{ "data": { "a": { "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" } }, "answer": "EverOS scores 69.4 (B) on agent readiness against LangMem's 47.7 (D), and leads in 6 of 7 scored categories. LangMem leads on payments \u0026 pricing.", "b": { "slug": "langmem", "name": "LangMem", "vendor": "LangChain", "vendorUrl": "https://www.langchain.com", "kind": "sdk", "category": "agent-memory", "summary": "LangMem is LangChain's open-source Python library for long-term agent memory. It extracts facts from conversations with an LLM, stores and searches them in a LangGraph store the owner runs, and includes two memory tools, message summarisation and prompt optimisation.", "url": "https://www.anchorterminal.com/tools/langmem", "markdownUrl": "https://www.anchorterminal.com/tools/langmem.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/langmem.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/langmem.json", "dns": "langmem.grade.anchorterminal.com", "repo": "https://github.com/langchain-ai/langmem", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "langmem" } ], "auth": "none", "authNotes": "The library has no account or key of its own. It runs in the owner's process and needs a key for the chosen LLM provider (the README uses `ANTHROPIC_API_KEY`) and, for semantic search, an embedding provider. Access to memories is whatever the owner's LangGraph store and namespace settings allow.", "pricing": "free", "pricingNotes": "Free under the MIT licence, with nothing to buy and no signup. The owner pays for the LLM calls that extract memories, the embedding calls behind search, and the database behind the store (https://github.com/langchain-ai/langmem).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1698, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://langchain-ai.github.io/langmem/", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "sdk", "open-source", "self-hosted", "local", "python", "free", "langgraph", "pre-1.0" ], "lastRelease": "2025-10-27", "graded": true, "anchor": { "graded": true, "score": 47.7, "grade": "D", "agentReady": false, "rank": 1145, "ranked": true, "rankOf": 1510, "categoryRank": 23, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 15, "payments": 60, "reliability": 32, "schema": 55, "security": 42, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "Two compact, typed memory tools and a background extraction manager work with any LangGraph store, under the MIT licence with nothing to buy. The newest version, 0.0.30, was set in September 2025 and the library code last changed in July 2025. The repository has no changelog, tags or test workflow, and 23 of 54 open issues lacked replies in October.", "bestFor": "Teams already on LangGraph that want memory tools and background extraction over a store they run.", "strengths": [ "MIT licence, installed with `pip install -U langmem`, with no account, key or fee of its own", "Two agent tools, `manage_memory` and `search_memory`, with typed inputs, an action enum and `limit`, `offset` and `filter` on search", "`actions_permitted` limits the manage tool to any subset of create, update and delete, and `create_memory_store_manager` leaves deletes off by default", "Namespace templates such as `(\"memories\", \"{langgraph_user_id}\")` keep each user's memories apart at run time", "Works with any LangGraph `BaseStore`, including `InMemoryStore` for tests and `AsyncPostgresStore` for durable storage" ], "weaknesses": [ "No release found in over a year. The newest version, 0.0.30, was set on 9 September 2025, and no commit has changed `src` since 28 July 2025", "No changelog, GitHub releases or tags, and versions are still 0.0.x", "The repository's two workflows deploy docs and publish to PyPI by manual dispatch. Neither runs the tests", "54 open issues, 23 with no comment, and 19 open pull requests, the oldest from June 2025 (8 October count)", "No guidance on memory poisoning or prompt injection found, and two open issues asking for it (May 2026) had no reply" ], "agentNotes": [ "Pass a store with an embedding index (`index={\"dims\": 1536, \"embed\": \"openai:text-embedding-3-small\"}`), or `search_memory` cannot rank by meaning", "Use a database-backed store such as `AsyncPostgresStore` for anything that must survive a restart. `InMemoryStore` loses everything", "Put a per-user placeholder in the namespace and set it in `config[\"configurable\"]` on every call, or users share one memory space", "Send the memory `id` with `update` and `delete`, and never with `create`. A retried `create` writes a duplicate under a new UUID", "Run on Python 3.11 or later. `src/langmem/knowledge/extraction.py` uses `typing.NotRequired`, which Python 3.10 lacks" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.7 } ], "editorialScores": { "ergonomics": 66, "maintenance": 15, "payments": 60, "reliability": 32, "schema": 55, "security": 42, "transparency": 63 }, "provenanceScore": 62, "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 } }, "connect": { "install": "pip install -U langmem" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/langmem" }, "sameCompany": [ "langgraph", "langsmith" ], "area": "agent-runtime", "provenance": { "legalEntity": "LangChain (the licence file gives no legal form)", "domain": "langchain.com", "domainRegistered": "2019-12-03", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "A library the owner runs, with no hosted endpoint. The code is on github.com under the langchain-ai organisation and the docs are on langchain-ai.github.io/langmem.", "The LICENSE file reads Copyright (c) 2025 LangChain.", "No terms or privacy document governs the library, so both fields are left out. The MIT licence is the only agreement. LangChain's Terms of Service (last updated 2 June 2026) govern the LangSmith Platform, not this library.", "No changelog file, GitHub releases or tags exist in the repository.", "The organisation's SECURITY.md points to two Intigriti disclosure programmes. No security.txt was found on www.langchain.com (per the 1 November LangGraph re-check)." ], "score": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/langmem.json", "live": { "slug": "langmem", "versions": [ { "registry": "pypi", "name": "langmem", "version": "0.0.30", "released": "2025-10-27", "seenAt": "2026-11-06T23:38:37.634686509Z" } ], "githubStars": 1750, "pypiWeekly": 190323, "securityTxt": { "url": "https://langchain.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:25.158914764Z" }, "domain": { "domain": "langchain.com", "registered": "2019-12-03", "source": "https://rdap.verisign.com/com/v1/domain/langchain.com", "checkedAt": "2026-11-01T14:16:16.486101867Z" }, "github": { "repo": "langchain-ai/langmem", "checkedAt": "2026-11-02T08:59:39.174765749Z", "stars": 1743, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T19:35:59Z", "openIssues": 58, "openPRs": 23, "issuesOpened90d": 10, "issuesClosed90d": 0, "prsMerged90d": 8, "ci": { "branch": "main", "runs": 33, "success": 27, "failure": 4, "other": 2, "latest": "success", "latestAt": "2026-10-30T19:36:27Z" }, "replies": { "sampled": 25, "unanswered": 23, "medianDays": 2 } }, "updatedAt": "2026-11-07T16:00:25.158914764Z" } }, "edges": [ { "by": 65, "category": "maintenance", "leads": "everos", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "No release found in the last 180 days. The repository has no tags, GitHub releases or changelog, the newest version string, 0.0.30, was set in `pyproject.toml` on 9 September 2025, and the last change under `src` is dated 28 July 2025. PyPI's release dates could not be read on 4 November (0). No release in the last 90 days (0). Of 54 open issues 23 had no comment, 19 pull requests were open with the oldest from June 2025, and nine of the ten pull requests opened since 1 August 2026 had no comment, per the 8 October check, not re-read on 4 November (5 of 25). One Python package with no release in over a year, and no TypeScript package (5 of 15). Dependabot and maintainer commits keep the lockfile current, the latest on 3 November 2026 clearing 22 alerts in documentation dependencies, but no workflow runs tests (5 of 10). 0+0+5+5+5 = 15." }, "scores": { "a": 80, "b": 15 } }, { "by": 47, "category": "reliability", "leads": "everos", "name": "Reliability", "reasons": { "a": "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.", "b": "Local-software reading. Installs from PyPI as `langmem` with Python 3.10 or later declared, but `extraction.py` on main uses `typing.NotRequired`, which arrived in Python 3.11, and issues 81 and 83 about failed imports on 3.10 are open (per the 8 October check). We read the source and did not run it on 3.10 (14 of 20). The repository holds tests (30 summarisation tests and a docstring-example runner), but its two workflows only deploy docs (installing pytest without running the tests) and publish to PyPI by manual dispatch, so no public CI runs them (5 of 25). 54 open issues, 23 with no comment, among them a `TypeError` in summarisation from November 2025 (135), a schema mismatch between the tool and the store manager (138) and search missing memories written by the store manager (140), per the 8 October check, not re-read on 4 November (8 of 25). Versions are 0.0.x with no changelog, GitHub releases or tags, and open issue 130 shows 0.0.30 was cut to restore compatibility with LangGraph 1.0 (5 of 15). Below 1.0 and not declared stable (0). 