Memory
Persistent memory: session search, curation, summarization, and user modeling.
Synapse does not rely on the context window alone. It maintains memory that survives sessions through three mechanisms, each inspectable and editable — nothing about your memory is hidden from you.
Session search
Conversation history is stored with SQLite FTS5 full-text search. Relevant past sessions are retrieved on demand and condensed with LLM summarization, so recalled context stays compact instead of dumping raw transcripts.
How recall flows
| Stage | What happens |
|---|---|
| Conversation | Every session produces text worth keeping |
| Session store | History persisted with full-text search (FTS5) |
| Search | Relevant past sessions retrieved on demand |
| Relevant memory | LLM summarization condenses what matters |
| Current task | Context is applied where it helps |
Agent-curated memories
The agent curates its own memory files (MEMORY.md / USER.md style entries) and periodically nudges itself to persist important knowledge. You can read and edit these files directly — they live in your Synapse home, in plain Markdown.
User modeling
Optional Honcho integration builds a dialectic model of you across sessions, deepening personalization over time: how you like answers structured, what projects you are working on, which conventions you follow.
Related commands
/usage— check current context consumption/compress— compact the active context/insights [--days N]— review recent session activity/memory— inspect curated memory state