sage-memory

Detects mistakes, stores prevention rules, promotes them across scope — the 'experience' layer for any AI agent that recurringly hits the same bugs, miscommunications, or wrong-tool choices across sessions. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = durable context, sage-self-learning = agent mistakes and gotchas).

Captures and recalls durable context for AI agents — architecture decisions, user preferences, debugging insights, conventions, anything worth remembering across sessions. Teaches the agent when to remember (store findings during work), when to recall (search memory at session start and task start), and how to learn (structured knowledge capture via sage learn). Use when the user mentions memory, remember, recall, learn, capture knowledge, onboard to codebase, or when starting any session where sage-memory MCP tools are available.

Typed knowledge graph for any AI agent that needs structure — entity relationships, dependency chains, code-symbol graphs (with 0.11+ scan-codebase), task/project links, supersession chains. Use when creating or querying structured entities (Person, Project, Task, Event, Document, or code symbols from scan-codebase), linking related objects, checking dependencies, planning multi-step actions as graph transformations, or when skills need to share structured state. Trigger on "remember that X is Y", "what do I know about", "link X to Y", "show dependencies", "what blocks X", "what depends on X", entity CRUD, cross-skill data access, or any request involving structured relationships between things.