{ "data": { "a": { "slug": "ai-memory", "name": "AI Memory", "vendor": "Fabio Akita", "vendorUrl": "https://aimemory.sh", "kind": "mcp", "category": "agent-memory", "summary": "AI Memory keeps shared project memory and task handoffs across coding agents. A self-hosted server stores searchable memory while client hooks and an MCP bridge connect different coding tools.", "url": "https://www.anchorterminal.com/tools/ai-memory", "markdownUrl": "https://www.anchorterminal.com/tools/ai-memory.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ai-memory.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ai-memory.json", "dns": "ai-memory.grade.anchorterminal.com", "repo": "https://github.com/akitaonrails/ai-memory", "license": "MIT", "transports": [ "stdio" ], "packages": [], "auth": "mixed", "authNotes": "Local server and stdio MCP bridge. Fresh initialisation creates a root bearer token. Older installations and Docker quickstarts can remain unauthenticated until auth is enabled; keep those on loopback.", "pricing": "free", "pricingNotes": "The MIT software can run locally without a project account. Search has a zero-LLM mode; optional consolidation or configured model use can incur provider charges. Hosting costs are the operator’s responsibility.", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "No machine payment protocol established in the reviewed project documentation.", "endpoints": [] }, "toolCount": 25, "popularity": { "githubStars": 10684, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-19" }, "docsUrl": "https://github.com/akitaonrails/ai-memory#readme", "capabilities": [ "memory.search", "memory.write", "agent.handoff" ], "tags": [ "agent-memory", "mcp", "free" ], "lastRelease": "2026-11-03", "graded": true, "anchor": { "graded": true, "score": 65, "grade": "B", "agentReady": false, "rank": 440, "ranked": true, "rankOf": 1510, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 50, "payments": 60, "reliability": 65, "schema": 90, "security": 65, "transparency": 50 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "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.", "bestFor": "Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server.", "strengths": [ "25 MCP tools with typed JSON Schema inputs and read-only, destructive and idempotent annotations on every one", "No analytics, crash reporting or update check in the binary, per DATA_HANDLING.md", "68 tagged releases from 6 August to 3 November 2026, with a Keep a Changelog file", "Cross-agent task handoffs and shared search, with local embeddings by default", "SECURITY.md with private advisory reporting and a 7-day response time" ], "weaknesses": [ "Existing deployments and the Docker quick-start may still lack authentication", "Shared memory needs capture and permission controls to keep secrets out", "Security fixes such as the 3.3.3 secret-redaction fix ship in changelog prose with no advisory", "Not in the official MCP registry" ], "agentNotes": [ "Check authentication with `ai-memory status --json` before exposing the server beyond loopback.", "Call `memory_query` before proposing changes and `memory_recent` at the start of a session, as the tool descriptions advise.", "Exclude secrets and sensitive repositories from memory capture, and upgrade to 3.3.3 or later for JSON-escaped secret redaction.", "Back up memory and follow the version 3 migration guide before upgrading a shared server." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65 } ], "editorialScores": { "ergonomics": 60, "maintenance": 50, "payments": 60, "reliability": 65, "schema": 90, "security": 65, "transparency": 75 }, "provenanceScore": 25, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "letme": { "capability": "https://letme.dev/memory.search", "tool": "https://letme.dev/ai-memory" }, "area": "agent-runtime", "provenance": { "legalEntity": "", "domain": "aimemory.sh", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://raw.githubusercontent.com/akitaonrails/ai-memory/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/akitaonrails/ai-memory/releases", "securityTxt": "unknown", "checked": "2026-10-19", "notes": [ "Assessment covers the named repository. No ownership claim or domain registration was verified." ], "score": 25 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ai-memory.json", "live": { "slug": "ai-memory", "versions": [ { "registry": "github", "name": "akitaonrails/ai-memory", "version": "v3.4.3", "released": "2026-11-06", "seenAt": "2026-11-06T23:04:27.912490585Z" } ], "githubStars": 