memorix

Store a new observation/memory. Automatically indexed for search. Use type to classify: gotcha (🔴 critical pitfall), decision (🟤 architecture choice), problem-solution (🟡 bug fix), how-it-works (🔵 explanation), what-changed (🟢 change), discovery (🟣 insight), why-it-exists (🟠 rationale), trade-off (⚖️ compromise), session-request (🎯 original goal). Stored memories persist across sessions and are shared with other IDEs (Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, Trae) via the same local data directory.

Suggest a stable topic_key for memory upserts. Use this before memorix_store when you want evolving topics (like architecture decisions, config docs) to update a single observation over time instead of creating duplicates. Returns a key like "architecture/auth-model" or "bug/timeout-in-api-gateway".

Search project memory. Returns a compact index (~50-100 tokens/result). Use memorix_detail to fetch full content for specific IDs. Use memorix_timeline to see chronological context. Searches across all observations stored from any IDE session — enabling cross-session and cross-agent context retrieval.

Mark observations as resolved (completed/no longer active). Resolved memories are hidden from default search but can still be found with status="all". Use this to mark completed tasks, fixed bugs, or outdated information so they don't pollute future context.

Scan active memories for duplicates, contradictions, and outdated information using LLM analysis. Automatically resolves redundant memories. Requires LLM to be configured (set MEMORIX_LLM_API_KEY or OPENAI_API_KEY environment variable). Without LLM, falls back to basic similarity-based consolidation.

Get chronological context around a specific observation. Shows what happened before and after the anchor observation.

Fetch full observation details by IDs (~500-1000 tokens each). Always use memorix_search first to find relevant IDs, then fetch only what you need.

Show memory retention status or archive expired memories. action="report" (default): show active/stale/archive-candidate counts. action="archive": move expired observations to archive file (reversible). Uses exponential decay scoring based on importance, age, and access patterns.

Scan project for agent rule files (Cursor, Claude Code, Codex, Windsurf, Antigravity, Copilot, Kiro, OpenCode, Trae), deduplicate, detect conflicts, and optionally generate rules for a target agent format. Without target: returns sync status report. With target: generates converted rule files.

Migrate your entire workspace environment between AI coding agents (Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, OpenCode, Trae). Syncs MCP server configs, workflows, rules, and skills across IDEs. Action "scan": detect all workspace configs. Action "migrate": generate configs for target agent (preview only). Action "apply": migrate AND write configs to disk with backup/rollback.

Memory-driven project skills. Action "list": show all available skills from all agents. Action "generate": auto-generate project-specific skills from observation patterns (gotchas, decisions, how-it-works). Action "inject": return a specific skill's full content for direct use. Generated skills follow the SKILL.md standard and can be synced across Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, OpenCode, and Trae.

Promote observations to permanent mini-skills that never decay and are auto-injected at session start. Action "promote": convert observation(s) to a mini-skill. Action "list": show all active mini-skills. Action "delete": remove a mini-skill by ID.

Mini-skills are project-specific specialized knowledge derived from your actual memories — gotchas, decisions, fixes that generic online skills cannot provide.

Find and merge similar observations to reduce memory bloat. Uses text similarity to cluster related observations by entity+type, then merges them into single consolidated records. Use action="preview" to see candidates without changing data, action="execute" to merge.

Example: 10 similar gotchas about Windows paths → 1 consolidated gotcha with all facts preserved.

Start a new coding session. Returns context from previous sessions so you can resume work seamlessly. Call this at the beginning of a session to track activity and get injected context. Any previous active session for this project will be auto-closed.

End a coding session with a structured summary. This summary will be injected into the next session so the next agent can resume work seamlessly.

Recommended summary format:

Goal

[What we were working on]

Discoveries

• [Technical findings, gotchas, learnings]

Accomplished

• ✅ [Completed tasks]

• 🔲 [Pending for next session]

Relevant Files

• path/to/file — [what changed]

Get context from previous coding sessions. Use this after compaction to recover lost context, or to manually review session history. Returns previous session summaries and key observations.

Export or import project memories. Action "export": export observations and sessions (JSON or Markdown). Action "import": import from a JSON export (re-assigns IDs, skips duplicate topicKeys).

Launch the Memorix Web Dashboard in the browser. Shows knowledge graph, observations, retention scores, and project stats in a visual interface.

Register, unregister, or list agents in the team. Action "join": register this agent (returns agent ID). Action "leave": mark agent inactive, release locks. Action "status": list all agents with roles and capabilities.

Advisory file locks to prevent conflicting edits. Auto-releases after 10 min TTL. Action "lock": acquire lock. Action "unlock": release lock. Action "status": check lock status.

Create, claim, complete, or list tasks in the team task board. Supports dependencies. Action "create": create a task. Action "claim": assign to yourself. Action "complete": mark done with result. Action "list": show tasks.

Send, broadcast, or read messages between agents. Action "send": direct message to one agent. Action "broadcast": message all active agents. Action "inbox": read this agent's inbox.