jevbooks

← All projects

jev-social

socai-io/jev-social · Homepage

Browser-grounded social research with Jev-chosen read-only operations.

Agent Decisions1.00Runner-up: Classification & Routing
Automated README summary

Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

An open-source, local-first research agent for Instagram, TikTok, and LinkedIn. It turns a research goal into source-cited reports by driving your own signed-in Chrome through the socai CLI.

How it uses Jev

At each step Jev makes a Choice over the current allowlist of read-only socai CLI operations and concrete targets discovered in prior results. The selected operation runs in Chrome; its observed result rebuilds the next choice set. Malformed or low-confidence choices are rejected before execution.

Primitives:choice

Technique worth stealing

Rebuild the typed choice set from live browser state after every executed operation, removing previously attempted actions.

Try it

npx github:socai-io/jev-social#v0.1.13 onboard, then npx github:socai-io/jev-social#v0.1.13

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.96
  • Shows a System One patternFound in material0.89
  • Describes handling uncertaintynot found in the excerpt0.20
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.87
  • Top-10 learning shortlist signalFound in material0.64
  • Is a replica of the modelnot found in the excerpt0.12
  • Solves a common problem (0–2)score on a 0–2 scale0.99 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.96Shows a System One pattern0.89Describes handling uncertainty0.20Reports measured numbers0.05Is a runnable tool0.87Top-10 learning shortlist signal0.64Is a replica of the model0.1200.51Solves a common problem (0–2)0.99 / 2012

no-judgment band (0.40–0.60)

Design patterns
Inspection0.68Funnel0.49Fail open, fail closed0.48Flight recorder0.2300.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 13 Oct 2026.