Teach your agent a website once. After that, it calls the site like an API instead of driving a browser.
API Anything watches a site's own page make a request and learns which parts of it are your inputs. It saves the result as an operation. Your agent calls that operation with new inputs over MCP, the CLI or TypeScript, and gets JSON back over plain HTTP.
<sub>Same agent (Claude Opus 5.5), same prompt, started together. Left: it drives headless Chrome through Playwright MCP. Right: it calls API Anything's Google Flights operation. Shown at 3× speed with no cuts; the timers show real elapsed time. Recorded 2026-09-28. MP4 · how it was recorded</sub>
Across 5 runs of each task, the agent using API Anything answered 1.5 to 2× sooner, read about half as many tokens, and cost the same or less. All 20 answers were correct. Method, raw numbers and limits.
Paste this into Claude Code, Codex or another coding agent:
Set up API Anything for me: https://github.com/goodnight000/api-anything/blob/main/INSTALL.md
The agent checks Node 22.13+, builds and installs the api-anything command, confirms that a
call works, then connects the MCP server and the skill to itself. Restart the agent, then ask it
something like "What does Goodreads rate Piranesi?"
Install by hand #
The package isn't on npm yet. Don't use npm install -g github:..., because it fails under npm 11.
git clone https://github.com/goodnight000/api-anything.git && cd api-anything
npm ci && npm install -g "$(npm pack --silent)"
api-anything call hacker-news search query=sqlite
{"ok":true,"class":"ok","tier":1,"data":[{"title":"Hosting SQLite databases on GitHub Pages or any static file hoster","url":"https://phiresky.github.io/blog/2021/hosting-sqlite-databases-on-github-pages/", ...}, ...],"ms":111}
tier: 1 means plain HTTP with no browser. A failure returns ok: false with a class, a
reason and a next step. Connect an agent with codex mcp add api-anything -- api-anything mcp,
claude mcp add --scope user api-anything -- api-anything mcp, or this MCP entry:
{ "mcpServers": { "api-anything": { "command": "api-anything", "args": ["mcp"] } } }
Over MCP an agent calls operations, using four tools: list_sites, list_operations,
call_operation and login. To create operations, an agent needs a shell and the
skill. Google Chrome is needed only for creating operations and
for browser fallback. Setup details.
Give it the page URL with a placeholder, and two example inputs:
api-anything add hn-demo links \
--trigger 'https://news.ycombinator.com/from?site={domain}' \
--example domain=github.com --example2 domain=github.io --match path=/from \
--html '{"items":"tr.athing","fields":{"title":".titleline > a","url":".titleline > a@href"}}'
api-anything call hn-demo links domain=arxiv.org # 30 arxiv.org stories, tier 1
Headless Chrome loads the page once for each example. The part of the request that changed with the input becomes a parameter, and the rest is stored as a template. The agent (or you) picks the request and the fields. API Anything builds the template without an LLM. Recorded demos.
Tell an agent what you need from a site. The skill makes it do this, in order:
- Ask about whatever the request leaves unclear.
- Propose operations and wait for your approval.
- Scout each page with
capture --outline. This is a summary of what each request returns, so the agent doesn't have to read full responses. - Build each operation and check it with an input that wasn't an example.
Goodreads has had no public API since 2020. One run took 6.3 minutes and $1.19. It produced search, book details, an author's books and reviews:
api-anything call goodreads searchBooks q=piranesi
api-anything call goodreads getBook bookId=50202953
- Tested on unseen books. The test used 30 books that nobody used while building the operations. For the 29 books the search found, every checked field matched the page Chrome rendered: title, rating, ratings count and pages. All 146 calls went over plain HTTP.
- Agent comparison. An agent using the operations answered 5 books in 30.5 s; the browser agent took 182.5 s. For one book, it cost a third as much.
- No agent needed. A plain script (
examples/reading-list.mjs) builds the same five-book table in 16 s with no model.
How it was explored, tested and compared.
22 read operations across 9 sites:
google-flights: search, top flights, price calendarhacker-newsxandinstagramprofiles- search on
youtube,airbnbandamazon linkedin: profiles, companies and search, with your own logingoodreads: search, books, author lists and reviews, built by the explorer above
They cover selected features, not whole sites. api-anything ops <site> lists parameters and
caveats.
-
Learn. Chrome records the page's requests for two example inputs. The request that followed the inputs becomes a template with slots, and cookies and tokens become references to a local store.
-
Call. Fill the slots and send the request with Node's
fetch. If the site blocks that, fetch from inside a Chrome page. As a last resort for reads, run the page itself and read its own response. -
Repair. If the request stops working (a rotated id, a moved field), re-learn it and save the new version only after a replay succeeds. Otherwise the call returns an error, not someone else's data.
-
It is a local tool, not a hosted API. It uses your machine, your network and your sessions.
-
It knows only the operations it was taught. It doesn't support every feature of every site.
-
Repair can fail. There is no CAPTCHA solving, and if a site challenges real Chrome, you have to clear the challenge by hand.
-
No write operations are bundled. LinkedIn messaging isn't bundled and hasn't been tested against LinkedIn. Writes are tested only against a local fixture, and they need
--allow-writes. An HTTP 2xx doesn't prove a message was delivered. -
Credentials stay in
~/.api-anything, and specs hold references, never values. Read each site's terms: you are responsible for how you use it.
Benchmark · Demos · Setup for agents · Reference · Design · Release checks · Contributing
MIT licensed.