{
  "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": 438,
        "ranked": true,
        "rankOf": 1486,
        "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": "Basic Memory scores 76.9 (BB) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on payments \u0026 pricing.",
    "b": {
      "slug": "basic-memory",
      "name": "Basic Memory",
      "vendor": "Basic Memory LLC",
      "vendorUrl": "https://basicmemory.com",
      "kind": "mcp",
      "category": "agent-memory",
      "summary": "Basic Memory is an open-source MCP server and CLI that keeps an AI assistant's memory as Markdown notes on the user's disk, with full-text, semantic and graph search, plus an optional paid cloud for shared team memory.",
      "url": "https://www.anchorterminal.com/tools/basic-memory",
      "markdownUrl": "https://www.anchorterminal.com/tools/basic-memory.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/basic-memory.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/basic-memory.json",
      "dns": "basic-memory.grade.anchorterminal.com",
      "repo": "https://github.com/basicmachines-co/basic-memory",
      "license": "AGPL-3.0",
      "transports": [
        "stdio"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "basic-memory"
        }
      ],
      "auth": "none",
      "authNotes": "The local stdio server needs no credential and works inside configured project folders. Basic Memory Cloud uses OAuth 2.1 through WorkOS, with API keys that are read-only or project-scoped on Pro and above.",
      "pricing": "freemium",
      "pricingNotes": "The open-source server is free. Cloud is $19 a month for up to 2 members with 1,900 credits and a 7-day trial, Pro $99 a month for 5 members, Business $249 a month for 25. Usage credits are $0.01 each.",
      "priceSummary": "$19 / mo",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the source, docs, llms.txt or pricing (checked 2026-11-06). Cloud subscriptions are paid through Polar.sh per the terms.",
        "endpoints": []
      },
      "toolCount": 13,
      "popularity": {
        "githubStars": 4509,
        "npmWeekly": null,
        "pypiWeekly": 19662,
        "asOf": "2026-11-06"
      },
      "docsUrl": "https://docs.basicmemory.com",
      "llmsTxt": "https://docs.basicmemory.com/llms.txt",
      "registryName": "io.github.basicmachines-co/basic-memory",
      "capabilities": [
        "memory.store",
        "memory.search",
        "memory.graph",
        "memory.delete"
      ],
      "tags": [
        "open-source",
        "local",
        "self-hosted",
        "hosted",
        "freemium",
        "agpl-3.0",
        "python",
        "mcp",
        "mcp-registry",
        "markdown",
        "llms-txt",
        "telemetry",
        "oauth"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 76.9,
        "grade": "BB",
        "agentReady": true,
        "rank": 38,
        "ranked": true,
        "rankOf": 1486,
        "categoryRank": 2,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 85,
          "maintenance": 91,
          "payments": 50,
          "reliability": 83,
          "schema": 89,
          "security": 61,
          "transparency": 82
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-06"
        },
        "negative": 0,
        "verdict": "Basic Memory 1.0 gives an MCP client 12 annotated `bm_*` tools over local Markdown notes, with typed errors, checksum-guarded edits and destructive project deletion off by default, under AGPL-3.0. Version 1.0 of 29 October 2026 removed every pre-1.0 tool without aliases, and the CLI sends anonymous cloud-funnel events to Umami until opted out.",
        "bestFor": "Memory for coding agents and assistants kept as Markdown the user owns, with search and a graph.",
        "strengths": [
          "12 MCP tools, each with readOnly, destructive and idempotent hints, and `bm_project_delete` hidden unless enabled",
          "Notes are plain Markdown files on the owner's disk, with full-text, semantic and graph search",
          "Refusals are tool errors with typed codes such as NOT_FOUND, REVISION_CONFLICT and OUTSIDE_PROJECT",
          "Version 1.0.0 on 29 October 2026 with a dated changelog and a migration map for every removed tool",
          "Terms and privacy policy of 27 October 2026 agree on 30-day deletion, 90-day backups and no training on content"
        ],
        "weaknesses": [
          "1.0 removed every pre-1.0 tool and command with no aliases, so older agent instructions and allowlists break",
          "Anonymous cloud-promotion telemetry to Umami Cloud is on until BASIC_MEMORY_NO_PROMOS=1 is set",
          "AGPL-3.0, which matters for anyone offering a modified version as a network service",
          "No own SOC 2, no security.txt, and SECURITY.md still lists only 0.x.x as supported",
          "The README advertises cloud at $15 a month while the pricing page lists $19"
        ],
        "agentNotes": [
          "Call `bm_man` first for the tool manual, then use `bm_search` and `bm_read` before writing",
