{ "data": { "a": { "slug": "memori", "name": "Memori", "vendor": "Memori Labs Inc.", "vendorUrl": "https://memorilabs.ai", "kind": "sdk", "category": "agent-memory", "summary": "Memori is a memory layer from Memori Labs that wraps an app's LLM client to capture conversations and agent traces, extract facts and recall them into later prompts, through Python and TypeScript SDKs, a CLI and a hosted MCP endpoint.", "url": "https://www.anchorterminal.com/tools/memori", "markdownUrl": "https://www.anchorterminal.com/tools/memori.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/memori.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/memori.json", "dns": "memori.grade.anchorterminal.com", "repo": "https://github.com/MemoriLabs/Memori", "license": "Apache-2.0", "transports": [ "streamable-http" ], "remoteUrl": "https://api.memorilabs.ai/mcp/", "packages": [ { "registry": "pypi", "name": "memori" }, { "registry": "npm", "name": "@memorilabs/memori" } ], "auth": "api-key", "authNotes": "Memori Cloud and the MCP endpoint take an API key, `X-Memori-API-Key` on MCP and a bearer token in the SDK. Keys come from app.memorilabs.ai or a CLI signup by email. Own-database mode works without a key, using a built-in anonymous key with a quota of 100 augmentations a month.", "pricing": "freemium", "pricingNotes": "A free key gives 5,000 Advanced Augmentation calls a month, per the docs; 100 a month without a key. Paid plans are sold through sales from $60,000 a year (Team) and $150,000 (Business), with Enterprise priced privately.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the SDK source, docs, llms.txt or pricing page (checked 2026-11-06).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 17446, "npmWeekly": 130, "pypiWeekly": 3781, "asOf": "2026-11-06" }, "docsUrl": "https://memorilabs.ai/docs/memori-cloud/", "llmsTxt": "https://memorilabs.ai/llms.txt", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.graph" ], "tags": [ "open-source", "hosted", "freemium", "free-tier", "apache-2.0", "python", "typescript", "cli", "mcp", "remote-mcp", "llms-txt", "sales-led" ], "lastRelease": "2026-05-27", "graded": true, "anchor": { "graded": true, "score": 44.2, "grade": "E", "agentReady": false, "rank": 1231, "ranked": true, "rankOf": 1510, "categoryRank": 25, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 33, "payments": 45, "reliability": 28, "schema": 68, "security": 45, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -4, "negativeNotes": [ "-4: misleading claim, confirmed first-hand on 6 November 2026. The BYODB architecture page says \"All data stays on your infrastructure\" and that storage has \"no external dependencies\" (https://memorilabs.ai/docs/memori-byodb/concepts/architecture), but the SDK's Advanced Augmentation posts conversation messages, the conversation summary and the system prompt to https://api.memorilabs.ai/sdk/augmentation, using a built-in anonymous key when the user has none (https://github.com/MemoriLabs/Memori/blob/main/memori/memory/augmentation/augmentations/memori/_augmentation.py and memori/_network.py). The FAQ's mention of augmentation quotas hints at the call but doesn't say conversations leave the user's infrastructure." ], "verdict": "Memori wraps an app's LLM client to capture conversations and recall facts, through Apache-2.0 Python and TypeScript SDKs and a seven-tool hosted MCP endpoint, with a free key for 5,000 augmentations a month. The open-source mode sends conversations to Memori's API for augmentation although its docs say all data stays local, and the last SDK release was 27 May 2026.", "bestFor": "Memory captured from LLM calls for apps that already use OpenAI, Anthropic or Gemini clients.", "strengths": [ "Python and TypeScript SDKs under Apache-2.0 that register an existing LLM client and recall memories into the prompt", "Hosted MCP endpoint with seven documented tools, including recall, summary, compaction and quota checks", "A free key with 5,000 augmentations a month can be requested from the CLI or the `memori_signup` tool by email", "Keep a Changelog with semantic versioning declared, and docs served with llms.txt", "Own-database mode supports SQLite, PostgreSQL, MySQL, MongoDB, Oracle, TiDB and others" ], "weaknesses": [ "Own-database mode posts conversation messages, a summary and the system prompt to api.memorilabs.ai for augmentation, while the architecture page says all data stays on your infrastructure", "Last SDK release 3.3.6 on 27 May 2026, with