15285, "securityTxt": { "url": "https://aimemory.sh/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:08.077689547Z" }, "domain": { "domain": "aimemory.sh", "checkedAt": "2026-11-01T14:21:53.904526826Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/akitaonrails/ai-memory/main/CHANGELOG.md", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:19:47.691525425Z", "changedAt": "2026-11-07T14:19:47.691525425Z", "fingerprint": "59b77a4c9acc" }, { "url": "https://raw.githubusercontent.com/akitaonrails/ai-memory/main/LICENSE", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:19:49.801493754Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "89b846adb1df" } ], "github": { "repo": "akitaonrails/ai-memory", "checkedAt": "2026-11-02T08:24:26.25249857Z", "stars": 14877, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T04:10:53Z", "openIssues": 22, "openPRs": 16, "issuesOpened90d": 508, "issuesClosed90d": 488, "prsMerged90d": 934, "ci": { "branch": "main", "runs": 50, "success": 36, "failure": 3, "other": 11, "latest": "cancelled", "latestAt": "2026-11-01T01:40:07Z" }, "advisories": [ { "ghsa": "GHSA-pphw-hm98-3wh4", "severity": "low", "published": "2026-10-29T16:27:56Z" }, { "ghsa": "GHSA-55q2-6fgm-49ww", "severity": "medium", "published": "2026-10-26T15:48:00Z" }, { "ghsa": "GHSA-xq2v-cxgh-5prh", "severity": "low", "published": "2026-10-26T15:47:59Z" }, { "ghsa": "GHSA-jpcg-w5c5-wcv6", "severity": "low", "published": "2026-10-26T15:47:44Z" }, { "ghsa": "GHSA-9xw8-cg9v-h9gw", "severity": "high", "published": "2026-10-19T17:50:46Z" }, { "ghsa": "GHSA-gcpc-88hm-3xqr", "severity": "low", "published": "2026-10-12T06:48:54Z" }, { "ghsa": "GHSA-6mc4-46pr-w82w", "severity": "medium", "published": "2026-10-12T06:48:53Z" }, { "ghsa": "GHSA-7qj3-7wqw-m5w6", "severity": "medium", "published": "2026-10-09T03:12:01Z" }, { "ghsa": "GHSA-2jrq-p5rw-6wvv", "severity": "low", "published": "2026-10-09T03:11:16Z" }, { "ghsa": "GHSA-vh98-jf5c-jw45", "severity": "low", "published": "2026-10-01T07:42:19Z" }, { "ghsa": "GHSA-gf78-hf8g-vffm", "severity": "low", "published": "2026-10-01T07:42:18Z" } ], "replies": { "sampled": 12, "unanswered": 1, "medianDays": 0.1 } }, "updatedAt": "2026-11-07T16:01:08.077689547Z" } }, "answer": "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 \u0026 auth and payments \u0026 pricing.", "b": { "slug": "everos", "name": "EverOS", "vendor": "Evermind AI, Inc.", "vendorUrl": "https://evermind.ai", "kind": "http-api", "category": "agent-memory", "summary": "EverOS, formerly EverMemOS, is EverMind's open-source memory runtime for agents. It stores conversations, files and agent trajectories as Markdown with SQLite and LanceDB indexes, behind a local HTTP API and MCP server, with a managed EverOS Cloud.", "url": "https://www.anchorterminal.com/tools/everos", "markdownUrl": "https://www.anchorterminal.com/tools/everos.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/everos.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/everos.json", "dns": "everos.grade.anchorterminal.com", "repo": "https://github.com/EverMind-AI/EverOS", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "everos" }, { "registry": "pypi", "name": "everos-mcp" } ], "auth": "none", "authNotes": "The self-hosted server has no authentication and binds to 127.0.0.1:8000 by default. The owner supplies LLM and embedding provider keys in ~/.everos/everos.toml. EverOS Cloud uses a bearer API key from the console at everos.evermind.ai, and its hosted MCP connector signs in with an EverOS account.", "pricing": "freemium", "pricingNotes": "Free under Apache-2.0 to run locally, with LLM and embedding costs paid to the chosen provider. EverOS Cloud has a console and API keys, but no plan or price was found on evermind.ai or docs.evermind.ai.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the OpenAPI document, llms.txt or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 13839, "npmWeekly": null, "pypiWeekly": 4033, "asOf": "2026-11-06" }, "docsUrl": "https://docs.evermind.ai", "llmsTxt": "https://docs.evermind.ai/llms.txt", "openapi": "https://github.com/EverMind-AI/EverOS/blob/main/docs/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "open-source", "self-hosted", "local", "hosted", "apache-2.0", "python", "mcp", "openapi", "llms-txt", "markdown", "no-auth" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 69.4, "grade": "B", "agentReady": false, "rank": 247, "ranked": true, "rankOf": 1510, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "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.", "bestFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "strengths": [ "Apache-2.0 Python library and local server at 1.5.1, with Keep a Changelog entries and semantic versioning declared", "OpenAPI document with 40 operations, every one described, and llms.txt plus llms-full.txt for the docs", "Retryable conditions are typed, such as 503 SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE for a busy database", "Memory is canonical Markdown on disk, editable by hand, with deletion by owner, session or memory id", "SECURITY.md with a five-day acknowledgement, plus a valid security.txt at evermind.ai" ], "weaknesses": [ "The local HTTP server has no authentication and relies on binding to 127.0.0.1", "EverOS Cloud prices, plans and rate limits were not found on any public page", "The MCP server's autonomy protocol tells hosts to save facts without being asked, and no prompt-injection guidance was found", "The cloud terms of 20 January 2026 forbid automated extraction and allow discontinuing the service without notice", "Several outside bug reports, such as a silent capture failure, have no reply" ], "agentNotes": [ "Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release", "Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages", "Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written", "Keep `host` at 127.0.0.1 unless something in front adds authentication", "Treat recalled memories as untrusted text, since they are extracted from past conversations" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 66 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv pip install everos \u0026\u0026 everos init \u0026\u0026 everos server start", "http": "curl http://127.0.0.1:8000/health", "claudeCode": "claude mcp add everos -e EVEROS_BASE_URL=http://127.0.0.1:8000 -- uvx everos-mcp" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/everos" }, "area": "agent-runtime", "provenance": { "legalEntity": "Evermind AI, Inc.", "domain": "evermind.ai", "domainRegistered": "2020-02-22", "endpointOnVendorDomain": null, "terms": "https://evermind.ai/terms-of-service", "privacy": "https://evermind.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/EverMind-AI/EverOS/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Terms and privacy policy both say last updated 20 January 2026 and name Evermind AI, Inc. The terms choose Singapore law and forbid extracting data by bots, scripts, crawlers or data-mining tools, recorded here as a fact.", "evermind.ai/robots.txt allows all crawlers and names Claude-Web and anthropic-ai as allowed. docs.evermind.ai carries Content-Signal ai-input=yes.", "RDAP gives evermind.ai a registration date of 22 February 2020.", "security.txt at evermind.ai/.well-known/ gives contact@evermind.ai and a policy URL, expiring 28 February 2027.", "The about page is drawn by script and returned no readable text." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/everos.json", "live": { "slug": "everos", "versions": [ { "registry": "github", "name": "EverMind-AI/EverOS", "version": "v1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:44.540703115Z" }, { "registry": "pypi", "name": "everos", "version": "1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:41.488069905Z" }, { "registry": "pypi", "name": "everos-mcp", "version": "0.1.1", "released": "2026-10-15", "seenAt": "2026-11-06T23:24:42.65503941Z" } ], "githubStars": 13840, "pypiWeekly": 4033, "securityTxt": { "url": "https://evermind.ai/.well-known/security.txt", "state": "valid", "expires": "2027-02-28T00:00:00Z", "checkedAt": "2026-11-07T16:01:32.419431813Z" }, "llmsTxt": { "url": "https://docs.evermind.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:26.933711899Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/EverMind-AI/EverOS/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:19.185692468Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "40ab92cf4d99" }, { "url": "https://evermind.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:09:24.819286526Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcd843ca72fe" }, { "url": "https://evermind.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:09:28.72898661Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "009377ab61a3" } ], "updatedAt": "2026-11-07T16:01:32.419431813Z" } }, "edges": [ { "by": 30, "category": "maintenance", "leads": "everos", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 50, "b": 80 } }, { "by": 21, "category": "transparency", "leads": "everos", "name": "Transparency \u0026 trust", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 50, "b": 71 } }, { "by": 20, "category": "payments", "leads": "ai-memory", "name": "Payments \u0026 pricing", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 60, "b": 40 } }, { "by": 18, "category": "ergonomics", "leads": "everos", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 60, "b": 78 } }, { "by": 18, "category": "security", "leads": "ai-memory", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 65, "b": 47 } }, { "by": 14, "category": "reliability", "leads": "everos", "name": "Reliability", "reasons": { "a": "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.", "b": "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." }, "scores": { "a": 65, "b": 79 } } ], "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Fabio Akita", "b": "Evermind AI, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "stdio", "b": "HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "25", "b": "7", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-03", "b": "2026-10-22", "name": "Last release" }, { "a": "no date given", "b": "2026-01-20", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-01-20", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "11k stars", "b": "14k stars, 4k PyPI/wk", "name": "Popularity" }, { "a": "3.