Continual Learning (Cursor plugin)
Official Cursor plugin that incrementally updates AGENTS.md memory from chat transcripts using high-signal bullet points.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Continual Learning (Cursor plugin), derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A first-party Cursor plugin that watches agent transcripts and distills them into concise, high-signal memory bullets appended to the repo's AGENTS.md. It runs as a Cursor plugin (commands + agent instructions) so the coding agent progressively 'learns' project conventions across sessions. Security surface: it reads full conversation transcripts and writes to a tracked project file.
Key features and capabilities
- Transcript-driven memory extraction
- Incremental AGENTS.md updates
- High-signal-only bullet filtering
Use cases
- Persist project conventions for the agent
- Reduce repeated context in long-lived repos