Memwyre
Memwyre is an open-source, universal memory infrastructure and persistent knowledge retrieval layer for Large Language Models (LLMs), AI agents, and custom applications.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
memwyreai
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
save_memorySave a new memory snippet to the Memwyre Vault. Use this tool when the user explicitly asks you to 'remember' something, 'save' a note, or when you encounter important information that should be persisted for future reference. Args: text: The content of the memory. source: Source of memory (default …
search_memwyreThe PRIMARY tool for searching the user's "Memwyre". Use this to retrieve relevant context, notes, code snippets, or past conversations from the Memwyre Vault. ALWAYS use this before answering questions that might require personal context. Args: query: The semantic search query (e.g., "python fastap…
get_inboxGet list of pending memories in the Memwyre Inbox. Args: workspace_name: Optional name of the workspace directory to filter inbox items.
approve_memoryApprove a pending memory in the Inbox and begin its ingestion process. Args: memory_id: The ID of the memory (e.g., 'mem_123').
discard_memoryDiscard a pending memory in the Inbox, removing it from view and deleting its embeddings. Args: memory_id: The ID of the memory (e.g., 'mem_123').
get_documentRetrieve the full content of a specific document by ID from Memwyre. Args: doc_id: The ID of the document.
generate_promptGenerate a prompt with retrieved context from Memwyre. Args: query: The user's question or request. template: The template to use ("standard", "code", "summary"). workspace_name: Optional name of the workspace directory. Pass this so that prompt context is scoped strictly to this project workspace.
update_memoryUpdate the content of an existing memory in Memwyre. Args: memory_id: The ID of the memory (must start with 'mem_'). content: The new content.
delete_memoryDelete a memory or document by ID from Memwyre. Args: memory_id: The ID of the item (e.g., 'mem_1' or 'doc_5').
list_memoriesList recent memories and documents in Memwyre. Args: limit: Number of items to return (default 10). offset: Pagination offset (default 0). workspace_name: Optional name of the workspace directory. Pass this so that items are filtered by this project workspace.
search_by_dateFind memories in Memwyre created within a specific date range. Args: start_date: Start date in YYYY-MM-DD format. end_date: End date in YYYY-MM-DD format (optional, defaults to end of start_date). workspace_name: Optional name of the workspace directory. Pass this so that items are filtered by this …
get_all_tagsGet a list of all tags currently used in Memwyre. Use this to understand the taxonomy of the user's knowledge. Args: workspace_name: Optional name of the workspace directory. Pass this so that tags are filtered by this project workspace.
save_fact_toolSave a precise fact or note to the Brain Vault for long-term memory.
MEMWYRE_FRONTEND_URLBRAIN_VAULT_API_KEYMEMWYRE_USER_EMAILBRAIN_VAULT_USER_EMAILMEMWYRE_USER_IDBRAIN_VAULT_USER_IDNOTION_CLIENT_IDNOTION_CLIENT_SECRETTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
13/13 tools missing one or more hints — save_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_memwyre (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_inbox (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — get_all_tags (line 851: tags_list = mem.tags if isinstance(mem.tags, list) else eval(mem.tags))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool description accuracy
get_all_tags: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/memwyreai/memwyre)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check