14+5+8+5+0 = 32." }, "scores": { "a": 79, "b": 32 } }, { "by": 34, "category": "schema", "leads": "everos", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.", "b": "Library reading, with the tool lines applied to the two agent tools. No OpenAPI applies. Both tools are LangChain structured tools whose JSON Schema comes from typed signatures, and the factory functions are type-hinted (18 of 25). langchain-ai.github.io/langmem/llms.txt returns 404 (0). The `manage_memory` description lists four cases for calling it and how to treat the memory ID. `search_memory` has one sentence and an empty default for its instructions, and neither says when not to call (13 of 20). `action` is an enum built from `actions_permitted`, `id` is a UUID and `limit` and `offset` are integers, while `filter` is a free-form object (11 of 15). Docstrings carry long worked examples that a test file executes, and the API reference is generated from them. Error behaviour is not documented (10 of 15). Version numbers exist only on PyPI, with no changelog (3 of 15)." }, "scores": { "a": 89, "b": 55 } }, { "by": 20, "category": "payments", "leads": "langmem", "name": "Payments \u0026 pricing", "reasons": { "a": "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.", "b": "MIT-licensed package the owner runs, with nothing to buy for LangMem itself, read with the self-hosted rule. 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 in the docs or source (0). LLM, embedding and database costs are the owner's." }, "scores": { "a": 40, "b": 60 } }, { "by": 12, "category": "ergonomics", "leads": "everos", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "Two tools with short descriptions (25). `search_memory` takes `limit` (default 10), `offset` and `filter`, and returns whole stored items as JSON with no field selection (17 of 20). Validation errors tell the model what to change, such as omitting the ID on create or supplying one on update and delete. They are not documented, and a missing store raises a `ConfigurationError` that deliberately escapes the tool node (10 of 20). Update and delete by ID are safe to repeat. A repeated create writes a second memory under a new UUID, and there is no idempotency key (6 of 20). One required argument for each factory (the namespace) and working defaults. Python only, with an open request for TypeScript (issue 121) (8 of 15)." }, "scores": { "a": 78, "b": 66 } }, { "by": 8, "category": "transparency", "leads": "everos", "name": "Transparency \u0026 trust", "reasons": { "a": "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.", "b": "MIT licence in the repository and on PyPI (30). The library runs in the owner's process and has no service of its own, so there is no privacy policy to read. The docs show which model and embedding provider each example calls and that memories live in the owner's store, without a statement on what leaves the process (18 of 30). No deprecation policy or dated notices were found (0 of 20). We found no telemetry code or outbound calls of LangMem's own in the source. Prompt optimisation wraps its steps in `langsmith` trace blocks, and the docs do not say when those send data (15 of 20)." }, "scores": { "a": 71, "b": 63 } } ], "facts": [ { "a": "HTTP API", "b": "SDK + MCP", "name": "Kind" }, { "a": "Evermind AI, Inc.", "b": "LangChain", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "7", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-22", "b": "2025-10-27", "name": "Last release" }, { "a": "2026-01-20", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-01-20", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "14k stars, 4k PyPI/wk", "b": "1.7k stars", "name": "Popularity" }, { "a": "none", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "EverOS scores 69.4 (B) on agent readiness against LangMem's 47.7 (D), and leads in 6 of 7 scored categories. LangMem leads on payments \u0026 pricing.", "question": "Which is better for AI agents, EverOS or LangMem?" }, { "answer": "EverOS runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for LangMem.", "question": "Can an agent call EverOS and LangMem without installing anything?" }, { "answer": "Yes. EverOS is open source (Apache-2.0). LangMem is open source (MIT).", "question": "Are EverOS and LangMem open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 79 against 32", "Schema \u0026 documentation, 89 against 55", "Agent ergonomics, 78 against 66", "Security \u0026 auth, 47 against 42", "Maintenance \u0026 community, 80 against 15", "Transparency \u0026 trust, 71 against 63" ], "also": [ "Runs on your own machine" ], "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" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 40" ], "also": null, "goodFor": "Teams already on LangGraph that want memory tools and background extraction over a store