Magnifico4625
UserPersistent project-aware memory for AI coding tools. Built on MCP. Works with Codex, Claude Code, and other MCP-compatible clients.
Categories
Indexed Skills (9)
remember
Save a project decision or context to Locus semantic memory. Use when the user says "remember this", "save this decision", or wants to store architectural context for future sessions.
locus-memory
Use when the user needs persistent project memory across sessions. Triggers on: "remember this", "what did we decide about...", "show project structure", "what changed recently", "search memory". Do NOT trigger for: ephemeral questions, one-off lookups, file reads that don't need memory.
forget
Delete memory entries from Locus matching a search query. Use when the user says "forget this", "delete memory", or "remove that decision".
memory-purge
Delete ALL Locus memory for the current project. This is destructive and irreversible.
compact
Clean up old episodic memory entries to free space. Keeps recent sessions intact.
memory-audit
Audit Locus stored data — shows inventory of structural map, semantic memories, episodic entries, hook captures, DB size, and security status. Use when the user wants to know what data Locus has stored.
memory-config
Show current Locus configuration values and their sources (default, env var, or detected)
memory-doctor
Run Locus environment health check — 10-point diagnostic covering Node.js version, storage backend, FTS5, DB permissions, git availability, and more. Use when troubleshooting plugin issues or checking setup.
memory-status
Show Locus memory statistics — files indexed, memories stored, DB size, scan strategy, backend info. Use when the user asks about memory status, storage info, or plugin health overview.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.