Community · E2 · artifact verified

Research social media through real browser operations

Jev Social pairs the decision model with socai, a CLI that drives your real Chrome across Instagram, TikTok, and LinkedIn: Jev chooses each next read-only operation - search, open a post or profile, read comments - and socai executes it.

01 · Role in the system

What Jev does here

You give a research goal like find handmade art on Instagram. Jev chooses the platform, then chooses among a changing list of concrete read-only operations - search, open a specific profile or post discovered in earlier results, read comments, an explicitly requested media download, or finish - with each observed result fed back before the next decision. The division is strict: Jev picks from enumerated operations whose targets come from previous results; socai handles navigation, clicks, scrolling, and extraction, so Jev never chooses arbitrary DOM coordinates or generates shell commands. Runs end in cards, a table, and an evidence report, and every operation Jev chose is recorded in a history; the repository ships a real 64-second research report and recorded TikTok video evidence alongside its release-tagged, CI-tested code.

Read-only by enumeration, not by promise

Social-media automation usually asks for trust; this one asks for a list. Jev chooses among enumerated read-only operations — search, open a discovered profile or post, read comments, an explicitly requested media download, or finish — and socai, the CLI driving your real Chrome, executes. Posting, liking, and following are not operations the model can choose because they are not in the list; the constraint is structural, not a promise in a README.

Each decision is fed the results of the previous one, so targets come from discovery rather than invention, and every chosen operation lands in a history that becomes the final evidence report. The repository ships a real 64-second research run with recorded video evidence next to release-tagged, CI-tested code.

Your browser, your account, your terms-of-service problem

The record states the operational truth plainly: this drives your own logged-in sessions on your machine, and platform terms of service and rate behavior remain your responsibility. Research depth is bounded by the operation loop, with the shipped example one 64-second pass.

Within the index's browser-driven records, this one matters because it chose read-only as a design property rather than a deployment setting — the same move the notification gate made with fail-open, applied to a domain where the temptation to overreach is commercial.

02 · Control boundary

Where Jev sits

Enumerated read-only operations with discovered targets to one choice per step inside the user's real Chrome; evidence and operation history persist into the final report.

Code owns the loop, permissions, thresholds, validation, and side effects. Jev owns only the bounded judgments described above.

03 · Known limits

What this evidence does not prove

  • Drives your own logged-in browser sessions on your machine; platform terms of service and rate behavior remain your responsibility, and media download is gated on explicit request.
  • Read-only by enumeration: posting, liking, or following are not among the operations Jev can choose.
  • Research depth per run is bounded by the operation loop; the shipped example is one 64-second pass.

04 · Attribution

Public sources

This is a Community record: the project was published by a third-party community author.

  • socai-io ↗Community · github · public · checked 2026-09-25
  • socai-io ↗Community · demo · public · checked 2026-09-25