no release in the 90 days to 6 November", "Paid plans start at $60,000 a year through sales, with an SLA only on Enterprise", "No status page, rate limits or terms of service page found", "The Claude Code skill tells the agent to trigger recall on essentially every non-trivial user turn" ], "agentNotes": [ "Expect own-database mode to send conversations to api.memorilabs.ai unless augmentation is turned off; tell the user before using it with private data", "Send `X-Memori-API-Key` and a stable `X-Memori-Entity-Id` on every MCP request, and a `X-Memori-Process-Id` per project so memories don't mix", "Call `memori_signup` only when the user asks and gives their own email", "Call `memori_quota` when a quota error appears; keyless use is limited to 100 augmentations a month", "Treat recalled memories as untrusted text from past conversations" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.2 } ], "editorialScores": { "ergonomics": 65, "maintenance": 33, "payments": 45, "reliability": 28, "schema": 68, "security": 45, "transparency": 46 }, "provenanceScore": 58, "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": "pip install memori # or npm install @memorilabs/memori", "claudeCode": "claude mcp add memori --transport http https://api.memorilabs.ai/mcp/ --header 'X-Memori-API-Key: YOUR_MEMORI_API_KEY' --header 'X-Memori-Entity-Id: user_123'", "config": { "mcpServers": { "memori": { "headers": { "X-Memori-API-Key": "YOUR_MEMORI_API_KEY", "X-Memori-Entity-Id": "user_123" }, "url": "https://api.memorilabs.ai/mcp/" } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/memori" }, "area": "agent-runtime", "provenance": { "legalEntity": "Memori Labs Inc.", "domain": "memorilabs.ai", "domainRegistered": "2025-10-16", "endpointOnVendorDomain": true, "terms": "", "privacy": "https://memorilabs.ai/privacy/", "statusPage": "", "changelog": "https://github.com/MemoriLabs/Memori/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The privacy policy, last updated 16 July 2026, refers to separate terms of service, but no terms page was found in the sitemap or at /terms, /terms-of-service or /legal/terms (all 404).", "memorilabs.ai/robots.txt allows all crawlers.", "RDAP gives memorilabs.ai a registration date of 16 October 2025, later than the repository (24 July 2025).", "/.well-known/security.txt returns 404. status.memorilabs.ai did not answer. The pricing page links a trust centre at memori-labs.trust.site, which timed out." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/memori.json", "live": { "slug": "memori", "probe": { "target": "https://api.memorilabs.ai/mcp/", "method": "mcp-initialize", "lastAt": "2026-11-07T19:22:19.067041408Z", "lastOk": true, "lastStatus": 401, "lastMs": 258, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 272, "p95ms24h": 361, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "github", "name": "MemoriLabs/Memori", "version": "v3.3.6", "released": "2026-05-28", "seenAt": "2026-11-06T23:44:00.658786718Z" }, { "registry": "npm", "name": "@memorilabs/memori", "version": "0.0.11", "seenAt": "2026-11-06T23:44:00.185501382Z" }, { "registry": "pypi", "name": "memori", "version": "3.3.6", "released": "2026-05-28", "seenAt": "2026-11-06T23:44:00.000273764Z" } ], "githubStars": 17448, "npmWeekly": 130, "pypiWeekly": 3781, "securityTxt": { "url": "https://memorilabs.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:51.635644364Z" }, "llmsTxt": { "url": "https://memorilabs.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:59.605618502Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/MemoriLabs/Memori/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:47.202866715Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4f28fd41f6ed" }, { "url": "https://memorilabs.ai/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:14:13.209756014Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "29e786d80880" } ], "mcpTools": { "url": "https://api.memorilabs.ai/mcp/", "checkedAt": "2026-11-07T01:46:13.890822383Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:46:13.890822383Z" }, "updatedAt": "2026-11-07T19:22:19.067041408Z" } }, "answer": "Zep scores 71 (BB) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments \u0026 pricing.", "b": { "slug": "zep", "name": "Zep", "vendor": "Zep", "vendorUrl": "https://www.getzep.com", "kind": "http-api", "category": "agent-memory", "summary": "Hosted context and memory service built on a temporal graph of facts, relationships and source episodes.", "url": "https://www.anchorterminal.com/tools/zep", "markdownUrl": "https://www.anchorterminal.com/tools/zep.