Automated README summary
Automatically summarized from the README on 23 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
BrowserClaw is a Chrome MV3 extension plus local MCP server that lets AI agents operate your real Chrome browser, preserving logins, cookies, and extensions while running in background tabs without stealing focus.
How it uses Jev
In chrome_act_toward_goal, the native server perceives the page and uses Jev System One inference (when TYPESAFE_API_KEY is set) to decide the next action toward a natural-language goal, falling back to a heuristic engine otherwise. The result is acted on locally without per-step MCP round-trips.
Primitives:choice
Technique worth stealing
Coupling a local Jev semantic micro-loop with a pruned, indexed DOM to avoid per-step network round-trips.
Try it
Set TYPESAFE_API_KEY, then call chrome_act_toward_goal with a natural-language goal.
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 projectnot found in the excerpt0.39
- Shows a System One patternFound in material0.77
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.27
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.18
- Is a replica of the modelnot found in the excerpt0.24
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 2
- About JevFound in material0.89
no-judgment band (0.40–0.60)
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 23 Sept 2026.