they run.", "slug": "langmem", "watchFor": "No release found in over a year. The newest version, 0.0.30, was set on 9 September 2025, and no commit has changed `src` since 28 July 2025" } ], "history": { "everos": null, "langmem": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": -0.6, "from": 48.3, "fromGrade": "D", "to": 47.7, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.4, "from": 47.9, "fromGrade": "D", "to": 48.3, "toGrade": "D" } ] }, "job": { "capability": "memory.store", "name": "Agent memory" }, "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/agentcore-memory-vs-langmem.json", "title": "Amazon Bedrock AgentCore Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem" }, { "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/basic-memory-vs-langmem.json", "title": "Basic Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-langmem" }, { "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/claude-mem-vs-langmem.json", "title": "claude-mem vs LangMem", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-langmem" }, { "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/cognee-vs-langmem.json", "title": "Cognee vs LangMem", "url": "https://www.anchorterminal.com/compare/cognee-vs-langmem" }, { "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-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/google-memory-bank-vs-langmem.json", "title": "Agent Platform Memory Bank vs LangMem", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-langmem.json", "title": "Graphiti vs LangMem", "url": "https://www.anchorterminal.com/compare/graphiti-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-langmem.json", "title": "Hindsight vs LangMem", "url": "https://www.anchorterminal.com/compare/hindsight-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-langmem.json", "title": "Honcho vs LangMem", "url": "https://www.anchorterminal.com/compare/honcho-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-langmem.json", "title": "Hy Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-localghost.json", "title": "LangMem vs LocalGhost", "url": "https://www.anchorterminal.com/compare/langmem-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-mem0.json", "title": "LangMem vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/langmem-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-memmachine.json", "title": "LangMem vs MemMachine", "url": "https://www.anchorterminal.com/compare/langmem-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-memori.json", "title": "LangMem vs Memori", "url": "https://www.anchorterminal.com/compare/langmem-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.json", "title": "LangMem vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-mempalace.json", "title": "LangMem vs MemPalace", "url": "https://www.anchorterminal.com/compare/langmem-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-past-dev.json", "title": "LangMem vs past.dev", "url": "https://www.anchorterminal.com/compare/langmem-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-supermemory.json", "title": "LangMem vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/langmem-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory.json", "title": "LangMem vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-tokenrip.json", "title": "LangMem vs Tokenrip", "url": "https://www.anchorterminal.com/compare/langmem-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-zep.json", "title": "LangMem vs Zep", "url": "https://www.anchorterminal.com/compare/langmem-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.json", "title": "AI Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-everos" }, { "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/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/context-mode-vs-langmem.json", "title": "Context Mode Engine vs LangMem", "url": "https://www.anchorterminal.com/compare/context-mode-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-langmem.json", "title": "Graphicle vs LangMem", "url": "https://www.anchorterminal.com/compare/graphicle-vs-langmem" } ], "panel": null, "scores": [ { "by": 47, "edge": "everos", "everos": 79, "key": "reliability", "langmem": 32, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 34, "edge": "everos", "everos": 89, "key": "schema", "langmem": 55, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 12, "edge": "everos", "everos": 78, "key": "ergonomics", "langmem": 66, "name": "Agent ergonomics", "weight": 13 }, { "by": 5, "edge": "everos", "everos": 47, "key": "security", "langmem": 42, "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "edge": "langmem", "everos": 40, "key": "payments", "langmem": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 