claude-mem vs Stele

claude-mem

Agents

Stele

Agents

Tagline

claude-mem

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

Stele

Shared project memory for AI coding agents across Claude Code, Cursor, Codex, and Copilot

Pricing

claude-mem

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

Stele

Freemium· Free tier · from $5.99/mo

Lowest paid tier

claude-mem

$30/mo · Pro

captured 2026-10-24

Stele

$5.99 / month · Indie

captured 2026-10-28

Free trial

claude-mem

Yes

Stele

Yes

API

claude-mem

Yes

Stele

Yes

Platforms

claude-mem

macoslinuxwindows

Stele

—

Open source

claude-mem

Yes

Stele

Not listed

Hacker News stories

claude-mem

1

checked 2026-10-09

Stele

1

checked 2026-10-21

Earliest Wayback capture

claude-mem

2026-02-01

earliest archived capture of the site, not a launch date

Stele

2026-07-22

earliest archived capture of the site, not a launch date

Model used

claude-mem

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

Stele

—

Best for

claude-mem

—

Stele

Developers and small teams who juggle multiple AI coding agents (Claude Code, Cursor, Codex, Copilot) and want a persistent, shared project memory that survives tool switches and session resets.

Not for

claude-mem

—

Stele

Solo developers who stay inside one agent and one IDE, or enterprises with strict data-residency rules who cannot wait for the self-hosted edition.

Editorial score

claude-mem

—

Stele

—

Use cases

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

Stele

shared memory across AI coding agentscross-tool project context handofftask queue for multi-agent workflowsagent onboarding from an existing codebasetracking failed refactor attemptscoordinating Claude Code and Cursor on one repoMCP-based agent memory backendarchitectural decision log for AI agents

Pros

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.

Stele

• MCP-native, so it works with Claude Code, Cursor, Codex, and Copilot without per-tool adapters
• One-line CLI install with automatic onboarding from an existing repo
• Shared task queue prevents two agents from duplicating the same work
• Graph-based memory captures failed attempts, not just successful ones, so agents stop repeating dead ends
• Free tier is genuinely usable for solo developers (unlimited public projects, one private)
• Self-hosted SQLite edition on the roadmap for teams that need local data
• Export and deletion controls on private project graphs

Cons

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.

Stele

• Currently hosted-only; the promised self-hosted build is not yet shipped
• Value depends on running multiple agents or switching tools often, less compelling for single-agent users
• Shared memory across agents can propagate a bad decision if not curated
• Early-stage product with limited public track record and small community
• Private project quota on the free tier is tight for anyone with several client repos

Website

claude-mem

cmem.ai

Stele

stele-ai.dev

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.