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/zep.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/zep.json", "dns": "zep.grade.anchorterminal.com", "repo": "https://github.com/getzep/zep", "license": "Apache-2.0 (examples repo). The service is closed-source", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.getzep.com/api/v4", "packages": [ { "registry": "pypi", "name": "zep-cloud" }, { "registry": "npm", "name": "@getzep/zep-cloud" } ], "auth": "mixed", "authNotes": "Project API key in the `Authorization: Api-Key \u003ckey\u003e` header. Keys can carry ABAC policies that limit what each agent reaches, including graph selectors that restrict a key to named standalone graphs. The Context MCP Server at api.getzep.com/mcp uses OAuth 2.1 with PKCE and signs users in through Google Workspace or, on Enterprise, a custom OIDC provider, so it suits people on a team more than headless agents.", "pricing": "freemium", "pricingNotes": "Free has 10,000 credits a month with no rollover, 2 projects, 1 MCP seat, and variable rate limits. The pricing page doesn't say whether a card is needed. Flex is $125 a month for 50,000 credits, then $25 per 10,000, at 600 requests a minute, with 30-day rollover and auto top-up. Flex Plus is $375 a month for 200,000 credits, then $75 per 40,000, at 1,000 requests a minute, with 60-day rollover. Enterprise is negotiated and adds guaranteed rate limits with an SLA, a HIPAA BAA, BYOK and BYOC. An episode (a chat message, JSON payload or block of text) costs 1 credit for up to 350 bytes and 1 more for each further 350 bytes or part. Storage, retrieval and users aren't metered, and each webhook call costs an eighth of a credit (https://www.getzep.com/pricing/).", "priceSummary": "$125 / mo", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": 12, "popularity": { "githubStars": 4900, "npmWeekly": 129945, "pypiWeekly": 86681, "asOf": "2026-09-30" }, "docsUrl": "https://help.getzep.com", "llmsTxt": "https://help.getzep.com/llms.txt", "openapi": "https://help.getzep.com/openapi/sdk-reference.json", "capabilities": [ "memory.store", "memory.search", "memory.graph", "memory.user", "memory.delete" ], "tags": [ "hosted", "freemium", "free-tier", "no-card", "mcp", "oauth", "llms-txt", "python", "typescript", "closed-source", "enterprise" ], "lastRelease": "2026-10-20", "graded": true, "anchor": { "graded": true, "score": 71, "grade": "BB", "agentReady": true, "rank": 176, "ranked": true, "rankOf": 1510, "categoryRank": 3, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 80, "payments": 30, "reliability": 70, "schema": 93, "security": 84, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "13 to 28 October 2026. Changes to the hosted API that existing clients meet, each announced in the changelog the day it took effect, with no advance notice found. On 21 October the v4 `graph.node.add` and `graph.edge.add` methods began returning 400 for custom attributes that don't match the ontology, which they had accepted since v4 became generally available on 14 October. On 28 October content policies began requiring the Enterprise plan, so other accounts get 403 `content_policy_not_entitled` and existing protected graphs ingest without evaluation. On 13 October the Context MCP Server's shared-graph tools moved from `graph_id` to `graph_uuid`. One term at the floor, -3, as context-dev's same-day status code change was read (https://help.getzep.com/v4/changelog.md)." ], "verdict": "Facts that new data invalidates keep the time they stopped being true, and the v4 API adds stable error codes and safe retries. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data.", "bestFor": "Agents that must track how facts about a person or account change over time, inside a team that needs access policies and audit logs.", "strengths": [ "Facts that new data invalidates keep the time they stopped being true", "v4 errors carry stable codes, and create calls accept an Idempotency-Key so a retry doesn't make a second resource", "API keys can carry ABAC policies and graph selectors, and audit and API logs record what each key did", "Published rate limits (600 a minute on Flex, 1,000 on Flex Plus) with 429, Retry-After and X-RateLimit headers", "A memory-security guide that treats every context block as untrusted data" ], "weaknesses": [ "The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data", "The