Skip to content
Recall logo

Recall

Stores dated, cited facts about each user from conversations and answers questions about them in one model call.

From $0.00 per useActively maintained

SupportUsage-based pricing
recallmem.dev ↗
Open recallmem.devAlternativesSet it up for my teamIs Recall yours? Claim the card →
At a glanceswept Oct 15, 2026

304 installs/mo

Emerging

For
Developers building AI agents whose users return across several conversations and expect the agent to remember them.
Price
From $0.00 per usepricing page, read Oct 22, 2026
Activity
Actively maintainedrelease 8 days ago
Runs as
APISDK
Used for
  • Keep per-user facts across repeated chat sessions
  • Answer questions about a user from cited past messages
  • Replace outdated facts while keeping their history
read off recallmem.dev on Oct 22, 2026
Worth knowingcomputed from what we read · each with its source
Pricingpricing page, read Oct 22, 2026

From $0.00 per use

pricing page

The companyeach fact with its source · read Oct 22, 2026
Your datawhat they publish, each line with its page · read Oct 22, 2026

“We do not store IP addresses in our database, card details stay with Stripe, the website counts visits with cookieless analytics we host ourselves (see the privacy policy ), and we do not use customer content to train AI models.”

security page ↗

These are Recall's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 22, 2026
  • MCP serverdev.recallmem/memoryverified in the MCP registry
  • Stateanswers, requires sign-inchecked 2026-10-22
  • Address to connectapi.recallmem.dev/mcp

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Supportby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Recall with

Pick up to two.

All 10 alternatives to Recall →

All Support tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Recall for?

Sign in to leave a note
Questions this page answers
  • What is Recall?

    Stores dated, cited facts about each user from conversations and answers questions about them in one model call. It is listed in the Atlas under Support.

  • Who is Recall for?

    Developers building AI agents whose users return across several conversations and expect the agent to remember them.

  • How much does Recall cost?

    Paid plans start at $0.00 per use, per Recall's pricing page on 2026-10-22.

  • Is Recall free?

    No. Its pricing page showed no free plan on 2026-10-22.

  • Do people use Recall?

    Emerging: 304 installs/mo (npm).

  • Is Recall still maintained?

    Actively maintained: release 8 days ago.

  • Does Recall train AI on your data?

    No, per its security page (2026-10-22): “We do not store IP addresses in our database, card details stay with Stripe, the website counts visits with cookieless analytics we host ourselves (see the privacy policy ), and we do not use customer content to train AI models.”

  • Is Recall safe?

    We do not audit vendors. What Recall publishes, read 2026-10-22: GDPR stated on its privacy policy; on training with your data, “We do not store IP addresses in our database, card details stay with Stripe, the website counts visits with cookieless analytics we host ourselves (see the privacy policy ), and we do not use customer content to train AI models.”.

  • What are alternatives to Recall?

    In Support, by use: Ada, Gorgias, Chatbase, Sierra, Maven AGI, Zaro.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk