KBAISE/ for lovable
Head to head

claude-mem vs graphify

claude-mem and graphify solve the same job (Memory & context), so this is a pick-one decision. claude-mem is our default here: Runs with no intervention after install, which is why it beats a manual notes file. Content wrapped in <private> tags is excluded from storage.

Quick read
  • Editor's pick: claude-mem.
Fieldclaude-memgithub.com Not yet sweptgraphifygithub.com Not yet swept
What it isCaptures what the agent does via hooks, compresses events into semantic summaries, stores them in SQLite with FTS5 plus a Chroma vector DB, and injects the relevant slice into future sessions. Progressive disclosure: search returns a ~50–100 token index before you fetch detail. ~91k stars.Turns a mixed corpus — code, docs, SQL schemas, configs, PDFs, images — into a queryable knowledge graph. Code extraction is deterministic and local; only prose and images route through Claude. Every edge is labeled EXTRACTED, INFERRED or AMBIGUOUS. Outputs graph.json, an interactive HTML visualization, a report and an Obsidian vault. ~107k stars.
CategoryMemory & contextMemory & context
Cost tierfreefree
PricingFree · Apache-2.0Free
Why builders pick itRuns with no intervention after install, which is why it beats a manual notes file. Content wrapped in <private> tags is excluded from storage.The mixed-corpus part is your project angle — it will ingest editorial PDFs, style guides and back-issue docs alongside the code, not just source files. The --wiki export produces agent-navigable markdown grouped by concept.
Watch out fornot loggednot logged
How to wire it upnpx claude-mem installuv tool install graphifyy
Editor's pickYesNo

Agent endpoint: GET /api/public/compare?slugs=claude-mem,graphify