Evan Hu
5e4fc2ccf3
The daemon's `manifest_missing_integrity_hooks` check (#3804) hard-fails any registry install whose plugin.toml declares hooks but lacks an [integrity] entry for each one. All 11 plugins under plugins/ had the [hooks] table but were missing [integrity], so `librefang plugin install <name>` would error after download with "missing [integrity] hashes for hook script(s): ...". Compute and pin SHA-256 over each `hooks/*.py` under every plugin dir. The mempalace-indexer entries were already present and are unchanged (reordered alphabetically by the regenerator). Verified each plugin.toml still parses (Python tomllib).
keyword-memory
Extracts keywords and named entities from user messages and returns them as contextual memories. Gives agents awareness of conversation topics without requiring external NLP libraries.
Extraction Techniques
- Plain keywords: Splits words, filters English stopwords (~50 words), removes short tokens
- Capitalized phrases: Detects multi-word proper nouns and mid-sentence capitalized words
- Emails and URLs: Regex pattern matching
- Numbers with units: e.g. 500ms, 10GB, 3.5GHz
- Dates: YYYY-MM-DD, MM/DD/YYYY, DD.MM.YYYY formats
- Technical terms: camelCase, snake_case, dotted identifiers (e.g.
os.path)
Results are deduplicated and capped at 10 keywords.
Hooks
| Hook | Script | Description |
|---|---|---|
| ingest | hooks/ingest.py |
Extracts keywords from the user message and returns them as a memory fragment |
Example Output
{"type": "ingest_result", "memories": [{"content": "[keyword-memory] Key topics: GPT-4, machine_learning, data pipeline, https://example.com"}]}
If no meaningful keywords are found, returns an empty memories list.
Usage
Installed automatically when enabled in agent configuration. No external dependencies required (stdlib only).