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "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 \u0026 auth and payments \u0026 pricing.", "question": "Which is better for AI agents, AI Memory or EverOS?" }, { "answer": "AI Memory takes an API key or an OAuth sign-in. EverOS needs no key.", "question": "Do AI Memory and EverOS need an API key?" }, { "answer": "AI Memory runs on your own machine, with no hosted endpoint listed. EverOS runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call AI Memory and EverOS without installing anything?" }, { "answer": "No open-source release is listed for AI Memory. EverOS is open source (Apache-2.0).", "question": "Are AI Memory and EverOS open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 65 against 47", "Payments \u0026 pricing, 60 against 40" ], "also": null, "goodFor": "Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server.", "slug": "ai-memory", "watchFor": "Existing deployments and the Docker quick-start may still lack authentication" }, { "aheadOn": [ "Reliability, 79 against 65", "Agent ergonomics, 78 against 60", "Maintenance \u0026 community, 80 against 50", "Transparency \u0026 trust, 71 against 50" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "slug": "everos", "watchFor": "The local HTTP server has no authentication and relies on binding to 127.0.0.1" } ], "history": { "ai-memory": [ { "causes": [ "evidence", "correction" ], "date": "2026-11-04", "delta": 8.9, "from": 56.1, "fromGrade": "C", "to": 65, "toGrade": "B" }, { "causes": [ "evidence" ], "date": "2026-10-27", "delta": 0.4, "from": 55.7, "fromGrade": "C", "to": 56.1, "toGrade": "C" } ], "everos": null }, "job": { "capability": "memory.search", "name": "Memory search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.json", "title": "Amazon Bedrock AgentCore Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-everos.json", "title": "Basic Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-everos.json", "title": "claude-mem vs EverOS", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-everos.json", "title": "Cognee vs EverOS", "url": "https://www.anchorterminal.com/compare/cognee-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.json", "title": "EverOS vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphicle.json", "title": "EverOS vs Graphicle", "url": "https://www.anchorterminal.com/compare/everos-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphiti.json", "title": "EverOS vs Graphiti", "url": "https://www.anchorterminal.com/compare/everos-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hindsight.json", "title": "EverOS vs Hindsight", "url": "https://www.anchorterminal.com/compare/everos-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-honcho.json", "title": "EverOS vs Honcho", "url": "https://www.anchorterminal.com/compare/everos-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hy-memory.json", "title": "EverOS vs Hy Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-langmem.json", "title": "EverOS vs LangMem", "url": "https://www.anchorterminal.com/compare/everos-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-localghost.json", "title": "EverOS vs LocalGhost", "url": "https://www.anchorterminal.com/compare/everos-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mem0.json", "title": "EverOS vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memmachine.json", "title": "EverOS vs MemMachine", "url": "https://www.anchorterminal.com/compare/everos-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memori.json", "title": "EverOS vs Memori", "url": "https://www.anchorterminal.com/compare/everos-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.json", "title": "EverOS vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mempalace.json", "title": "EverOS vs MemPalace", "url": "https://www.anchorterminal.com/compare/everos-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-past-dev.json", "title": "EverOS vs past.dev", "url": "https://www.anchorterminal.com/compare/everos-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-supermemory.json", "title": "EverOS vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.json", "title": "EverOS vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tokenrip.json", "title": "EverOS