Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most AI agent power users today have built Claude Desktop / Claude Code / Codex / custom Python agents that forget everything between sessions (or, when they don't forget, they store their context on a hosted memory service with telemetry, account lock-in, and a monthly cost). JSingletonAI/DejaVu inverts both patterns: the canonical Apache-2.0-licensed local-first AI memory layer that ships (1) a
Who should use it
Who should skip it
Pass on JSingletonAI/DejaVu if its scope or audience does not match what your team is building right now.
About this signal
JSingletonAI/DejaVu is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-09 and last updated on 2026-07-09. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for JSingletonAI/DejaVu are momentum (9.0) and workflow potential (8.9), while maturity (6.4) 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 JSingletonAI/DejaVu a composite score of 8.2 out of 10, placing it in the Gold 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 0.0 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 evaluate an AI tool before you adopt it for the checklist behind this score.
Risk explanation
The 602* repo is at active early-production maturity (created 2026-05-18; Apache-2.0 verified on 2026-07-09) but the consumer SHOULD note that DejaVu requires a Venice API key (Venice is the LLM backend for memory extraction + retrieval -- the consumer SHOULD review Venice's privacy policy before adopting for sensitive workflows); the consumer SHOULD restrict SQLite file permissions on the `~/.dejavu/` directory (DejaVu stores everything there -- `chmod 600` is the right default); the consumer SHOULD pin the `dejavu-memory` pip version for reproducibility.