# cogmemai

Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search,

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add hifriendbot/cogmemai

# Browse available tools
npx -y @smithery/cli@latest tool list hifriendbot/cogmemai

# Get full schema for a tool
npx -y @smithery/cli@latest tool get hifriendbot/cogmemai save_memory

# Call a tool
npx -y @smithery/cli@latest tool call hifriendbot/cogmemai save_memory '{}'
```

## Direct MCP Connection

Endpoint: `https://cogmemai--hifriendbot.run.tools`

## Tools (33)

- `save_memory` — Store a developer memory (fact, preference, decision, architecture detail). Memories persist across all Claude Code ses…
- `save_rule` — Save a mandatory rule that will ALWAYS be followed in every session. Rules bypass scoring and decay — they are injected…
- `list_rules` — List all mandatory rules for the current project and/or globally. Rules are always-on memories that surface in every se…
- `delete_rule` — Delete a mandatory rule by its memory ID. Use list_rules to find the ID first.
- `recall_memories` — Search stored memories using semantic search. Returns memories ranked by relevance, importance, and recency. Use this t…
- `extract_memories` — Extract memories from a conversation exchange using AI. Send the developer message and assistant response, and the serv…
- `get_project_context` — Load top memories for the current project plus relevant global memories. Use at the start of a session to get full cont…
- `list_memories` — List stored memories with optional filters by type, category, scope, or project.
- `delete_memory` — Delete a specific memory by its ID. This is permanent.
- `update_memory` — Update an existing memory's content, importance, or scope.
- `bulk_delete` — Delete multiple memories at once by their IDs. Maximum 100 IDs per call. This is permanent.
- `bulk_update` — Update multiple memories at once. Each item needs a memory_id and fields to update. Maximum 50 items per call.
- `get_usage` — Get current usage statistics — memory count, extractions this month, tier info, projects.
- `export_memories` — Export all memories as JSON. Use this to back up memories or transfer them to another project.
- `import_memories` — Bulk import memories from a JSON array. Each memory needs at minimum a content field. Deduplication is applied automati…
- `ingest_document` — Extract memories from a document by splitting it into chunks and processing each one. Great for onboarding — feed in RE…
- `save_session_summary` — Save a summary of the current coding session. Captures what was accomplished, decisions made, and next steps. Stored as…
- `list_tags` — List all tags in use across your memories, with counts. Use this to see what threads/groups exist and find related memo…
- `link_memories` — Connect two related memories with a named relationship. Use this to build a knowledge graph — e.g., linking a bug fix t…
- `get_memory_links` — View all memories linked to a specific memory. Returns the relationship type and full memory details for each connectio…
- `get_memory_versions` — View the edit history of a memory. Shows all previous versions with timestamps and what changed. Useful for understandi…
- `get_analytics` — Get a memory health dashboard with insights: most recalled memories, never-recalled memories, stale memories, growth tr…
- `promote_memory` — Promote a project-scoped memory to global scope so it applies across all projects. Use this when you discover a prefere…
- `consolidate_memories` — Consolidate related memories into fewer, richer memories. Finds clusters of memories sharing the same subject (3+ memor…
- `save_task` — Create a task that persists across sessions. Tasks are tracked with status (pending, in_progress, done, blocked) and pr…
- `get_tasks` — Get tasks for the current project. Returns tasks filtered by status — defaults to showing pending and in_progress tasks…
- `update_task` — Update a task's status, title, description, or priority. Use this to mark tasks as in_progress, done, or blocked as you…
- `save_correction` — Save a correction pattern — what went wrong and what the right approach is. These are surfaced automatically when simil…
- `set_reminder` — Set a reminder that surfaces automatically at the start of your next session. Use for follow-ups, things to check, or d…
- `get_stale_memories` — Find memories that may be outdated based on age and access patterns. Returns memories that haven't been recalled or upd…
- `get_file_changes` — Show what files changed since your last session. Compares the current git state to a snapshot saved when your previous …
- `feedback_memory` — Signal whether a recalled memory was useful or irrelevant. Helps improve future recall quality over time. Use after rec…
- `generate_skills` — Manually trigger skill generation from your corrections, preferences, and patterns. Skills are behavioral directives th…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get hifriendbot/cogmemai <tool-name>
```