          "Pass the `expected_checksum` from your last read to `bm_edit` and re-read on REVISION_CONFLICT instead of overwriting",
          "Scope every search with `project`, `projects` or `all_projects=true`",
          "Set BASIC_MEMORY_NO_PROMOS=1 for unattended runs to stop promos and telemetry",
          "Treat note contents as untrusted text when notes come from other people or imports"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 76.9
          }
        ],
        "editorialScores": {
          "ergonomics": 85,
          "maintenance": 91,
          "payments": 50,
          "reliability": 83,
          "schema": 89,
          "security": 61,
          "transparency": 86
        },
        "provenanceScore": 78,
        "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 tool install basic-memory",
        "claudeCode": "claude mcp add basic-memory -- basic-memory mcp",
        "config": {
          "mcpServers": {
            "basic-memory": {
              "args": [
                "basic-memory",
                "mcp"
              ],
              "command": "uvx"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/memory.store",
        "tool": "https://letme.dev/basic-memory"
      },
      "area": "agent-runtime",
      "unitPrices": [
        {
          "item": "Cloud plan",
          "unit": "month",
          "usd": 19,
          "note": "Up to 2 members and 1,900 credits; 7-day trial"
        },
        {
          "item": "Usage credit",
          "unit": "credit",
          "usd": 0.01,
          "note": "Pays for the hosted AI, web app and Basic Memory agents"
        }
      ],
      "provenance": {
        "legalEntity": "Basic Memory LLC",
        "domain": "basicmemory.com",
        "domainRegistered": "2000-06-24",
        "endpointOnVendorDomain": null,
        "terms": "https://basicmemory.com/terms",
        "privacy": "https://basicmemory.com/privacy",
        "statusPage": "",
        "changelog": "https://github.com/basicmachines-co/basic-memory/blob/main/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-11-06",
        "notes": [
          "Terms and privacy policy both effective 27 October 2026, read in their Markdown versions at basicmemory.com/raw/legal/. They name Basic Memory LLC, Austin, Texas. The terms point to an Acceptable Use Policy on automated and agent-driven use, not read.",
          "basicmemory.com/robots.txt allows all crawlers except /install/ and names ClaudeBot as allowed. docs.basicmemory.com carries Content-Signal ai-input=yes.",
          "RDAP gives basicmemory.com a registration date of 24 June 2000, which predates the product, so the domain was probably bought later.",
          "/.well-known/security.txt returns 404. SECURITY.md gives hello@basicmachines.co with a 72-hour response aim."
        ],
        "score": 78
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/basic-memory.json",
      "live": {
        "slug": "basic-memory",
        "versions": [
          {
            "registry": "github",
            "name": "basicmachines-co/basic-memory",
            "version": "v1.0.0",
            "released": "2026-10-29",
            "seenAt": "2026-11-06T23:10:24.344334834Z"
          },
          {
            "registry": "pypi",
            "name": "basic-memory",
            "version": "1.0.0",
            "released": "2026-10-29",
            "seenAt": "2026-11-06T23:10:24.086880294Z"
          }
        ],
        "githubStars": 4513,
        "securityTxt": {
          "url": "https://basicmemory.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-07T15:59:33.039496203Z"
        },
        "llmsTxt": {
          "url": "https://docs.basicmemory.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-07T15:31:42.053120181Z"
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/basicmachines-co/basic-memory/main/CHANGELOG.md",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-07T14:20:09.92162468Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "f0d13083be72"
          },
          {
            "url": "https://basicmemory.com/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-07T13:59:59.298399437Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "653d0ae981d7"
          },
          {
            "url": "https://basicmemory.com/terms",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-07T14:00:03.097753192Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "bb02aea11329"
          }
        ],
        "updatedAt": "2026-11-07T15:59:33.039496203Z"
      }
    },
    "edges": [
      {
        "by": 41,
        "category": "maintenance",
        "leads": "basic-memory",
        "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": "v1.0.0 on 29 October 2026 (30). v0.24.0 and v0.24.1 on 22 October and v1.0.0, three releases in 90 days (20). Recent issues from outside users got maintainer replies within a few days (20 of 25). Verified namespace io.github.basicmachines-co/basic-memory in the official MCP registry, published by a workflow (15). uv.lock and CI, with an open report of an unmaintained dependency (6 of 10). Total 91."
