claude-mem

claude-mem is an open-source memory engine for AI agents that automatically captures, stores, and retrieves session context across multiple devices and clients.

claude-mem is an open-source memory engine that records agent activity as it happens. It functions as a database, vector index, and MCP server, generating observations from agent sessions to build a long-term, searchable history. Users connect it to Claude Code, Cursor, and other MCP clients via a private MCP link to maintain context across sessions. The system operates locally-first using SQLite and provides optional cloud synchronization for cross-device access. It is designed for developers who want their agents to recall past decisions and project architectures without repetitive explanations.

claude-mem at a glance

Best for: Software engineer
Runs on: Web, CLI
Pricing: Engine is free; CMEM Cloud Pro is $30/month for solo developers; Team Cloud is $333/user/month.
Released: August 2025
Category: AI coding tool
Website: claude-mem.ai

Key features

Automatic observation database creation
Local-first SQLite storage
Semantic vector recall
Private MCP link integration
Cross-device memory synchronization
Temporal context management
Per-project memory scopes and isolation

Use it for

Retaining architectural context between coding sessions
Syncing agent memory across multiple machines
Searching past agent decisions and project history
Briefing agents on previous project tasks automatically

Alternatives to claude-mem

memsearch — It shares continuous context across Claude Code, Codex, and other AI coding agents.
memU — It gives every connected agent a shared and inspectable memory layer.
ProjectMem — Records project history locally to prevent AI from repeating failed work.
Memsaga — Keeps git history and two-way sync for Claude Code memory files across machines.
Engram — Single Go binary with zero dependencies and built-in full-text search.
OptMem — Provides permanent agent memory with fast lookups and no background processes.
AgentMemory — It runs locally with zero external databases and achieves high retrieval recall.
Mem0 — It provides drop-in persistent memory for AI agents without changing pipelines.
Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
Claude Context — It reduces token costs and provides deep context for large codebases.
MuscleMemory — It cuts input tokens, tool calls, and execution time while maintaining task success.
AI Memory — Shared memory for coding agents that works across machines and team members.

All claude-mem alternatives