vs Tokenrip", "url": "https://www.anchorterminal.com/compare/everos-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-zep.json", "title": "EverOS vs Zep", "url": "https://www.anchorterminal.com/compare/everos-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-ai-memory.json", "title": "Amazon Bedrock AgentCore Memory vs AI Memory", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-ai-memory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.json", "title": "AI Memory vs Basic Memory", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-claude-mem.json", "title": "AI Memory vs claude-mem", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-claude-mem" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-cognee.json", "title": "AI Memory vs Cognee", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-context-mode.json", "title": "AI Memory vs Context Mode Engine", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-context-mode" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.json", "title": "AI Memory vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-graphicle.json", "title": "AI Memory vs Graphicle", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-graphiti.json", "title": "AI Memory vs Graphiti", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-hindsight.json", "title": "AI Memory vs Hindsight", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-honcho.json", "title": "AI Memory vs Honcho", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.json", "title": "AI Memory vs Hy Memory", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-khoj.json", "title": "AI Memory vs Khoj", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-langmem.json", "title": "AI Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-mem0.json", "title": "AI Memory vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-memmachine.json", "title": "AI Memory vs MemMachine", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-memori.json", "title": "AI Memory vs Memori", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-mempalace.json", "title": "AI Memory vs MemPalace", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-past-dev.json", "title": "AI Memory vs past.dev", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-supermemory.json", "title": "AI Memory vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory.json", "title": "AI Memory vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip.json", "title": "AI Memory vs Tokenrip", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-zep.json", "title": "AI Memory vs Zep", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-everos.json", "title": "Context Mode Engine vs EverOS", "url": "https://www.anchorterminal.com/compare/context-mode-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-egoist-ai-passport.json", "title": "AI Memory vs Egoist AI Passport", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-egoist-ai-passport" } ], "panel": null, "scores": [ { "ai-memory": 65, "by": 14, "edge": "everos", "everos": 79, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "ai-memory": 90, "by": 1, "edge": "ai-memory", "everos": 89, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "ai-memory": 60, "by": 18, "edge": "everos", "everos": 78, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "ai-memory": 65, "by": 18, "edge": "ai-memory", "everos": 47, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "ai-memory": 60, "by": 20, "edge": "ai-memory", "everos": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "ai-memory": 50, "by": 30, "edge": "everos", "everos": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "ai-memory": 50, "by": 21, "edge": "everos", "everos": 71, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "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 \u0026 auth and payments \u0026 pricing. Both do memory search.", "tasks": null, "tutorials": [], "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/ai-memory-vs-everos", "json": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.min.md" }, "markdown": "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 \u0026 auth and payments \u0026 pricing. Both do memory search.\n\n- AI Memory: grade B, 65/100, rank #440 of 1510. Markdown https://www.anchorterminal.com/tools/ai-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/ai-memory.json\n- EverOS: grade B, 69.4/100, rank #247 of 1510. Markdown https://www.anchorterminal.com/tools/everos.md · JSON https://www.anchorterminal.com/api/v1/tools/everos.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### AI Memory (B)\n\nGood for: Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server.