        },
        "scores": {
          "a": 50,
          "b": 91
        }
      },
      {
        "by": 32,
        "category": "transparency",
        "leads": "basic-memory",
        "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": "AGPL-3.0, an OSI licence (30). The terms and privacy policy of 27 October 2026 agree on 30-day retention after cancellation, backups up to 90 days and no training on or sale of content, and name the infrastructure providers (26 of 30). The 1.0 release ships a migration guide mapping every removed tool and command, without a written deprecation period (14 of 20). Telemetry is disclosed in the README with what is and isn't sent and one opt-out, but it is on by default (16 of 20). Total 86."
        },
        "scores": {
          "a": 50,
          "b": 82
        }
      },
      {
        "by": 25,
        "category": "ergonomics",
        "leads": "basic-memory",
        "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": "13 tools, one hidden unless enabled, so the 11 to 30 band (15), with 6 back for the manual tool and the progressive-discovery tags (21 of 25). Search narrows by mode, filters, note types, items, `since`, `path` and line context (18 of 20). Refusals are tool errors with typed codes an agent can act on (17 of 20). Every tool has readOnly, destructive and idempotent hints, and edits take an expected checksum that refuses a stale write (19 of 20). Most arguments are optional and the server starts with one command, but there is one language and no SDK beyond the CLI (10 of 15). Total 85."
        },
        "scores": {
          "a": 60,
          "b": 85
        }
      },
      {
        "by": 18,
        "category": "reliability",
        "leads": "basic-memory",
        "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 stdio MCP server the owner runs. `basic-memory` on PyPI with Python 3.12 or newer stated, installed with uv (20). Test, SQLite lifecycle and Docker workflows run on the repository, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 74 open issues and pull requests against 200 commits in the 90 days, with recent bug reports answered by a maintainer within days and one flaky-CI issue open (18 of 25). The changelog calls out breaking changes in their own sections (15). v1.0.0 on 29 October 2026 (15). Total 83."
        },
        "scores": {
          "a": 65,
          "b": 83
        }
      },
      {
        "by": 10,
        "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 the cloud. No x402, MPP or L402 (0 of 40). Cloud plans are public, and credits are $0.01 each, but what a credit buys isn't priced per unit (10). The open-source server is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 50."
        },
        "scores": {
          "a": 60,
          "b": 50
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Fabio Akita",
        "b": "Basic Memory LLC",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio",
        "b": "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": "AGPL-3.0",
        "name": "Licence"
      },
      {
        "a": "25",
        "b": "13",
        "name": "Tools exposed"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "io.github.basicmachines-co/basic-memory",
        "name": "MCP registry"
      },
      {
        "a": "2026-11-03",
        "b": "2026-10-29",
        "name": "Last release"
      },
      {
        "a": "no date given",
        "b": "2026-10-27",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "2026-10-27",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "11k stars",
        "b": "4.5k stars, 20k PyPI/wk",
        "name": "Popularity"
      },
      {
        "a": "3.5/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Basic Memory scores 76.9 (BB) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on payments \u0026 pricing.",
        "question": "Which is better for AI agents, AI Memory or Basic Memory?"
      },
      {
        "answer": "AI Memory takes an API key or an OAuth sign-in. Basic Memory needs no key.",
        "question": "Do AI Memory and Basic Memory need an API key?"
      },
      {
        "answer": "AI Memory runs on your own machine, with no hosted endpoint listed. Basic Memory runs on your own machine, with no hosted endpoint listed.",
        "question": "Can an agent call AI Memory and Basic Memory without installing anything?"
