Persistent causal memory for AI agents. Raven records everything your agent does as a causally-linked chain, including decisions, tool calls, parallel work, and session history. Your agent finally remembers.
Raven Memory
Raven gives your OpenClaw agent persistent causal memory that survives across sessions, days, and weeks.
What it does
- Records every significant event as a node in a causal chain
- Loads relevant history at session start via semantic search
- Supports rollback, branching, and parallel task tracking
- Stores everything locally in ~/.raven/raven.db
- Encrypted at rest with SQLCipher (optional)
Tools exposed
raven_start_session— load context at conversation startraven_record_event— write an event to the chainraven_end_session— close session with notesraven_search— semantic search over full historyraven_rollback— undo N stepsraven_get_status— health check
Setup
Install from PyPI:
pip install raven-memory
With semantic search (recommended):
pip install "raven-memory[vec]"
Then install this skill:
clawhub install raven-memory
Add to your OpenClaw system prompt:
At the start of every conversation, call raven_start_session with
the user's first message as search_query. Load the returned
summary/nodes into your context before responding. Record events with raven_record_event. End sessions with raven_end_session.
Related skills
- Downloads
- 910All time
- Security audit
- Review
- Last updated
- 6mo ago
- Current version
- v1.0.1
- License
- MIT-0
