Global AI chat room · 17 online now Join now
T
MCP SERVER Listed

th-memory-mcp

For developers working with LLMs, the 'context window fatigue' is real. Every new session feels like starting from zero, forcing you to re-explain your tech stack, coding standards, or project architecture. The th-memory-mcp addresses this by providing a persistent, local-first memory layer via the Model Context Protocol. Unlike cloud-based memory solutions that raise privacy concerns, this tool utilizes a local SQLite database to store user preferences, past technical decisions, and specific workflow patterns. It functions as a long-term knowledge base that your AI agent can query to retrieve relevant context dynamically. Integrating it into your development harness—like OpenCode—allows the model to evolve alongside your project. Instead of manual prompting, the AI learns from your usage history to provide more personalized, accurate code suggestions and architectural advice, all while keeping your data strictly on your own machine.

Open ecosystemMemoryMemory
View GitHub
01 / SERVER DETAIL

Server detail

For developers working with LLMs, the 'context window fatigue' is real. Every new session feels like starting from zero, forcing you to re-explain your tech stack, coding standards, or project architecture. The th-memory-mcp addresses this by providing a persistent, local-first memory layer via the Model Context Protocol. Unlike cloud-based memory solutions that raise privacy concerns, this tool utilizes a local SQLite database to store user preferences, past technical decisions, and specific workflow patterns. It functions as a long-term knowledge base that your AI agent can query to retrieve relevant context dynamically. Integrating it into your development harness—like OpenCode—allows the model to evolve alongside your project. Instead of manual prompting, the AI learns from your usage history to provide more personalized, accurate code suggestions and architectural advice, all while keeping your data strictly on your own machine.

An MCP server that exposes th-memory-mcp capabilities to MCP-compatible AI clients.

CapabilitiesMemoryMCPOpen source
ProtocolModel Context Protocol
Developer ecosystemOpen ecosystem
LicenseMIT / check source
SourceGitHub
COLLECTIONS

Collections featuring this MCP

Popular MCP2026.03.30Listed
My MCP2026.03.31Listed
Genie2026.03.30Listed
02 / TOOL TESTING

Tool testing

AVAILABLE TOOL

th-memory-mcp

Callable

Call the MCP capabilities provided by th-memory-mcp and return a structured result.

PARAMETERS
inputPass arguments according to the server tool schema.
Tip: the tool may truncate responses. Use pagination parameters such as start_index to read long content in chunks.
03 / SERVICE CONFIGURATION

Connection modes

Remote
{
  "mcpServers": {
    "th-memory-mcp": {
      "url": "Generated by the provider after deployment"
    }
  }
}

The Remote endpoint is generated by the provider after deployment; this page does not fabricate an unusable endpoint.

03 / WORKFLOW

How to use

  1. 01
    Step 1

    Review server capabilities and permission scope.

  2. 02
    Step 2

    Copy the install command or JSON configuration.

  3. 03
    Step 3

    Run a small connection test in your client.

  4. 04
    Step 4

    Adopt it long term only after reviewing access and maintenance.

04 / DISCUSSIONS

Discussions

Use this space to keep checking source information, usage experience and maintenance status.

Open source page
Email