No description
Find a file
ProofOfConcept d14710e477 scripts: use capnp store instead of reading markdown directly
Add store_helpers.py with shared helpers that call poc-memory commands
(list-keys, render, journal-tail) instead of globbing ~/.claude/memory/*.md
and parsing section headers.

All 9 Python scripts updated: get_semantic_keys(), get_topic_file_index(),
get_recent_journal(), parse_journal_entries(), read_journal_range(),
collect_topic_stems(), and file preview rendering now go through the store.

This completes the clean switch — no script reads archived markdown files.
2026-02-28 23:32:47 -05:00
prompts poc-memory v0.4.0: graph-structured memory with consolidation pipeline 2026-02-28 22:17:00 -05:00
schema add position field to capnp schema 2026-02-28 23:15:10 -05:00
scripts scripts: use capnp store instead of reading markdown directly 2026-02-28 23:32:47 -05:00
src add position field to capnp schema 2026-02-28 23:15:10 -05:00
.gitignore poc-memory v0.4.0: graph-structured memory with consolidation pipeline 2026-02-28 22:17:00 -05:00
build.rs poc-memory v0.4.0: graph-structured memory with consolidation pipeline 2026-02-28 22:17:00 -05:00
Cargo.lock replace state.json cache with bincode state.bin 2026-02-28 22:30:03 -05:00
Cargo.toml replace state.json cache with bincode state.bin 2026-02-28 22:30:03 -05:00