65, "edge": "everos", "everos": 80, "key": "maintenance", "langmem": 15, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 8, "edge": "everos", "everos": 71, "key": "transparency", "langmem": 63, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "EverOS scores 69.4 (B) on agent readiness against LangMem's 47.7 (D), and leads in 6 of 7 scored categories. LangMem leads on payments \u0026 pricing. Both do agent memory.", "tasks": null, "tutorials": [], "verdicts": { "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.", "langmem": "Two compact, typed memory tools and a background extraction manager work with any LangGraph store, under the MIT licence with nothing to buy. The newest version, 0.0.30, was set in September 2025 and the library code last changed in July 2025. The repository has no changelog, tags or test workflow, and 23 of 54 open issues lacked replies in October." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/everos-vs-langmem", "json": "https://www.anchorterminal.com/compare/everos-vs-langmem.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/everos-vs-langmem.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/everos-vs-langmem.min.md" }, "markdown": "EverOS scores 69.4 (B) on agent readiness against LangMem's 47.7 (D), and leads in 6 of 7 scored categories. LangMem leads on payments \u0026 pricing. Both do agent memory.\n\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- LangMem: grade D, 47.7/100, rank #1145 of 1510. Markdown https://www.anchorterminal.com/tools/langmem.md · JSON https://www.anchorterminal.com/api/v1/tools/langmem.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### 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 32\n- Schema \u0026 documentation, 89 against 55\n- Agent ergonomics, 78 against 66\n- Security \u0026 auth, 47 against 42\n- Maintenance \u0026 community, 80 against 15\n- Transparency \u0026 trust, 71 against 63\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: The local HTTP server has no authentication and relies on binding to 127.0.0.1\n\n### LangMem (D)\n\nGood for: Teams already on LangGraph that want memory tools and background extraction over a store they run.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 40\n\nWatch for: No release found in over a year. The newest version, 0.0.30, was set on 9 September 2025, and no commit has changed `src` since 28 July 2025\n\n\n## Why the edge\n\n### Maintenance \u0026 community: EverOS +65\n\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- LangMem (15): No release found in the last 180 days. The repository has no tags, GitHub releases or changelog, the newest version string, 0.0.30, was set in `pyproject.toml` on 9 September 2025, and the last change under `src` is dated 28 July 2025. PyPI's release dates could not be read on 4 November (0). No release in the last 90 days (0). Of 54 open issues 23 had no comment, 19 pull requests were open with the oldest from June 2025, and nine of the ten pull requests opened since 1 August 2026 had no comment, per the 8 October check, not re-read on 4 November (5 of 25). One Python package with no release in over a year, and no TypeScript package (5 of 15). Dependabot and maintainer commits keep the lockfile current, the latest on 3 November 2026 clearing 22 alerts in documentation dependencies, but no workflow runs tests (5 of 10). 0+0+5+5+5 = 15.\n\n### Reliability: EverOS +47\n\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- LangMem (32): Local-software reading. Installs from PyPI as `langmem` with Python 3.10 or later declared, but `extraction.py` on main uses `typing.NotRequired`, which arrived in Python 3.11, and issues 81 and 83 about failed imports on 3.10 are open (per the 8 October check). We read the source and did not run it on 3.10 (14 of 20). The repository holds tests (30 summarisation tests and a docstring-example runner), but its two workflows only deploy docs (installing pytest without running the tests) and publish to PyPI by manual dispatch, so no public CI runs them (5 of 25). 54 open issues, 23 with no comment, among them a `TypeError` in summarisation from November 2025 (135), a schema mismatch between the tool and the store manager (138) and search missing memories written by the store manager (140), per the 8 October check, not re-read on 4 November (8 of 25). Versions are 0.0.x with no changelog, GitHub releases or tags, and open issue 130 shows 0.0.30 was cut to restore compatibility with LangGraph 1.0 (5 of 15). Below 1.0 and not declared stable (0). 14+5+8+5+0 = 32.\n\n### Schema \u0026 documentation: EverOS +34\n\n- EverOS (89): OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.