE_API_KEY in an environment variable and never print it
  • Respect the target sites' own terms when automating logins or scraping
  • The main repo is SSPL-1.0, not a permissive license: check it before self-hosting or redistributing

llms.txt: www.notte.cc/llms.txt · MCP: https://api.notte.cc/mcp

Paste into your agent: Read https://agentgid.com/resources/notte/agent.md before using Notte.

Quick answers

Does Notte have an API?

Yes. Notte has an official API documented at https://docs.notte.cc/.

Does the Notte API need a key?

Yes, you need an API key. Limits: Per-API-key per-minute, per-hour and per-day windows on session start, agent start and prompt endpoints; window sizes depend on plan

Is Notte free?

Yes, there is a free tier: Free: $0, $10 credits granted once (no expiry), 5 concurrent browsers, 15-minute sessions; usage: sessions $0.01/hour, functions $0.05/hour, residential proxies $10/GB Paid plans start at $20 a month.

Can I use Notte in a commercial project?

Yes. Its terms say: "Startup For teams scaling browser agents in production. $100 /mo $100 credits / mo"

What you can build

  • A price-watch job that runs a scheduled browser function on competitor pages and stores the extracted JSON
  • An agent that downloads monthly invoices from vendor portals using saved browser profiles and vault credentials
  • A coding-agent setup where Claude Code or Cursor gets a cloud browser through the Notte MCP server for end-to-end checks

Alternatives in Web data for agents

All 5 →

AgentKey Instead of signing up for and wiring a separate paid API for search, scraping, social and market data, an agent gets all of them through one install and one bill, with fallback to a second provider when one fails. APIOpen sourceFree tierLicense unclear Context.dev An agent or RAG pipeline gets clean page text from JavaScript-heavy or protected sites without you running headless browsers and proxy pools. APICommercial: conditions TinyFish It gives an agent search, clean page text and a remote browser without running your own scrapers, proxies or headless Chrome fleet, and search and fetch cost nothing within rate limits. APIFree tierCommercial: conditions BrowserAct You get a scraper that runs again on a schedule and is meant to adapt when the page layout changes, instead of hand-maintaining CSS or XPath selectors. APIFree tierCommercial: conditions

Something wrong or out of date? Tell us.