strands-datacircle
Find the best GTM APIs. We benchmark all the GTM APIs and we put the results on our website.
Our website: https://datacircle.dev
This package gives Strands Agents four tools that call Datacircle's public API, https://api.datacircle.dev/v1. You need no key and no account.
| Tool | What the tool gives | Call |
|---|---|---|
datacircle_list_apis |
Every GTM API on Datacircle, with the API's slug, number of plans, number of providers and best plan | GET /apis |
datacircle_best_plans |
One API's plans, sorted by score out of 100, best first. Each plan comes with a rank and a price per 1,000 calls | GET /apis/{slug}/best |
datacircle_search_plans |
Plans that match a provider or plan name, on all APIs or on one API. You can sort them by score, provider or price | GET /plans |
datacircle_provider |
The APIs a provider sells, and the provider's rank on each API | GET /providers/{slug} |
Install
pip install strands-datacircle
The package needs Strands Agents 1.30 or later and Python 3.10 or later.
Use the tools in an agent
Give the tools to an agent:
from strands import Agent
from strands_datacircle import datacircle_tools
agent = Agent(tools=datacircle_tools())
agent("Which email finder API is best for under $5 per 1,000?")
The agent runs on Strands' default model. To pick a model, pass model= to Agent. To use our tools next to your own, put them all in one list: tools=[*datacircle_tools(), my_tool].
Agent(tools=["strands_datacircle"]) loads the same four tools. A config file with "tools": ["strands_datacircle"] loads all four Datacircle tools too.
Call a tool yourself
You can call each tool as a plain function. The function returns our API's answer as a dict:
from strands_datacircle import datacircle_best_plans
print(datacircle_best_plans("email-finder", limit=3))
agent.tool.datacircle_best_plans(slug="email-finder") runs the tool just as an agent does.
What the model reads
Each tool gives the model a JSON object. Each plan comes with a rank, provider, plan, score, price per 1,000 (perThousand, in dollars) and a page on datacircle.dev. The page on datacircle.dev lists every field.
You can give a provider's name in place of a slug. The tool turns Bright Data into bright-data.
An unknown slug raises DatacircleError with the API's message. For an unknown API slug, the message lists every valid slug. A number out of range also raises DatacircleError. The agent gives the error to the model. The model can then call the tool again.
Network
Each tool call makes one HTTPS GET request to https://api.datacircle.dev/v1 and nothing else. The request holds only the tool's own arguments. The API takes up to 60 calls a minute from one IP address. When the API asks the tool to wait, the tool waits up to a minute. The tool waits once per call at most. All plans are in one file at https://datacircle.dev/datacircle.json.
Links
- Datacircle: https://datacircle.dev
- The API: https://datacircle.dev/api
- The API's spec: https://api.datacircle.dev/v1/openapi.json
- What each key means: https://datacircle.dev/fields
MIT license.
Metadata
Release files for strands-datacircle 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| strands_datacircle-0.1.0.tar.gz | 9.2 kB | Without provenance | Details for strands_datacircle-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| strands_datacircle-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for strands_datacircle-0.1.0-py3-none-any.whl |
Total release size: 17.3 kB
Release files / strands_datacircle-0.1.0.tar.gz
| Download URL | strands_datacircle-0.1.0.tar.gz |
|---|---|
| Size | 9.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e5f28b759b0c21af7a96824e11cfa0823db4caab269e3da04d6e89f1181c3977
|
|
BLAKE2b-256 checksum How to use checksums |
b99e8d455e8c4b79f2b3044a209e40a7f96c68be34b3b24f6a5674faeddef629
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / strands_datacircle-0.1.0-py3-none-any.whl
| Download URL | strands_datacircle-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c75077bfe1baf3a9330bf3564568fac6af78976f121196e8a2e63ad53b36767a
|
|
BLAKE2b-256 checksum How to use checksums |
80ce9b31cb4b75571d1d42edc0af3d296ecccbe2ac37602585c0d87ea6442bcb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for strands-datacircle 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.