\n- LangMem (55): Library reading, with the tool lines applied to the two agent tools. No OpenAPI applies. Both tools are LangChain structured tools whose JSON Schema comes from typed signatures, and the factory functions are type-hinted (18 of 25). langchain-ai.github.io/langmem/llms.txt returns 404 (0). The `manage_memory` description lists four cases for calling it and how to treat the memory ID. `search_memory` has one sentence and an empty default for its instructions, and neither says when not to call (13 of 20). `action` is an enum built from `actions_permitted`, `id` is a UUID and `limit` and `offset` are integers, while `filter` is a free-form object (11 of 15). Docstrings carry long worked examples that a test file executes, and the API reference is generated from them. Error behaviour is not documented (10 of 15). Version numbers exist only on PyPI, with no changelog (3 of 15).\n\n### Payments \u0026 pricing: LangMem +20\n\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- LangMem (60): MIT-licensed package the owner runs, with nothing to buy for LangMem itself, read with the self-hosted rule. 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 in the docs or source (0). LLM, embedding and database costs are the owner's.\n\n### Agent ergonomics: EverOS +12\n\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- LangMem (66): Two tools with short descriptions (25). `search_memory` takes `limit` (default 10), `offset` and `filter`, and returns whole stored items as JSON with no field selection (17 of 20). Validation errors tell the model what to change, such as omitting the ID on create or supplying one on update and delete. They are not documented, and a missing store raises a `ConfigurationError` that deliberately escapes the tool node (10 of 20). Update and delete by ID are safe to repeat. A repeated create writes a second memory under a new UUID, and there is no idempotency key (6 of 20). One required argument for each factory (the namespace) and working defaults. Python only, with an open request for TypeScript (issue 121) (8 of 15).\n\n### Transparency \u0026 trust: EverOS +8\n\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- LangMem (63): MIT licence in the repository and on PyPI (30). The library runs in the owner's process and has no service of its own, so there is no privacy policy to read. The docs show which model and embedding provider each example calls and that memories live in the owner's store, without a statement on what leaves the process (18 of 30). No deprecation policy or dated notices were found (0 of 20). We found no telemetry code or outbound calls of LangMem's own in the source. Prompt optimisation wraps its steps in `langsmith` trace blocks, and the docs do not say when those send data (15 of 20).\n\n## Score by category\n\n| Category | Weight | EverOS | LangMem | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 79 | 32 | EverOS +47 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 55 | EverOS +34 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 66 | EverOS +12 |\n| Security \u0026 auth | 14% (17.5 this run) | 47 | 42 | EverOS +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | LangMem +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 15 | EverOS +65 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 63 | EverOS +8 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **69.4 · B** | **47.7 · D** | |\n\n## Facts side by side\n\n| Fact | EverOS | LangMem |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | Evermind AI, Inc. | LangChain |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP, stdio | |\n| Auth | None | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Tools exposed | 7 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-22 | 2025-10-27 |\n| Terms last updated | 2026-01-20 | no document linked |\n| Privacy policy last updated | 2026-01-20 | no document linked |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | 14k stars, 4k PyPI/wk | 1.7k stars |\n| Agent reviews | none | 2.8/5 (4) |\n\n## How the scores have moved\n\n### EverOS\n\nNo score change since it was listed.\n\n### LangMem\n\n- -0.6 on 4 November 2026: correction\n- +0.4 on 27 October 2026: checklist\n\n## Verdicts\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**LangMem.** Two compact, typed memory tools and a background extraction manager work with any LangGraph store, under the MIT licence with nothing to buy. The newest version, 0.0.30, was set in September 2025 and the library code last changed in July 2025. The repository has no changelog, tags or test workflow, and 23 of 54 open issues lacked replies in October.