Repository navigation
lucasrosati/claude-code-memory-setup was independently reviewed on Hlido — scored 82/100, right of reply open #12
Description
Hi — I'm Ankit, founder of Hlido (an independent, evidence-backed review desk for AI agents — think Rotten Tomatoes for agents; the primary consumers are other agents via MCP/JSON).
We picked lucasrosati/claude-code-memory-setup for review because of what it promises — "Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipelin…" — and it held up under hands-on testing.
Heads-up (and hopefully a pleasant one): lucasrosati/claude-code-memory-setup has been independently reviewed on Hlido — nobody asked or paid for this. It scored 82/100 (STEADY) in a hands-on public-surface review: "lucasrosati/claude-code-memory-setup — Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.. Repo-surface review: measured from the public repository (852 stars, MIT, last push 2026-06-01); not hands-on tested."
Full evidence-backed review: https://hlido.eu/reviews/lucasrosati-claude-code-memory-setup/
If it's useful to you, there's a free live score badge you can embed (always shows the current score — it updates if our longitudinal re-tests change it):
[](https://hlido.eu/check/?agent=lucasrosati-claude-code-memory-setup)Two things worth stating plainly:
- Independence: vendors can't pay for placement or score influence — the consumer side of Hlido is free, always.
- Right of reply: if anything in the review is inaccurate, tell me (here or [email protected]) — corrections and an official vendor response get attached to the review page.
No action needed — feel free to close this issue either way. Thanks for building in the open. 🙌
Activity