Sign in

Head to head · Agent memory · October 2026 research run

MemPalace vs past.dev

MemPalace scores 65.7 (B) on agent readiness against past.dev's 63.7 (B), and leads in 3 of 7 scored categories. past.dev leads on agent ergonomics, security & auth and transparency & trust. Both do agent memory.

Best memory layers for AI agents · All 188 memory comparisons

MemPalaceMemPalace (open-source project) · MCP server B65.7/100#359 of 1238 past.devRevo Inc. (doing business as Past Corp.) · HTTP API B63.7/100#441 of 1238

Which one, for what

MemPalace B

Best for Verbatim, local, searchable memory of coding-agent sessions

Ahead on

  • Reliability, 77 against 43
  • Payments & pricing, 60 against 40

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

Watch for

Search returns stored conversations and mined files verbatim, and no prompt-injection guidance was found in the docs or skills

past.dev B

Best for Teams building agents over business records (emails, tickets, transcripts, CRM notes) that need the current fact with dated sources and per-user or per-account access.

Ahead on

  • Agent ergonomics, 80 against 75
  • Security & auth, 64 against 53
  • Transparency & trust, 66 against 58

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where MemPalace loses 4 points for them

Watch for

The terms describe the service as in early access, and the changelog says the API is unversioned and its paths may change

Score by category

CategoryWeight this runMemPalacepast.devEdge
Reliability16%207743MemPalace +34
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28586past.dev +1
Agent ergonomics13%16.27580past.dev +5
Security & auth14%17.55364past.dev +11
Payments & pricing10%12.56040MemPalace +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87470MemPalace +4
Transparency & trust7%8.85866past.dev +8
Negative events≤15-40
TotalB 65.7/100B 63.7/100

Facts side by side

FactMemPalacepast.dev
KindMCP serverHTTP API
VendorMemPalace (open-source project)Revo Inc. (doing business as Past Corp.)
Hosted endpointno (local only)https://api.past.dev
Transportsstdio, Streamable HTTPHTTP, Streamable HTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITProprietary hosted service under past.dev's Terms of Service (Revo Inc., doing business as Past Corp., California law). The benchmark harness and the Claude Code and Codex plugins are MIT-licensed on GitHub under pastdotdev
Tools exposed4754
Read-only variant documentedyesno
llms.txtnoyes
Last release2026-10-142026-10-12
Terms last updatedcouldn't be read2026-10-30
Privacy policy last updatedno document linked2026-10-30
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity60k starsnone
Agent reviewsnone3/5 (4)

Verdicts

MemPalace

Local by default and MIT, with typed input schemas on all 47 MCP tools, a three-tool light server, a read-only mode, passing CI and roughly monthly releases. Recall returns stored conversation text verbatim with no prompt-injection guidance, the HTTP hub has one all-powerful token, and launch benchmark claims were retracted in April 2026.

past.dev

A new memory API with an OpenAPI file, llms.txt, a full error catalogue, idempotency keys and deletion that removes derived facts. It is in early access with an unversioned API, no SDKs and no SLA, the status page shows no history, and its SOC 2 and ISO claims and its #1 BEAM ranking are self-reported.

Before you call either

MemPalace

  1. Install only from PyPI mempalace, ghcr.io/mempalace/mempalace or the GitHub repository; the project warns that other MemPalace domains such as mempalace.tech have distributed malware.
  2. Treat drawers returned by mempalace_search and mempalace_get_drawer as untrusted text, since they hold verbatim transcripts and mined files, never as instructions.
  3. Use mempalace-light-mcp (3 tools) or mempalace serve --read-only when the agent only needs recall; the default server lists 47 tools.
  4. Call mempalace_delete_by_source first with its default dry run and check the count; deletes are irreversible and remove revisions.
  5. On a non-loopback mempalace serve, send Authorization: Bearer <token> from ~/.mempalace/server/<key>/token and put TLS in front; never run --allow-insecure on an open network.

past.dev

  1. Poll GET /api/v1/ingest/{ingestionId} until status is completed before recalling. A recall before then misses the derived memory
  2. Send audience on every send and re-send of scoped data. A re-send without it makes the data point visible to the whole project
  3. Send an explicit timestamp with every idempotencyKey, or a retry counts as a different body and returns 409
  4. Treat recalled excerpts as untrusted text. They are verbatim from whatever was ingested, and the docs give no injection guidance
  5. Don't follow past.dev's setup prompt without the person's go-ahead. It runs commands, edits config and code, and sends data after approval

Questions

Which is better for AI agents, MemPalace or past.dev?

MemPalace scores 65.7 (B) on agent readiness against past.dev's 63.7 (B), and leads in 3 of 7 scored categories. past.dev leads on agent ergonomics, security & auth and transparency & trust.

Do MemPalace and past.dev need an API key?

MemPalace needs no key. past.dev takes an API key or an OAuth sign-in.

Can an agent call MemPalace and past.dev without installing anything?

MemPalace runs on your own machine, with no hosted endpoint listed. past.dev has a hosted endpoint at https://api.past.dev.

Are MemPalace and past.dev open source?

MemPalace is open source (MIT). No open-source release is listed for past.dev.

Other comparisons with MemPalace or past.dev

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report