The hard stuff,
as one call.

Drop heelo in and your agent gets ordering, booking, outreach, and posting as single calls. No agent loops, no browser automation, no maintenance.

Get started

free to start · no credit card

The tasks that take 40 tool calls.
Now one call.

Your agent can drive a browser. It can string together tool calls. It can probably get most of the way through ordering, posting, booking. But it will take 40 tool calls, tens of thousands of tokens, and will quietly break the next time the platform changes.

Heelo ships the whole action as one call.

orderbookpostsendapplyscheduletransfercancelconfirm

without heelo

> user   send a personalized follow-up to these 12 leads
> agent  drafting messages...
         -> linkedin.send · ok
         -> linkedin.send · ok
         -> linkedin.send · timeout, retry
         -> linkedin.send · rate-limited, backoff
         [...37 more steps...]
> result x partial: 6 of 12 sent · 47s · $0.81

with heelo

> user   send a personalized follow-up to these 12 leads
> agent  calling heelo

  * heelo · linkedin.outreach
    |- v 12 personalized messages sent
    |- v 3 replied within 2h

  v success · 5s · $0.04

Or do what it already can.
At a fraction of the cost.

If your agent already does these tasks with a generic computer-use loop, great. We just do them with 90% fewer tool calls and 95% fewer tokens. Same outcome, dramatically different bill.

your agent today

> book a flight from NYC to London next Friday

 1  llm.plan()              2,048 tok
 2  browser.navigate()
 3  browser.screenshot()    1,184 tok
 4  llm.extract()           3,210 tok
 5  browser.click()
 6  browser.type()
 7  browser.screenshot()    1,902 tok
 8  llm.extract()           4,820 tok
 9  browser.click()
10  browser.screenshot()    2,047 tok
11  llm.extract()           5,102 tok
    ... 31 more steps
42  browser.screenshot()    1,891 tok
42 calls · 87k tokens · 58s · $3.94

with heelo

> book a flight from NYC to London next Friday

  * heelo · kiwi.book_flight
    |- searching JFK → LHR...
    |- found 8 options from $342
    |- v booked · BA-20481
1 call · 298 tokens · 4s · $0.10
42 calls -> 1 call87k tokens -> 298 tokens58s -> 4.1s$3.94 -> $0.17

Same outcome. 23x cheaper.

Two ways in.
Every platform on the other side.

Use heelo from any agent runtime that speaks MCP, or wire it into your own agent code with the SDK.

bash tool · mcp

# add heelo to your mcp config
$ npx heelo init
v added to .mcp.json

# your agent can now use heelo tools
> book me a flight from NYC to London next Friday

  * heelo · kiwi.book_flight
    |- searching flights...
    |- found 8 options, cheapest $342
    |- v booked · confirmation BA-20481

  v success · 6.3s · $0.10
claude code·codex·openclaw·hermes

sdk

from agents import Agent, Runner
from heelo import heelo_tools

agent = Agent(
  name="assistant",
  tools=heelo_tools(api_key="hl_..."),
)

result = Runner.run_sync(
  agent,
  "book a flight from NYC to London next Friday"
)

# agent picks kiwi.book_flight, handles
# clarifications, returns booked confirmation
openai·anthropic·langchain·vercel ai

Both paths share the same auth, the same tools, the same reliability. Pick what fits your stack.

amazonshopifybooking.comexpedialinkedinxinstagramgmailstripe

Give your agent hands.
Not just a brain.

Sign upLog in

free to start · no credit card