      },
      {
        "answer": "No open-source release is listed for AI Memory. Basic Memory is open source (AGPL-3.0).",
        "question": "Are AI Memory and Basic Memory open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Payments \u0026 pricing, 60 against 50"
        ],
        "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, 83 against 65",
          "Agent ergonomics, 85 against 60",
          "Maintenance \u0026 community, 91 against 50",
          "Transparency \u0026 trust, 82 against 50"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "No key needed to call it",
          "Open source"
        ],
        "goodFor": "Memory for coding agents and assistants kept as Markdown the user owns, with search and a graph.",
        "slug": "basic-memory",
        "watchFor": "1.0 removed every pre-1.0 tool and command with no aliases, so older agent instructions and allowlists break"
      }
    ],
    "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"
        }
      ],
      "basic-memory": null
    },
    "job": {
      "capability": "memory.search",
      "name": "Memory search"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-basic-memory.json",
        "title": "Amazon Bedrock AgentCore Memory vs Basic Memory",
        "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-basic-memory"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-claude-mem.json",
        "title": "Basic Memory vs claude-mem",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-claude-mem"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-cognee.json",
        "title": "Basic Memory vs Cognee",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-cognee"
      },
      {
        "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-google-memory-bank.json",
        "title": "Basic Memory vs Agent Platform Memory Bank",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-graphicle.json",
        "title": "Basic Memory vs Graphicle",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-graphicle"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-graphiti.json",
        "title": "Basic Memory vs Graphiti",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-graphiti"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-hindsight.json",
        "title": "Basic Memory vs Hindsight",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-hindsight"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-honcho.json",
        "title": "Basic Memory vs Honcho",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-honcho"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-hy-memory.json",
        "title": "Basic Memory vs Hy Memory",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-hy-memory"
      },
      {
        "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/basic-memory-vs-localghost.json",
        "title": "Basic Memory vs LocalGhost",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-localghost"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-mem0.json",
        "title": "Basic Memory vs Mem0 Platform + MCP",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-mem0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-memmachine.json",
        "title": "Basic Memory vs MemMachine",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-memmachine"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-memori.json",
        "title": "Basic Memory vs Memori",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-memori"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server.json",
        "title": "Basic Memory vs Memory (MCP reference server)",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-mempalace.json",
        "title": "Basic Memory vs MemPalace",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-mempalace"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-past-dev.json",
        "title": "Basic Memory vs past.dev",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-past-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-supermemory.json",
        "title": "Basic Memory vs Supermemory API + MCP",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-supermemory"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory.json",
        "title": "Basic Memory vs TencentDB Agent Memory",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-tokenrip.json",
        "title": "Basic Memory vs Tokenrip",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-tokenrip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/basic-memory-vs-zep.json",
        "title": "Basic Memory vs Zep",
        "url": "https://www.anchorterminal.com/compare/basic-memory-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-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-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-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/basic-memory-vs-context-mode.json",
        "title": "Basic Memory vs Context Mode Engine",
        "url": "https://www.anchorterminal.com/compare/basic-memory-vs-context-mode"
      },
      {
        "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,
        "basic-memory": 83,
        "by": 18,
        "edge": "basic-memory",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "ai-memory": 90,
        "basic-memory": 89,
        "by": 1,
        "edge": "ai-memory",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "ai-memory": 60,
        "basic-memory": 85,
        "by": 25,
        "edge": "basic-memory",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "ai-memory": 65,
        "basic-memory": 61,
        "by": 4,
        "edge": "ai-memory",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "ai-memory": 60,
        "basic-memory": 50,
        "by": 10,