\n\n## Before you call either\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### LangMem\n\n1. Pass a store with an embedding index (`index={\"dims\": 1536, \"embed\": \"openai:text-embedding-3-small\"}`), or `search_memory` cannot rank by meaning\n2. Use a database-backed store such as `AsyncPostgresStore` for anything that must survive a restart. `InMemoryStore` loses everything\n3. Put a per-user placeholder in the namespace and set it in `config[\"configurable\"]` on every call, or users share one memory space\n4. Send the memory `id` with `update` and `delete`, and never with `create`. A retried `create` writes a duplicate under a new UUID\n5. Run on Python 3.11 or later. `src/langmem/knowledge/extraction.py` uses `typing.NotRequired`, which Python 3.10 lacks\n\n## Questions\n\n### Which is better for AI agents, EverOS or LangMem?\n\nEverOS scores 69.4 (B) on agent readiness against LangMem's 47.7 (D), and leads in 6 of 7 scored categories. LangMem leads on payments \u0026 pricing.\n\n### Can an agent call EverOS and LangMem without installing anything?\n\nEverOS runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for LangMem.\n\n### Are EverOS and LangMem open source?\n\nYes. EverOS is open source (Apache-2.0). LangMem is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/everos-vs-langmem.json, and with the fewest tokens: https://www.anchorterminal.com/compare/everos-vs-langmem.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"everos\", \"b\": \"langmem\"}`. From a terminal: `anchor compare everos langmem`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/everos.json and https://www.anchorterminal.com/api/v1/tools/langmem.json\n\n## Other comparisons with EverOS or LangMem\n\n- [Amazon Bedrock AgentCore Memory vs EverOS](https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.md)\n- [Amazon Bedrock AgentCore Memory vs LangMem](https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [Basic Memory vs LangMem](https://www.anchorterminal.com/compare/basic-memory-vs-langmem.md)\n- [claude-mem vs EverOS](https://www.anchorterminal.com/compare/claude-mem-vs-everos.md)\n- [claude-mem vs LangMem](https://www.anchorterminal.com/compare/claude-mem-vs-langmem.md)\n- [Cognee vs EverOS](https://www.anchorterminal.com/compare/cognee-vs-everos.md)\n- [Cognee vs LangMem](https://www.anchorterminal.com/compare/cognee-vs-langmem.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 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- [Agent Platform Memory Bank vs LangMem](https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem.md)\n- [Graphiti vs LangMem](https://www.anchorterminal.com/compare/graphiti-vs-langmem.md)\n- [Hindsight vs LangMem](https://www.anchorterminal.com/compare/hindsight-vs-langmem.md)\n- [Honcho vs LangMem](https://www.anchorterminal.com/compare/honcho-vs-langmem.md)\n- [Hy Memory vs LangMem](https://www.anchorterminal.com/compare/hy-memory-vs-langmem.md)\n- [LangMem vs LocalGhost](https://www.anchorterminal.com/compare/langmem-vs-localghost.md)\n- [LangMem vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/langmem-vs-mem0.md)\n- [LangMem vs MemMachine](https://www.anchorterminal.com/compare/langmem-vs-memmachine.md)\n- [LangMem vs Memori](https://www.anchorterminal.com/compare/langmem-vs-memori.md)\n- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)\n- [LangMem vs MemPalace](https://www.anchorterminal.com/compare/langmem-vs-mempalace.md)\n- [LangMem vs past.dev](https://www.anchorterminal.com/compare/langmem-vs-past-dev.md)\n- [LangMem vs Supermemory API + MCP](https://www.anchorterminal.com/compare/langmem-vs-supermemory.md)\n- [LangMem vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory.md)\n- [LangMem vs Tokenrip](https://www.anchorterminal.com/compare/langmem-vs-tokenrip.md)\n- [LangMem vs Zep](https://www.anchorterminal.com/compare/langmem-vs-zep.md)\n- [AI Memory vs EverOS](https://www.anchorterminal.com/compare/ai-memory-vs-everos.md)\n- [AI Memory vs LangMem](https://www.anchorterminal.com/compare/ai-memory-vs-langmem.md)\n- [Context Mode Engine vs EverOS](https://www.anchorterminal.com/compare/context-mode-vs-everos.md)\n- [Context Mode Engine vs LangMem](https://www.anchorterminal.com/compare/context-mode-vs-langmem.md)\n- [Graphicle vs LangMem](https://www.anchorterminal.com/compare/graphicle-vs-langmem.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": "EverOS vs LangMem", "url": "" } ], "description": "EverOS scores 69.4 (B) to LangMem's 47.7 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "EverOS B 69.4", "LangMem D 47.7", "scores" ], "h1": "EverOS vs LangMem", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/everos-vs-langmem", "published": "2026-10-01", "section": "tools", "title": "EverOS vs LangMem for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/everos-vs-langmem" }, "tokens": { "markdown": 4850, "slim": 2580 }, "version": 1 }