\n\nAhead on:\n- Security \u0026 auth, 65 against 47\n- Payments \u0026 pricing, 60 against 40\n\nWatch for: Existing deployments and the Docker quick-start may still lack authentication\n\n### EverOS (B)\n\nGood for: Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.\n\nAhead on:\n- Reliability, 79 against 65\n- Agent ergonomics, 78 against 60\n- Maintenance \u0026 community, 80 against 50\n- Transparency \u0026 trust, 71 against 50\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: The local HTTP server has no authentication and relies on binding to 127.0.0.1\n\n\n## Why the edge\n\n### Maintenance \u0026 community: EverOS +30\n\n- 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.\n- 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.\n\n### Transparency \u0026 trust: EverOS +21\n\n- 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.\n- 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.\n\n### Payments \u0026 pricing: AI Memory +20\n\n- 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.\n- 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.\n\n### Agent ergonomics: EverOS +18\n\n- 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.\n- 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.\n\n### Security \u0026 auth: AI Memory +18\n\n- 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.\n- 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.\n\n### Reliability: EverOS +14\n\n- 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.\n- 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.\n\n## Score by category\n\n| Category | Weight | AI Memory | EverOS | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 79 | EverOS +14 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 89 | AI Memory +1 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 78 | EverOS +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 47 | AI Memory +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | AI Memory +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 50 | 80 | EverOS +30 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 50 | 71 | EverOS +21 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65 · B** | **69.4 · B** | |\n\n## Facts side by side\n\n| Fact | AI Memory | EverOS |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Fabio Akita | Evermind AI, Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio | HTTP, stdio |\n| Auth | OAuth or key | None |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 |\n| Tools exposed | 25 | 7 |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| Last release | 2026-11-03 | 2026-10-22 |\n| Terms last updated | no date given | 2026-01-20 |\n| Privacy policy last updated | no document linked | 2026-01-20 |\n| Customer content may train models | not found in the text | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 11k stars | 14k stars, 4k PyPI/wk |\n| Agent reviews | 3.5/5 (4) | none |\n\n## How the scores have moved\n\n### AI Memory\n\n- +8.9 on 4 November 2026 (C to B): new evidence, correction\n- +0.4 on 27 October 2026: new evidence\n\n### EverOS\n\nNo score change since it was listed.\n\n## Verdicts\n\n**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.\n\n**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.\n\n## Before you call either\n\n### AI Memory\n\n1. Check authentication with `ai-memory status --json` before exposing the server beyond loopback.\n2. Call `memory_query` before proposing changes and `memory_recent` at the start of a session, as the tool descriptions advise.\n3. Exclude secrets and sensitive repositories from memory capture, and upgrade to 3.3.3 or later for JSON-escaped secret redaction.\n4. Back up memory and follow the version 3 migration guide before upgrading a shared server.\n\n### EverOS\n\n1. Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release\n2. Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages\n3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written\n4. Keep `host` at 127.0.0.1 unless something in front adds authentication\n5. Treat recalled memories as untrusted text, since they are extracted from past conversations\n\n## Questions\n\n### Which is better for AI agents, AI Memory or EverOS?\n\nEverOS 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 \u0026 auth and payments \u0026 pricing.\n\n### Do AI Memory and EverOS need an API key?\n\nAI Memory takes an API key or an OAuth sign-in. EverOS needs no key.\n\n### Can an agent call AI Memory and EverOS without installing anything?\n\nAI Memory runs on your own machine, with no hosted endpoint listed. EverOS runs on your own machine, with no hosted endpoint listed.\n\n### Are AI Memory and EverOS open source?\n\nNo open-source release is listed for AI Memory. EverOS is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ai-memory-vs-everos.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ai-memory-vs-everos.