        "edge": "ai-memory",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "ai-memory": 50,
        "basic-memory": 91,
        "by": 41,
        "edge": "basic-memory",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "ai-memory": 50,
        "basic-memory": 82,
        "by": 32,
        "edge": "basic-memory",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Basic Memory scores 76.9 (BB) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on 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.",
      "basic-memory": "Basic Memory 1.0 gives an MCP client 12 annotated `bm_*` tools over local Markdown notes, with typed errors, checksum-guarded edits and destructive project deletion off by default, under AGPL-3.0. Version 1.0 of 29 October 2026 removed every pre-1.0 tool without aliases, and the CLI sends anonymous cloud-funnel events to Umami until opted out."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory",
    "json": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.min.md"
  },
  "markdown": "Basic Memory scores 76.9 (BB) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on payments \u0026 pricing. Both do memory search.\n\n- AI Memory: grade B, 65/100, rank #438 of 1486. Markdown https://www.anchorterminal.com/tools/ai-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/ai-memory.json\n- Basic Memory: grade BB, 76.9/100, rank #38 of 1486. Markdown https://www.anchorterminal.com/tools/basic-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/basic-memory.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- Payments \u0026 pricing, 60 against 50\n\nWatch for: Existing deployments and the Docker quick-start may still lack authentication\n\n### Basic Memory (BB)\n\nGood for: Memory for coding agents and assistants kept as Markdown the user owns, with search and a graph.\n\nAhead on:\n- Reliability, 83 against 65\n- Agent ergonomics, 85 against 60\n- Maintenance \u0026 community, 91 against 50\n- Transparency \u0026 trust, 82 against 50\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No key needed to call it\n- Open source\n\nWatch for: 1.0 removed every pre-1.0 tool and command with no aliases, so older agent instructions and allowlists break\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Basic Memory +41\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- Basic Memory (91): v1.0.0 on 29 October 2026 (30). v0.24.0 and v0.24.1 on 22 October and v1.0.0, three releases in 90 days (20). Recent issues from outside users got maintainer replies within a few days (20 of 25). Verified namespace io.github.basicmachines-co/basic-memory in the official MCP registry, published by a workflow (15). uv.lock and CI, with an open report of an unmaintained dependency (6 of 10). Total 91.\n\n### Transparency \u0026 trust: Basic Memory +32\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- Basic Memory (82): AGPL-3.0, an OSI licence (30). The terms and privacy policy of 27 October 2026 agree on 30-day retention after cancellation, backups up to 90 days and no training on or sale of content, and name the infrastructure providers (26 of 30). The 1.0 release ships a migration guide mapping every removed tool and command, without a written deprecation period (14 of 20). Telemetry is disclosed in the README with what is and isn't sent and one opt-out, but it is on by default (16 of 20). Total 86.\n\n### Agent ergonomics: Basic Memory +25\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- Basic Memory (85): 13 tools, one hidden unless enabled, so the 11 to 30 band (15), with 6 back for the manual tool and the progressive-discovery tags (21 of 25). Search narrows by mode, filters, note types, items, `since`, `path` and line context (18 of 20). Refusals are tool errors with typed codes an agent can act on (17 of 20). Every tool has readOnly, destructive and idempotent hints, and edits take an expected checksum that refuses a stale write (19 of 20). Most arguments are optional and the server starts with one command, but there is one language and no SDK beyond the CLI (10 of 15). Total 85.\n\n### Reliability: Basic Memory +18\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- Basic Memory (83): Local-software lines, as a stdio MCP server the owner runs. `basic-memory` on PyPI with Python 3.12 or newer stated, installed with uv (20). Test, SQLite lifecycle and Docker workflows run on the repository, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 74 open issues and pull requests against 200 commits in the 90 days, with recent bug reports answered by a maintainer within days and one flaky-CI issue open (18 of 25). The changelog calls out breaking changes in their own sections (15). v1.0.0 on 29 October 2026 (15). Total 83.\n\n### Payments \u0026 pricing: AI Memory +10\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- Basic Memory (50): Self-hosted rule, with the price lines read for the cloud. No x402, MPP or L402 (0 of 40). Cloud plans are public, and credits are $0.01 each, but what a credit buys isn't priced per unit (10). The open-source server is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 50.