Add SQLite Graph Memory to Systems and Open Sources - #133
Open
tonydzi wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
One open-source memory system added to 💻 Systems and Open Sources, in publication-date order (2026-07-03, the repository creation date), and mirrored in both
README.mdandREADME_cn.mdas the contributing guide requires.System: SQLite Graph Memory — Graph RAG for agent long-term memory on plain SQLite. Retrieval combines vector search, a hand-curated wikilink graph over the note corpus, and a cross-encoder rerank step; a separate per-turn ledger records memory state with no LLM call, so recall costs zero tokens until something is actually retrieved.
Why it may interest this list: most entries in the table are hosted services or heavier stacks. This one is deliberately the opposite end — a single-file SQLite store with no server and no vendor, which makes it easy to reproduce and to run fully offline. The wikilink graph is curated by a human rather than extracted by an LLM, which is a different point on the precision/recall trade-off than most graph-memory systems here.
Details: MIT licensed, working pilot, no paid backend. No website, so the website cell says "No official website" in the existing style.
Checked the table for a duplicate entry — nothing matching this project. Happy to adjust the date or the row if you order by first public release rather than repository creation.