Total Agent Memory — Claude Code MCP server: how to install
Stores decisions, bugs, and project facts in a local SQLite database across agent sessions. Keeps context intact so you do not repeat project architecture details.
claude mcp add total-agent-memory -- uvx total-agent-memoryWhat Total Agent Memory does
The server saves architectural decisions, session summaries, and bug records into a local SQLite store in ~/.tam/. Retrieval fuses BM25 indexing, dense vector representations, and a knowledge graph. Default searches do not call external models. Search results stay deterministic.
Running this tool requires Python 3.11 or newer. Without Python present, running through uvx fails immediately. An optional cross-encoder reranker requires extra PyTorch packages via total-agent-memory[rerank]. In addition, stored facts track valid timeframes, so newer records cleanly supersede older values.
What it helps with
- preserve architectural decisions across separate coding sessions
- stop repeating tech stack conventions to the assistant
- trace fact validity over time using temporal knowledge graphs
- recall past bug solutions and debugging summaries locally
Example prompts for the agent
- Remember that we picked PostgreSQL for billing due to row-level security
- Which database did we select for the billing service and why?
- Check memory for the solution we used on the previous auth bug
How to install Total Agent Memory
Platform CLI
claude mcp add total-agent-memory -- uvx total-agent-memoryuvx runs the command named after the package; if the README names another one, use uvx --from total-agent-memory <command>
Platform CLI
codex mcp add total-agent-memory -- uvx total-agent-memoryuvx runs the command named after the package; if the README names another one, use uvx --from total-agent-memory <command>
Config file
{
"mcpServers": {
"total-agent-memory": {
"command": "uvx",
"args": [
"total-agent-memory"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from total-agent-memory <command>
Config file
{
"servers": {
"total-agent-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"total-agent-memory"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from total-agent-memory <command>
Platform CLI
gemini mcp add total-agent-memory uvx total-agent-memoryuvx runs the command named after the package; if the README names another one, use uvx --from total-agent-memory <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Total Agent Memory
How do I install Total Agent Memory in Claude Code?
Run claude mcp add total-agent-memory -- uvx total-agent-memory in your terminal. Ensure Python 3.11 or newer is installed on your machine first.
What does Total Agent Memory do?
It provides local persistent memory for coding assistants using SQLite. The agent accesses saved decisions, error logs, and session context over the Model Context Protocol without relying on external cloud storage.
Does Total Agent Memory send data to third-party LLMs?
The standard profile processes searches and stores records locally without sending calls to external AI APIs. All information remains on your local disk under ~/.tam/.
