feat: add FTS5 full-text search for memory retrieval - #2
Merged
codejunkie99 merged 1 commit intoApr 16, 2026
Merged
Conversation
Currently the memory system can only surface top-k entries by salience score, but cannot search by topic or keyword. This adds a lightweight SQLite FTS5 search tool that indexes all .md and .jsonl files under .agent/memory/ and returns ranked results with context snippets. - memory_search.py: FTS5 index with auto-rebuild and grep fallback - .gitignore: exclude derived .index/ directory - memory-manager SKILL.md: document the search command Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
codejunkie99
pushed a commit
that referenced
this pull request
Apr 16, 2026
Written by Minimax-M2.7 in Claude Code Harness. Integrates sergi-rz's FTS5 memory search (#2) behind a beta feature flag. Default OFF; users opt in through the onboarding wizard or by editing .agent/memory/.features.json directly. Addresses the three codex review findings on that PR at the same time. Beta feature framework - onboard_features.py (new): read/write .agent/memory/.features.json with a simple {key: {enabled: bool, beta: bool}} schema. - onboard.py: adds a final "Optional features" step to the wizard. Default answer is No — beta features stay off unless the user explicitly opts in. --yes (non-interactive) path writes the features file too, all off. - memory_search.py gates search/rebuild behind feature_enabled(). --status still works regardless so users can see the toggle. Codex review fixes on PR #2 - [P1] needs_rebuild now compares the set of memory files currently on disk with the set already in the index; any previously-indexed file that no longer exists flags the index stale. Without this, deleted/renamed files kept appearing in results until some unrelated file bumped the index. - [P2] search_grep now passes explicit .md/.jsonl target paths to grep instead of scanning the whole .agent/memory/ tree. Source files (archive.py, auto_dream.py, etc.) no longer pollute fallback search results. - [P3] .gitignore now ignores .agent/memory/.index/ correctly. The previous rule was cancelled by the !.agent/memory/** negation placed below it; moved the .index/ exclusion AFTER the negation so the later rule wins. Verified with git status --ignored.
joyanes97
pushed a commit
to joyanes97/agentic-stack
that referenced
this pull request
Sep 27, 2026
feat: add FTS5 full-text search for memory retrieval
joyanes97
pushed a commit
to joyanes97/agentic-stack
that referenced
this pull request
Sep 27, 2026
…nkie99#2 review Written by Minimax-M2.7 in Claude Code Harness. Integrates sergi-rz's FTS5 memory search (codejunkie99#2) behind a beta feature flag. Default OFF; users opt in through the onboarding wizard or by editing .agent/memory/.features.json directly. Addresses the three codex review findings on that PR at the same time. Beta feature framework - onboard_features.py (new): read/write .agent/memory/.features.json with a simple {key: {enabled: bool, beta: bool}} schema. - onboard.py: adds a final "Optional features" step to the wizard. Default answer is No — beta features stay off unless the user explicitly opts in. --yes (non-interactive) path writes the features file too, all off. - memory_search.py gates search/rebuild behind feature_enabled(). --status still works regardless so users can see the toggle. Codex review fixes on PR codejunkie99#2 - [P1] needs_rebuild now compares the set of memory files currently on disk with the set already in the index; any previously-indexed file that no longer exists flags the index stale. Without this, deleted/renamed files kept appearing in results until some unrelated file bumped the index. - [P2] search_grep now passes explicit .md/.jsonl target paths to grep instead of scanning the whole .agent/memory/ tree. Source files (archive.py, auto_dream.py, etc.) no longer pollute fallback search results. - [P3] .gitignore now ignores .agent/memory/.index/ correctly. The previous rule was cancelled by the !.agent/memory/** negation placed below it; moved the .index/ exclusion AFTER the negation so the later rule wins. Verified with git status --ignored.
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
2 participants
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.
Problem
The memory system can surface the top-k entries by salience score (
context_budget.py), but there's no way to search by topic or keyword. If an agent needs to recall what it learned about deploys, or a specific past failure, it has no retrieval path — it only sees whatever happens to score highest globally.Solution
A lightweight
memory_search.pythat builds a SQLite FTS5 index over all.mdand.jsonlfiles in.agent/memory/. It:Usage
python3 .agent/memory/memory_search.py "deploy failure" python3 .agent/memory/memory_search.py --status python3 .agent/memory/memory_search.py --rebuildWhat's changed
.agent/memory/memory_search.py— the search tool (~170 lines, zero dependencies beyond stdlib).gitignore— excludes.agent/memory/.index/(derived, auto-rebuilt)memory-manager/SKILL.md— documents the search command so the agent knows it existsNo existing code is modified. This is purely additive.
Context
I'm building Claudia OS, a personal AI assistant on top of Claude Code. I adopted your episodic memory architecture, dream cycle, and salience scoring (credited in my ATTRIBUTION.md). While adapting it, I needed keyword search over memory — the salience-only retrieval wasn't enough when the agent needed to recall something specific. This FTS5 approach solved it cleanly without adding infrastructure.
🤖 Generated with Claude Code