PMB AI — MCP server memory for Claude Code and Cursor
Local memory for your coding agent: decisions, lessons and project structure live in SQLite and come back in later sessions. No cloud, no API keys.
claude mcp add pmb-ai -- uvx pmb-aiWhat PMB AI does
PMB AI gives an agent long-term memory. Decisions from last week, rules you taught it, facts about the project and the shape of the codebase sit in a local workspace and survive restarts, model upgrades and switching agents. SQLite is the durable source of truth, with rebuildable search indexes next to it. Nothing calls an LLM on the read path.
It installs as an MCP server. Claude and Codex take a single command; Cursor and GitHub Copilot get a JSON block pointing at uvx pmb-ai. Then pmb setup detects your agent and writes the MCP entry, pmb warmup preloads the model so the first recall is instant, and pmb doctor confirms the wiring. Hooks in Claude and Codex inject the right memory before the model starts thinking, so you never have to call a tool by hand. Search is multilingual: a Russian query finds an English fact.
To see what was captured, run pmb dashboard — a local web UI on http://127.0.0.1:8765 with tabs for the entity map, timeline and lessons. It binds to 127.0.0.1 only, so nothing leaves the machine. pmb export dumps everything to Markdown or JSON. Apache 2.0.
What it helps with
- recall an auth decision from an earlier session
- teach the agent a rule it must not break
- locate the file and line behind a bug description
- carry context over when switching agents or models
- export all project memory to Markdown
Example prompts for the agent
- Recall what we decided about auth last week
- Find where the discount threshold is set and show me the line
- Remember: we never drop the threshold below 25%
How to install PMB AI
Platform CLI
claude mcp add pmb-ai -- uvx pmb-aiuvx runs the command named after the package; if the README names another one, use uvx --from pmb-ai <command>
Platform CLI
codex mcp add pmb-ai -- uvx pmb-aiuvx runs the command named after the package; if the README names another one, use uvx --from pmb-ai <command>
Config file
{
"mcpServers": {
"pmb-ai": {
"command": "uvx",
"args": [
"pmb-ai"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from pmb-ai <command>
Config file
{
"servers": {
"pmb-ai": {
"type": "stdio",
"command": "uvx",
"args": [
"pmb-ai"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from pmb-ai <command>
Platform CLI
gemini mcp add pmb-ai uvx pmb-aiuvx runs the command named after the package; if the README names another one, use uvx --from pmb-ai <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 PMB AI
How do I install PMB AI in Claude Code?
Run claude mcp add pmb-ai -- uvx pmb-ai, then pmb setup, pmb warmup and restart your agent. pmb doctor confirms the wiring.
What does PMB AI do?
It keeps decisions, lessons and project structure in a local SQLite database and serves them to your agent over MCP. Memory survives restarts and model changes.
Does it need API keys or a cloud account?
No. Everything stays in a local workspace, the read path makes no LLM call, and there is no account or subscription.
