About tdai-memory-mcp
tdai-memory-mcp is a local-first memory MCP server for coding agents; the package has been renamed remem-mcp. The migration notes say the existing SQLite database, path, tools, and hooks remain unchanged.
Key features
- 01Renamed to remem-mcp
- 02Preserves existing memory.db
- 03Keeps the same database path
- 04Tools and hooks unchanged
Use cases
- 01Migrate the existing package to remem-mcp
- 02Continue using existing memory.db data
- 03Keep using the existing tools and hooks
MCP support
The README identifies it as a memory MCP server and says its tools and database remain unchanged after the rename.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | enum | No | The search mode.hybrid | keyword | vector |
| limit | integer | No | The maximum number of results. |
| query | string | Yes | A natural language query. The tool uses this text for the BM25 search and the vector search. |
| offset | integer | No | The pagination offset. Use this to get the next page of results. |
| max_tokens | integer | No | The maximum number of tokens in the response. If the result exceeds this value, the tool truncates the text. |
| session_key | string | No | The session key. The default is hash(cwd). Use this to recall memory from a different project. |
Details
From the project READMEtdai-memory-mcp → remem-mcp
This package has been renamed to remem-mcp.
Migrate
npx remem-mcp setup
Your existing memory.db is preserved — same SQLite file, same path (~/.local/share/remem-mcp/memory.db).
What changed
- Package name:
tdai-memory-mcp→remem-mcp - Env vars:
TDAI_*→REMEM_* - Everything else stays the same: same tools, same DB, same hooks
Links
- New repo: github.com/tinhien11/remem-mcp
- npm: npmjs.com/package/remem-mcp
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.