Evan Hu
afcb260554
All plugins are stdlib-only Python with no external dependencies. - auto-summarizer: extractive conversation summary for long context compression, persists per-agent summaries to disk - conversation-logger: JSONL audit logs per agent with ISO 8601 timestamps, auto-creates log directory tree - guardrails: safety filter detecting PII (email, phone, SSN, CC), prompt injection patterns, and credential exposure via regex - keyword-memory: extracts entities (emails, URLs, dates, technical terms like camelCase/snake_case/dotted identifiers) as memories - sentiment-tracker: keyword-based sentiment scoring with intensifiers and negation handling, only injects context for non-neutral sentiment - todo-tracker: detects action items via 7 task patterns, tracks completion, deduplicates, persists per-agent with 20-item FIFO limit
1.2 KiB
1.2 KiB
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).