Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent developers, automation builders, AI-curious readers, students, researchers, and any developer wiring an AI agent to a local learning surface -- and who can pair shlokkhemani/rabbithole with Node 18+ for the runtime surface, a browser (default) for the canvas surface, the `npx -y github:shlokkhemani/rabbithole` invocation for the MCP install command, and the `RABBITHOLE_NO_BROWS
Who should use it
Who should skip it
Move on from shlokkhemani/rabbithole if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
shlokkhemani/rabbithole is tracked by RepoRadar as a local mcp server that gives any in the Local MCP Infinite Canvas for Agent Learning section. It was first seen on 2026-07-07 and last updated on 2026-07-07. The current verdict is 'try now' with a Silver tier and easy setup difficulty. The standout signals for shlokkhemani/rabbithole are workflow potential (9.1) and setup ease (8.8), while maturity (5.6) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned shlokkhemani/rabbithole a composite score of 7.6 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 75* / 6-fork repo is at active maintenance but the canvas auto-opens a browser tab on `open_rabbithole` -- the consumer SHOULD review the browser policy before deploying in a headless / production environment (`RABBITHOLE_NO_BROWSER=1` disables auto-open); the persistence model keeps every hole on the local filesystem -- the consumer SHOULD review the persistence directory and decide on a retention policy before relying on the canvas for long-running research sessions; the six MCP tools drive a browser canvas; so any XSS / untrusted-document risk from the rendered documents inherits from the browser -- the consumer SHOULD review the document sources before opening them in the canvas.