open-memex
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPEN_MEMEX_HOME | No | Override the storage root (default is %APPDATA%\open-memex on Windows, ~/.local/share/open-memex on macOS/Linux; the pre-rename MY_O_MEMORY_HOME name is still honored as a fallback). | |
| OPEN_MEMEX_CONFIG | No | Override the config file path (default is ~/.config/opencode/open-memex.jsonc; the pre-rename MY_O_MEMORY_CONFIG name is still honored as a fallback). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory_addA | Save a fact, preference, decision, or note to persistent local memory. Call this PROACTIVELY whenever the user shares something worth remembering across sessions — project conventions, tool choices, personal preferences, decisions made, error fixes and their causes. Worth saving: decisions and their reasons, preferences, conventions, gotchas, approaches tried and abandoned. Not worth saving: one-off task details or anything re-derivable from the code. Do not wait to be asked. For facts you infer yourself rather than the user stating, propose them first and save only on approval. Keep each memory to one self-contained statement; attach aliases when the parameter is available. If a note tells you the user's own wording was already stored verbatim this turn, that statement is already saved: do not retry it in a rewording — save only what that text does not contain, or use memory_supersede on the given id. Default scope is the current project; use the personal scope for facts about the user that apply across all projects. |
| memory_searchA | Search persistent memory by keyword (BM25 full-text). Returns matching memories from the current project and/or personal scope. Call before asking the user about past decisions, conventions, or preferences they may have told you before. Search well: break the question into its concepts and try 2–3 phrasings per concept — synonyms, the user's other language, shorter keyword forms — and check the other scope too, before concluding nothing is stored. |
| memory_listA | List memories in a scope, newest first, as a numbered inventory. Each line keeps the raw fields — [type] id=… created=… source=… — say them back to the user in plain words (source=user → 'you told me this'; inference → 'I inferred this, check me'; keyword → 'caught from your own wording'), never read the raw id aloud unless they ask. When the user asks 'what do you remember about me?', use scope=both and present the inventory conversationally. The user may point at an entry by its number ('delete #3'): numbers are only valid for the listing you just produced — re-run memory_list, read the candidate back in full, and get a confirmation before calling memory_forget (deletion is permanent). include=all is the audit view (superseded versions, retracted, archived also shown). |
| memory_supersedeA | Replace an existing memory with a newer version. The old memory is kept as history (status: superseded) and retrieval returns the new one. Use when a saved fact becomes outdated and should be replaced rather than duplicated. |
| memory_forgetA | Delete a memory by id. Use when the user asks to forget something. Deletion is permanent: before deleting, restate the memory's content to the user and get a confirmation. With soft=true the memory is hidden instead (retracted: out of lists and search, file kept, one-way). |
| memory_statusA | Show the project memory sync pipeline: drafts waiting in the outbox (appdata), memories in the repo awaiting review or published, and any repo files not yet committed. Call this at session start, when the server reports drafts waiting for review, or when the user says 'sync memory' (or '同步记忆'); then ask the user which drafts to sync. (MCP server and the |
| memory_submitA | Move outbox drafts into the repo memory dir for review: copies the drafts in as proposed (or keeps a local approval), commits locally on the current branch, and moves the outbox originals out. Never creates a branch on its own — pass branch= only with the user's explicit approval for the full chain. Prints the push and PR commands — those need the user's explicit approval and are never run automatically. (MCP server and the |
| memory_proposeA | Copy personal memories into the project outbox as review drafts. The personal originals stay put. (MCP server and the |
| memory_promoteA | Advance a project memory one step up the review ladder (proposed → approved → published), or reject it with a note. Rejected memories are never deleted — they can be revised and resubmitted. (MCP server and the |
| memory_resolveA | List git-conflicted memory files, or attempt a field-level 3-way merge of one. Semantic conflicts are reported, never auto-resolved. (MCP server and the |
| memory_pr_statusA | Read the current branch's GitHub PR and map its review state onto each in-repo memory: merged PR → published, PR approval → approved (approved_by = reviewer), changes-requested → suggestion only. Report by default; apply=true performs the mapped transitions locally (no push). (MCP server and the |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Core operations (add, search, list, supersede, forget) are clearly distinct. The workflow-stage tools (promote, submit, propose) and the two status tools (status, pr_status) have adjacent purposes, but descriptions differentiate them well enough that misselection is unlikely.
Every tool uses a consistent memory_ prefix with snake_case verb or verb_noun naming (memory_add, memory_search, memory_pr_status, memory_supersede). The pattern is predictable and uniform throughout.
11 tools is well within a comfortable range and each maps to a distinct action in a memory lifecycle (CRUD, search, review promotion, git sync). No tool feels redundant or filler.
The surface covers the full memory lifecycle: create, search, list, supersede, forget, review-ladder promotion, git conflict resolution, and outbox-to-repo sync. Minor gaps exist (e.g., no explicit memory_update/edit or bulk operations) but core workflows are complete.