docs: refresh README to reflect 0.9.0 - #44
Merged
Conversation
… modes, semantic GA)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The README was last substantially updated on 2026-05-28 (commit
446c586, FastMCP entrypoint consolidation). Since then, PRs #29–#40 shipped in the 0.9.0 release, and several README sections had gone stale. This brings the README in line with the current state of the package.Changes by section
Semantic Search — Removed the stale "v0.6.0 was yanked / shipping in a future release" warnings. 0.9.0 (and 0.6.0–0.8.6) are live on PyPI, so the install instructions are now unconditional. Renamed the section anchor from
semantic-search-v060tosemantic-searchand updated the badge/links. Added a Search modes subsection documenting mode resolution order,LORE_SEARCH_MODE_DEFAULT(defaulthybrid), and therequested_moderesponse field. Added a note thatsummarymode was removed (now a validation error; Lore is LLM-free by design). Noted that PostgreSQL uses a GIN full-text index for the lexical leg. AddedLORE_SEARCH_MODE_DEFAULTto the semantic config table.Automatic Memory Extraction (new section) — Documents the opt-in session-end extraction pipeline (OpenRouter/Cerebras), graceful degradation,
source:auto-extractedtagging and the review queue, with a pointer todocs/auto-extraction-setup.mdfor full setup.Quick Start — Dropped the "v0.6.0 yanked" note from the optional semantic-search install step; updated the cross-link anchor.
Tool Reference — Made the table complete:
kb_get_batch,kb_backfill_embeddings,kb_embedding_status; clarifiedkb_searchcovers semantic/hybrid/FTS.investigation_delete_note,investigation_delete_experiment(0.8.6, Add journal_delete and investigation_delete tools for test/admin cleanup #21).journal_delete(0.8.6, Add journal_delete and investigation_delete tools for test/admin cleanup #21).strategyis nowfullorchunked(nosummary).Backends — Added a "Semantic search" row to the comparison table (sqlite-vec + FTS5 vs pgvector + GIN) and noted the PostgreSQL GIN full-text index in the prose.
Configuration reference — Added
LORE_SEMANTIC_SEARCH,LORE_SEARCH_MODE_DEFAULT,OPENROUTER_API_KEY, andCEREBRAS_API_KEY.Hermes Memory Provider — Noted that the plugin drives the auto-extraction pipeline.
No content was added as a changelog; the README continues to describe current state only. The detailed history lives in
CHANGELOG.md.🤖 Generated with Claude Code