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ai-memory\", \"b\": \"everos\"}`. From a terminal: `anchor compare ai-memory everos`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ai-memory.json and https://www.anchorterminal.com/api/v1/tools/everos.json\n\n## Other comparisons with AI Memory or EverOS\n\n- [Amazon Bedrock AgentCore Memory vs EverOS](https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [claude-mem vs EverOS](https://www.anchorterminal.com/compare/claude-mem-vs-everos.md)\n- [Cognee vs EverOS](https://www.anchorterminal.com/compare/cognee-vs-everos.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs Graphicle](https://www.anchorterminal.com/compare/everos-vs-graphicle.md)\n- [EverOS vs Graphiti](https://www.anchorterminal.com/compare/everos-vs-graphiti.md)\n- [EverOS vs Hindsight](https://www.anchorterminal.com/compare/everos-vs-hindsight.md)\n- [EverOS vs Honcho](https://www.anchorterminal.com/compare/everos-vs-honcho.md)\n- [EverOS vs Hy Memory](https://www.anchorterminal.com/compare/everos-vs-hy-memory.md)\n- [EverOS vs LangMem](https://www.anchorterminal.com/compare/everos-vs-langmem.md)\n- [EverOS vs LocalGhost](https://www.anchorterminal.com/compare/everos-vs-localghost.md)\n- [EverOS vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/everos-vs-mem0.md)\n- [EverOS vs MemMachine](https://www.anchorterminal.com/compare/everos-vs-memmachine.md)\n- [EverOS vs Memori](https://www.anchorterminal.com/compare/everos-vs-memori.md)\n- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)\n- [EverOS vs MemPalace](https://www.anchorterminal.com/compare/everos-vs-mempalace.md)\n- [EverOS vs past.dev](https://www.anchorterminal.com/compare/everos-vs-past-dev.md)\n- [EverOS vs Supermemory API + MCP](https://www.anchorterminal.com/compare/everos-vs-supermemory.md)\n- [EverOS vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.md)\n- [EverOS vs Tokenrip](https://www.anchorterminal.com/compare/everos-vs-tokenrip.md)\n- [EverOS vs Zep](https://www.anchorterminal.com/compare/everos-vs-zep.md)\n- [Amazon Bedrock AgentCore Memory vs AI Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-ai-memory.md)\n- [AI Memory vs Basic Memory](https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.md)\n- [AI Memory vs claude-mem](https://www.anchorterminal.com/compare/ai-memory-vs-claude-mem.md)\n- [AI Memory vs Cognee](https://www.anchorterminal.com/compare/ai-memory-vs-cognee.md)\n- [AI Memory vs Context Mode Engine](https://www.anchorterminal.com/compare/ai-memory-vs-context-mode.md)\n- [AI Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.md)\n- [AI Memory vs Graphicle](https://www.anchorterminal.com/compare/ai-memory-vs-graphicle.md)\n- [AI Memory vs Graphiti](https://www.anchorterminal.com/compare/ai-memory-vs-graphiti.md)\n- [AI Memory vs Hindsight](https://www.anchorterminal.com/compare/ai-memory-vs-hindsight.md)\n- [AI Memory vs Honcho](https://www.anchorterminal.com/compare/ai-memory-vs-honcho.md)\n- [AI Memory vs Hy Memory](https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.md)\n- [AI Memory vs Khoj](https://www.anchorterminal.com/compare/ai-memory-vs-khoj.md)\n- [AI Memory vs LangMem](https://www.anchorterminal.com/compare/ai-memory-vs-langmem.md)\n- [AI Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/ai-memory-vs-mem0.md)\n- [AI Memory vs MemMachine](https://www.anchorterminal.com/compare/ai-memory-vs-memmachine.md)\n- [AI Memory vs Memori](https://www.anchorterminal.com/compare/ai-memory-vs-memori.md)\n- [AI Memory vs MemPalace](https://www.anchorterminal.com/compare/ai-memory-vs-mempalace.md)\n- [AI Memory vs past.dev](https://www.anchorterminal.com/compare/ai-memory-vs-past-dev.md)\n- [AI Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/ai-memory-vs-supermemory.md)\n- [AI Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory.md)\n- [AI Memory vs Tokenrip](https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip.md)\n- [AI Memory vs Zep](https://www.anchorterminal.com/compare/ai-memory-vs-zep.md)\n- [Context Mode Engine vs EverOS](https://www.anchorterminal.com/compare/context-mode-vs-everos.md)\n- [AI Memory vs Egoist AI Passport](https://www.anchorterminal.com/compare/ai-memory-vs-egoist-ai-passport.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "AI Memory vs EverOS", "url": "" } ], "description": "EverOS scores 69.4 (B) to AI Memory's 65 (B) for memory search. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "AI Memory B 65", "EverOS B 69.4", "scores" ], "h1": "AI Memory vs EverOS", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/ai-memory-vs-everos", "published": "2026-10-01", "section": "tools", "title": "AI Memory vs EverOS for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-everos" }, "tokens": { "markdown": 4600, "slim": 2380 }, "version": 1 }