\n\n## Score by category\n\n| Category | Weight | AI Memory | Basic Memory | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 83 | Basic Memory +18 |\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 | 85 | Basic Memory +25 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 61 | AI Memory +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 50 | AI Memory +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 50 | 91 | Basic Memory +41 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 50 | 82 | Basic Memory +32 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65 · B** | **76.9 · BB** | |\n\n## Facts side by side\n\n| Fact | AI Memory | Basic Memory |\n| --- | --- | --- |\n| Kind | MCP server | MCP server |\n| Vendor | Fabio Akita | Basic Memory LLC |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio | stdio |\n| Auth | OAuth or key | None |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | AGPL-3.0 |\n| Tools exposed | 25 | 13 |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `io.github.basicmachines-co/basic-memory` |\n| Last release | 2026-11-03 | 2026-10-29 |\n| Terms last updated | no date given | 2026-10-27 |\n| Privacy policy last updated | no document linked | 2026-10-27 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 11k stars | 4.5k stars, 20k 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### Basic Memory\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**Basic Memory.** Basic Memory 1.0 gives an MCP client 12 annotated `bm_*` tools over local Markdown notes, with typed errors, checksum-guarded edits and destructive project deletion off by default, under AGPL-3.0. Version 1.0 of 29 October 2026 removed every pre-1.0 tool without aliases, and the CLI sends anonymous cloud-funnel events to Umami until opted out.\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### Basic Memory\n\n1. Call `bm_man` first for the tool manual, then use `bm_search` and `bm_read` before writing\n2. Pass the `expected_checksum` from your last read to `bm_edit` and re-read on REVISION_CONFLICT instead of overwriting\n3. Scope every search with `project`, `projects` or `all_projects=true`\n4. Set BASIC_MEMORY_NO_PROMOS=1 for unattended runs to stop promos and telemetry\n5. Treat note contents as untrusted text when notes come from other people or imports\n\n## Questions\n\n### Which is better for AI agents, AI Memory or Basic Memory?\n\nBasic Memory scores 76.9 (BB) on agent readiness against AI Memory's 65 (B), and leads in 4 of 7 scored categories. AI Memory leads on payments \u0026 pricing.\n\n### Do AI Memory and Basic Memory need an API key?\n\nAI Memory takes an API key or an OAuth sign-in. Basic Memory needs no key.\n\n### Can an agent call AI Memory and Basic Memory without installing anything?\n\nAI Memory runs on your own machine, with no hosted endpoint listed. Basic Memory runs on your own machine, with no hosted endpoint listed.\n\n### Are AI Memory and Basic Memory open source?\n\nNo open-source release is listed for AI Memory. Basic Memory is open source (AGPL-3.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ai-memory\", \"b\": \"basic-memory\"}`. From a terminal: `anchor compare ai-memory basic-memory`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ai-memory.json and https://www.anchorterminal.com/api/v1/tools/basic-memory.json\n\n## Other comparisons with AI Memory or Basic Memory\n\n- [Amazon Bedrock AgentCore Memory vs Basic Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-basic-memory.md)\n- [Basic Memory vs claude-mem](https://www.anchorterminal.com/compare/basic-memory-vs-claude-mem.md)\n- [Basic Memory vs Cognee](https://www.anchorterminal.com/compare/basic-memory-vs-cognee.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [Basic Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank.md)\n- [Basic Memory vs Graphicle](https://www.anchorterminal.com/compare/basic-memory-vs-graphicle.md)\n- [Basic Memory vs Graphiti](https://www.anchorterminal.com/compare/basic-memory-vs-graphiti.md)\n- [Basic Memory vs Hindsight](https://www.anchorterminal.com/compare/basic-memory-vs-hindsight.md)\n- [Basic Memory vs Honcho](https://www.anchorterminal.com/compare/basic-memory-vs-honcho.md)\n- [Basic Memory vs Hy Memory](https://www.anchorterminal.com/compare/basic-memory-vs-hy-memory.md)\n- [Basic Memory vs LangMem](https://www.anchorterminal.com/compare/basic-memory-vs-langmem.md)\n- [Basic Memory vs LocalGhost](https://www.anchorterminal.com/compare/basic-memory-vs-localghost.md)\n- [Basic Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/basic-memory-vs-mem0.md)\n- [Basic Memory vs MemMachine](https://www.anchorterminal.com/compare/basic-memory-vs-memmachine.md)\n- [Basic Memory vs Memori](https://www.anchorterminal.com/compare/basic-memory-vs-memori.md)\n- [Basic Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server.md)\n- [Basic Memory vs MemPalace](https://www.anchorterminal.com/compare/basic-memory-vs-mempalace.md)\n- [Basic Memory vs past.dev](https://www.anchorterminal.com/compare/basic-memory-vs-past-dev.md)\n- [Basic Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/basic-memory-vs-supermemory.md)\n- [Basic Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory.md)\n- [Basic Memory vs Tokenrip](https://www.anchorterminal.com/compare/basic-memory-vs-tokenrip.md)\n- [Basic Memory vs Zep](https://www.anchorterminal.com/compare/basic-memory-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 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 EverOS](https://www.anchorterminal.com/compare/ai-memory-vs-everos.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- [Basic Memory vs Context Mode Engine](https://www.anchorterminal.com/compare/basic-memory-vs-context-mode.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 Basic Memory",
        "url": ""
      }
    ],
    "description": "Basic Memory scores 76.9 (BB) to AI Memory's 65 (B) for memory search. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "AI Memory B 65",
      "Basic Memory BB 76.9",
      "scores"
    ],
    "h1": "AI Memory vs Basic Memory",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/ai-memory-vs-basic-memory",
    "published": "2026-10-01",
    "section": "tools",
    "title": "AI Memory vs Basic Memory for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-07",
    "url": "https://www.anchorterminal.com/compare/ai-memory-vs-basic-memory"
  },
  "tokens": {
    "markdown": 4350,
    "slim": 1930
  },
  "version": 1
}
