CrestingRadarGet featured →

Rank #1635 · on radar since 2026-07-03

mercury-mcp

Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.

Visit homepage ↗llmmechanistic-interpretabilityanchor-dimensionsmodel-context-protocol+7GitHub

Momentum

42.2
24h7d

Why it's ranked

Every score decomposes into published factors — the same math for every tool, paid or not. Read the methodology →

Velocity (weighted, cohort-normalized)0.438
Signal decay0.995
Corroboration1.000
Quality gate1.000

Raw signals (30 days)

github · forks13 latest · 2 snapshots
github · stars43 latest · 2 snapshots