DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to sample AI engines by hand with no API keys with Geolook

Use a weekly buyer-intent sheet and the Chrome sampling assistant to collect AI answers without paying for API access.

Credentials. Persistent logged-in profiles for engines that need accounts keep login sessions on your machine, so protect the profile folder.

Who it is forA small team that wants AI engine data but has no engine API budget, or that needs to sample engines without public APIs.

The problemMany important engines have no API, and sampling them by hand is slow and inconsistent.

The outcomeA weekly buyer-intent queue that the Chrome extension fills in and submits back to the local dashboard as samples, cutting a weekly check from about 30 minutes to about 10.

What you need first

  • Python 3.9+ on macOS or Linux (Windows via WSL)
  • git
  • Optional: an engine API key, such as DeepSeek or GLM, for automated sampling and drafts

Steps

  1. Run git clone https://github.com/aigclink/geolook.git and pip3 install requests beautifulsoup4 lxml, then skip the engine key step.
  2. Run python3 scripts/geo.py ui to start the dashboard.
  3. Run python3 scripts/geo.py sample-sheet --intent buyer --limit 20 to export the weekly buyer-intent sheet. (inferred, check the README)
  4. Load the extension/ folder as an unpacked Chrome extension and open its side panel to work through the queue.
  5. Launch the disposable sandbox with ./extension/sandbox.sh so each session starts clean. (inferred, check the README)

Prompt for your agent

Using the geolook repo at <repo path>, export the buyer-intent sample sheet and list the 20 questions with their intent group. Confirm that the Chrome extension side panel shows the same queue, then report how many samples are still missing for this week.

Caveat. Automated sampling is skipped without keys, and the auto-run mode carries ToS risks that the project documents in its own README.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page