npx claudepluginhub sumeet138/qwen-code-agents --plugin pensyve<entity: fact> or <fact># /remember Store a fact about an entity as a semantic memory in Pensyve. ## Instructions When the user invokes `/remember <fact>`, follow these steps: 1. **Parse the input.** Look for an entity prefix in the format `entity: fact` or `entity - fact`. If no entity prefix is found, infer the most appropriate entity name from the fact content. Use lowercase, hyphenated names for entities (e.g., `auth-service`, `project-config`, `user-preferences`). 2. **Call the MCP tool.** Use `pensyve_remember` with: - `entity`: The parsed or inferred entity name (lowercase, hyphenated) - `fact`: ...
/rememberAdds user-specified content as a manual entry to .claude/memories/project_memory.json and confirms with a success message.
/rememberStores reusable guidance in knowledge memory service. Prompts for title, content, tags, scope; checks duplicates, validates, then stores and confirms.
/rememberStores decisions, patterns, outcomes, and context in a knowledge graph for future reference. Supports flags for success/failure tracking, categories, agent scoping, and global best practices.
/rememberSaves input as a classified experience (solution, gotcha, pattern, technique, decision, preference) to a JSON file in _memory/experiences/, extracting summary, problem, solution, and tags. Confirms with summary.
/rememberStores user facts (tech stack, conventions, decisions) in structured memory via entity-predicate extraction with project/global scope. Includes quote and confirms storage.
/rememberAnalyzes recent conversation or specified topic to draft persistent memory entries on decisions, patterns, and preferences, presents for approval, and stores approved ones for future sessions.
Store a fact about an entity as a semantic memory in Pensyve.
When the user invokes /remember <fact>, follow these steps:
Parse the input. Look for an entity prefix in the format entity: fact or entity - fact. If no entity prefix is found, infer the most appropriate entity name from the fact content. Use lowercase, hyphenated names for entities (e.g., auth-service, project-config, user-preferences).
Call the MCP tool. Use pensyve_remember with:
entity: The parsed or inferred entity name (lowercase, hyphenated)fact: The fact text to storeconfidence: Default to 1.0 unless the user indicates uncertaintyConfirm storage. Report back to the user what was stored, including:
User: /remember auth-service: uses JWT tokens with RS256 signing
auth-serviceuses JWT tokens with RS256 signingUser: /remember the database migration script requires Python 3.11+
database-migration (inferred)the database migration script requires Python 3.11+User: /remember we decided to use SQLite instead of PostgreSQL for the MVP
project-decisions (inferred)we decided to use SQLite instead of PostgreSQL for the MVP.claude/ memory files. All memory operations go through the Pensyve MCP tools.auth-service, not AuthService or auth service).pensyve_remember returns an error, display the error message and suggest the user check that the Pensyve MCP server is running (pensyve-mcp).