AgentMemory vs claude-mem

AgentMemory

Agents

claude-mem

Agents

Tagline

AgentMemory

Open-source persistent memory runtime for AI coding agents, with hybrid retrieval and zero external dependencies.

claude-mem

Keeps decisions, discoveries, and fixes from work ready for the next session, machine, and tool.

Pricing

AgentMemory

Free· Free, open-source (Apache 2.0); bring your own LLM API key

claude-mem

Freemium· Open source claude-mem: Free; CMEM Pro: $30/month; Heavy: $70/month; CMEM Max: $100/month

Lowest paid tier

AgentMemory

—

claude-mem

$30/mo · Pro

captured 2026-10-24

Free trial

AgentMemory

Not listed

claude-mem

Yes

API

AgentMemory

Yes

claude-mem

Yes

Platforms

AgentMemory

cliapi

claude-mem

macoslinuxwindows

Open source

AgentMemory

Yes · Apache-2.0

claude-mem

Yes

GitHub stars

AgentMemory

29,984

checked 2026-10-29

claude-mem

—

Last GitHub push

AgentMemory

2026-10-28

claude-mem

—

First commit

AgentMemory

2026-02

claude-mem

—

Package downloads (30 d)

AgentMemory

77,138 · npm @agentmemory/agentmemory

checked 2026-11-07

claude-mem

—

Hacker News stories

AgentMemory

1

checked 2026-11-07

claude-mem

1

checked 2026-10-09

Earliest Wayback capture

AgentMemory

2026-04-19

earliest archived capture of the site, not a launch date

claude-mem

2026-02-01

earliest archived capture of the site, not a launch date

Company

AgentMemory

AgentMemory

claude-mem

—

Model used

AgentMemory

Multi-model (Claude, Gemini, MiniMax, OpenRouter)

claude-mem

Model-agnostic — works with the models used by the connected agent (Claude, GPT, Gemini, etc.) via MCP

Best for

AgentMemory

Pick AgentMemory if you want a drop-in, self-hosted memory layer for your coding agent stack without running a vector DB or graph store.

claude-mem

—

Not for

AgentMemory

Skip it if you need a hosted, multi-tenant memory service with SLAs or a production-grade datastore behind it.

claude-mem

—

Editorial score

AgentMemory

7.3 / 10

claude-mem

—

Use cases

AgentMemory

agent-memorycoding-agentscontext-managementknowledge-graphmcp-server

claude-mem

Searching for past decisions, discoveries, and fixesPicking up work on another machineReturning to the history behind a specific changeRecalling synced memory from MCP clientsCoding, research, and building custom tools

Pros

AgentMemory

• Zero external infrastructure: single Node process, JSON on disk
• Triple-stream retrieval (BM25 + vectors + graph) with sub-20ms recall
• Native plugins for Claude Code, Cursor, Cline, Windsurf, and 15+ agents
• Apache 2.0, runs on your existing LLM subscription
• Strong benchmark numbers (95.2% R@5 on LongMemEval-S)

claude-mem

• The local claude-mem engine is open source.
• Progressive recall allows the agent to find a note before reading its details.
• Cloud sync keeps captured project memory available when moving between connected computers.
• Synced memory can be recalled from MCP clients, including ChatGPT when the account supports custom connectors.

Cons

AgentMemory

• Pre-1.0 (v0.9.27), expect breaking changes
• Single-process JSON storage may not scale to team-wide deployments
• Self-hosted only; you operate the runtime
• Effectiveness depends on the LLM provider you wire in

claude-mem

• The ChatGPT connection does not automatically capture ChatGPT conversations or backfill local-only history.
• A credit or debit card is required for the trial, and prepaid cards are not eligible.

Website

AgentMemory

agent-memory.dev

claude-mem

cmem.ai

Editorial score: rule-based, 0–10, from AI-assisted profile inputs (see /methodology) — not a user rating; “—” means unscored. “Not listed” means we have no record of it, not that it is absent. GitHub figures and prices carry the date they were checked or captured; prices are shown as published, unconverted.