Skip to main content
MCP server CX Codex

agentmem · oxgeneral — Claude Code MCP server: what it does, how to install

Keeps long-term agent memory inside a single SQLite database using hybrid search. It saves facts, decisions, and rules across sessions.

Open on GitHub

What agentmem does

The server stores persistent context inside a single SQLite database file. Queries run on a hybrid engine. It pairs FTS5 keyword matching with vector embeddings, applying recency weighting to keep fresh facts on top. Namespaces isolate data across projects, and five memory tiers classify everything from permanent setup details to temporary notes.

The package exposes 16 MCP tools alongside an HTTP REST service with 14 endpoints. It scans dialogue turns to pull out decisions, IP addresses, URLs, and environment variables without manual formatting. Fact updates stay auditable through revision chains, while near-duplicate entries merge using the consolidate tool.

Running it requires Python. The complete setup with vector search takes 12MB, but it can also operate purely on standard library modules without extra dependencies. Memory marked as learned or episodic auto-compacts after 90 days, so keep non-expiring rules strictly in the core tier.

What it helps with

  • persist working state and decisions between chat sessions
  • pass behavioral rules into system prompts via get_procedures
  • search stored memories using hybrid keyword and semantic ranking
  • extract IP addresses, URLs, and action items from conversation logs
  • merge duplicate memory records with consolidate

Example prompts for the agent

  • Remember in the core tier under namespace infra that our production server IP is 10.0.0.1.
  • Use recall to find our earlier decisions about database indexing.
  • Run save_state to store my current progress before context compression happens.

How to install agentmem

Install

The MCP registry has no launch command for it: see the repository README

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 agentmem

How do I install agentmem for Claude Code?

Install the package with pip install agentmem-lite[all]. Then register the server in your MCP configuration using command python with arguments ["-m", "agentmem", "--db", "/path/to/memory.db"].

What does agentmem do?

It gives AI agents persistent memory in an SQLite file so facts and instructions survive session resets. It combines keyword and semantic search, isolates memories with namespaces, and provides 16 MCP tools.

How do agentmem memory tiers work?

The core and procedural tiers never auto-expire, making them suitable for permanent facts and system prompt rules. In contrast, entries in the learned and episodic tiers are archived automatically after 90 days.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

agentmem by other authors comes first.

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor