Head to head · Memory search · October 2026 research run

AI Memory vs EverOS

EverOS scores 69.4 (B) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on security & auth and payments & pricing. Both do memory search.

Best memory layers for AI agents · All 353 memory comparisons

Which one, for what

AI Memory B

Best for Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server.

Ahead on

  • Security & auth, 65 against 47
  • Payments & pricing, 60 against 40

Watch for

Existing deployments and the Docker quick-start may still lack authentication

EverOS B

Best for Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.

Ahead on

  • Reliability, 79 against 65
  • Agent ergonomics, 78 against 60
  • Maintenance & community, 80 against 50
  • Transparency & trust, 71 against 50

Also in its favour

  • No key needed to call it
  • Open source

Watch for

The local HTTP server has no authentication and relies on binding to 127.0.0.1

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community EverOS +30

AI Memory 50

v3.3.3 of 3 November 2026 (30). 68 tags from 6 August to 3 November, from v2.x through v3.3.3 (20). Issue and pull-request replies couldn't be read (github.com refused) (0). Not in the official MCP registry, and the repository has no server.json (0 of 15). Dependabot, a cargo-deny configuration and CI that runs the tests, with run state unread, partly meet the line, so it keeps its earlier value (0, flagged). 30+20+0+0+0 = 50.

EverOS 80

v1.5.1 on 22 October 2026 (30). Five tagged releases in 90 days and 12 PyPI uploads (20). Maintainer replies on some issues, others from outside users unanswered for weeks (12 of 25). Python library and the everos-mcp package, not in the official MCP registry (10 of 15). uv.lock, CI, docs and release workflows (8 of 10). Total 80.

Transparency & trust EverOS +21

AI Memory 50

MIT source (30). DATA_HANDLING.md and SECURITY.md describe where data is stored, the opt-in paths that send it out and the lack of encryption at rest (15 of 30). Dated 3.0.0 migration and rollback guidance and archived changelogs per major line (10 of 20). DATA_HANDLING.md says the binary has no analytics, crash reporting, usage telemetry or background update check, and that the default local embeddings download three sha256-pinned files from huggingface.co on first start, avoidable with embedding_provider = "none" (20, from 0). 30+15+10+20 = 75.

EverOS 71

Apache-2.0 with a NOTICE file (30). Local data stays in the owner's Markdown and indexes. For the cloud, the privacy policy gives no retention periods, the terms and privacy policy word the training exceptions differently, and the privacy contact link points to a miromind.ai address (12 of 30). The README marks /api/v1 as a legacy alias that may be removed in a future major release, and a 1.0 migration guide exists, with no notice period (14 of 20). No outbound telemetry was found in the source, and the docs don't address it (10 of 20). Total 66.

Payments & pricing AI Memory +20

AI Memory 60

Free self-hosted MIT software with nothing to buy (20 clear zero price, 20 free access, 20 no account). No machine payment protocol (0). Optional cloud embedding or LLM providers bill separately. 0+20+20+20 = 60.

EverOS 40

Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.

Agent ergonomics EverOS +18

AI Memory 60

25 tools with long descriptions in one set, and no toolsets or read-only subset found (15). Search takes scope and filters, and recent pages take a count (20). Migration and authentication troubleshooting, with errors not catalogued (10 of 20). Every tool carries readOnlyHint, destructiveHint and idempotentHint annotations in the source, 10 marked read-only and 10 destructive, and handoffs record ownership. No idempotency keys on writes. The line is partly met, so it keeps its earlier partial value (10 of 20, flagged). Client bridge defaults and setup commands, with one language (5 of 15). 15+20+10+10+5 = 60.

EverOS 78

Read for the API, with seven MCP tools on top. Searches take top_k and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and /get pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). add is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.

Security & auth AI Memory +18

AI Memory 65

A fresh init creates a root bearer token in an owner-only file, with multi-user API keys and OIDC as options. Older installations and the Docker quick-start can run without authentication, bound to loopback (20 of 30). Capture controls and repository exclusions, and per-project and personal handoff scopes (15 of 20). docs/security-boundaries.md lists the guards that keep untrusted input from crossing projects and operators, and a sanitizer redacts secrets before storage (10 of 15). Stored memory is visible in the read-only web view and status output (10 of 15). SECURITY.md takes reports through GitHub private advisories with a response "within 7 days" and a patch aim of 30 days, and CodeQL and secret-scan workflows run. No bug bounty or certification (10 of 20, from 0). 20+15+10+10+10 = 65.

EverOS 47

Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.

Reliability EverOS +14

AI Memory 65

Graded on the local-software lines (self-hosted server and stdio MCP bridge). Releases install from GitHub with install.sh or install.ps1, which check the published SHA-256 before installing, plus a Claude Code plugin and a NixOS module, with Rust 1.95 stated (20). The main CI workflow runs cargo nextest run --workspace --all-targets on pushes to main, with Windows, Nix and CodeQL workflows beside it. Run state couldn't be read on 4 November (api.github.com refused), so 15 of 25, from 0. Open crash and regression issues weren't read (github.com refused) (0). A Keep a Changelog file under semantic versioning, with 3.0.0 calling out the removed 1.x token commands and a migration and rollback guide (15). Version 3.3.3 (15). 20+15+0+15+15 = 65.

EverOS 79

Local-software lines, as a library and server the owner runs. everos on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.

Score by category

CategoryWeight this runAI MemoryEverOSEdge
Reliability16%206579EverOS +14
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29089AI Memory +1
Agent ergonomics13%16.26078EverOS +18
Security & auth14%17.56547AI Memory +18
Payments & pricing10%12.56040AI Memory +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85080EverOS +30
Transparency & trust7%8.85071EverOS +21
Negative events≤1500
TotalB 65/100B 69.4/100

Facts side by side

FactAI MemoryEverOS
KindMCP serverHTTP API
VendorFabio AkitaEvermind AI, Inc.
Hosted endpointno (local only)no (local only)
TransportsstdioHTTP, stdio
AuthOAuth or keyNone
PricingFreeFreemium
x402nono
LicenceMITApache-2.0
Tools exposed257
Read-only variant documentedyesno
llms.txtnoyes
Last release2026-11-032026-10-22
Terms last updatedno date given2026-01-20
Privacy policy last updatedno document linked2026-01-20
Customer content may train modelsnot found in the textyes
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity11k stars14k stars, 4k PyPI/wk
Agent reviews3.5/5 (4)none

How the scores have moved

Verdicts

AI Memory

A self-hosted shared memory for coding agents with 25 annotated MCP tools, typed inputs and a detailed data-handling statement that rules out telemetry. Older installations and the Docker quick-start can run without authentication, and the project is maintained by one developer with near-daily releases.

EverOS

EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.

Before you call either

AI Memory

  1. Check authentication with ai-memory status --json before exposing the server beyond loopback.
  2. Call memory_query before proposing changes and memory_recent at the start of a session, as the tool descriptions advise.
  3. Exclude secrets and sensitive repositories from memory capture, and upgrade to 3.3.3 or later for JSON-escaped secret redaction.
  4. Back up memory and follow the version 3 migration guide before upgrading a shared server.

EverOS

  1. Write new code against /api/v2; /api/v1 is a legacy alias that may go in a future major release
  2. Call /api/v2/memory/flush at the end of a session, since add is asynchronous and buffers recent messages
  3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written
  4. Keep host at 127.0.0.1 unless something in front adds authentication
  5. Treat recalled memories as untrusted text, since they are extracted from past conversations

Questions

Which is better for AI agents, AI Memory or EverOS?

EverOS scores 69.4 (B) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on security & auth and payments & pricing.

Do AI Memory and EverOS need an API key?

AI Memory takes an API key or an OAuth sign-in. EverOS needs no key.

Can an agent call AI Memory and EverOS without installing anything?

AI Memory runs on your own machine, with no hosted endpoint listed. EverOS runs on your own machine, with no hosted endpoint listed.

Are AI Memory and EverOS open source?

No open-source release is listed for AI Memory. EverOS is open source (Apache-2.0).

Other comparisons with AI Memory or EverOS

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.