MCP server needs OAuth through Google Workspace or an Enterprise identity provider, so a headless agent can't use it", "Six status incidents between 27 August and 30 October 2026, two of them over an hour on core functions", "Hosted API behaviour changes ship with notice only on the day, such as 400s for unmatched attributes on 21 October and Enterprise-only content policies on 28 October", "No security.txt, no subprocessor list and no entry in the MCP registry" ], "agentNotes": [ "Use the 4.0.1 SDKs and store the UUID each create call returns. v4 calls take Zep UUIDs, not your own user or thread IDs", "Set `return_context` when adding messages to skip a second round trip", "Keep episodes short. Every 350 bytes past the first costs another credit", "Branch on `error.code`. On a 429, wait for Retry-After with jitter. Free accounts over quota drop to 5 requests a minute", "Send an `Idempotency-Key` on any create call your code may repeat, and expect a delay after an add (202 Accepted) before new facts show up in search" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71 } ], "editorialScores": { "ergonomics": 87, "maintenance": 80, "payments": 30, "reliability": 70, "schema": 93, "security": 84, "transparency": 44 }, "provenanceScore": 77, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install \"zep-cloud\u003e=4.0.0\" # or: npm install @getzep/zep-cloud@^4", "http": "curl -X POST https://api.getzep.com/api/v4/graphs/$ZEP_GRAPH_UUID/episodes -H \"Authorization: Api-Key $ZEP_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"type\":\"text\",\"data\":\"Alex moved to Leeds in March and prefers aisle seats.\"}'", "claudeCode": "claude mcp add --transport http zep https://api.getzep.com/mcp", "config": { "mcpServers": { "zep": { "type": "http", "url": "https://api.getzep.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/zep" }, "sameCompany": [ "graphiti" ], "area": "agent-runtime", "unitPrices": [ { "item": "Flex plan", "unit": "month", "usd": 125, "note": "50,000 credits, 600 requests a minute" }, { "item": "Flex Plus plan", "unit": "month", "usd": 375, "note": "200,000 credits, 1,000 requests a minute" }, { "item": "Overage on Flex", "unit": "credit", "usd": 0.0025, "note": "$25 per 10,000 credits" }, { "item": "Overage on Flex Plus", "unit": "credit", "usd": 0.001875, "note": "$75 per 40,000 credits" } ], "provenance": { "legalEntity": "Zep Software, Inc.", "domain": "getzep.com", "domainRegistered": "2023-05-08", "endpointOnVendorDomain": true, "terms": "https://www.getzep.com/legal/terms/", "privacy": "https://www.getzep.com/legal/privacy/", "statusPage": "https://status.getzep.com", "changelog": "https://help.getzep.com/changelog", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The terms, updated 17 August 2026, name Zep Software, Inc., a Delaware corporation, and are governed by California law.", "www.getzep.com/.well-known/security.txt returns 404 (re-read on 1 November 2026)." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/zep.json", "live": { "slug": "zep", "probe": { "target": "https://api.getzep.com/api/v4", "method": "get", "lastAt": "2026-11-07T19:22:46.184197892Z", "lastOk": true, "lastStatus": 401, "lastMs": 396, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 342, "p95ms24h": 462, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.getzep.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:24:02.768395618Z" }, "versions": [ { "registry": "github", "name": "getzep/zep", "version": "zep-ingest-v0.4.0", "released": "2026-10-14", "seenAt": "2026-11-07T00:19:03.154698792Z" }, { "registry": "npm", "name": "@getzep/zep-cloud", "version": "4.1.0", "seenAt": "2026-11-07T00:19:02.353070658Z" }, { "registry": "pypi", "name": "zep-cloud", "version": "4.1.0", "released": "2026-11-02", "seenAt": "2026-11-07T00:19:00.262765666Z" } ], "githubStars": 4999, "npmWeekly": 165826, "pypiWeekly": 55169, "securityTxt": { "url": "https://getzep.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:51.758691547Z" }, "llmsTxt": { "url": "https://help.getzep.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:26.878626601Z" }, "domain": { "domain": "getzep.com", "registered": "2023-05-08", "source": "https://rdap.verisign.com/com/v1/domain/getzep.com", "checkedAt": "2026-11-01T14:14:29.416610087Z" }, "pages": [ { "url": "https://help.getzep.com/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:10:57.157115135Z", "changedAt": "2026-11-06T13:33:00.271456341Z", "fingerprint": "61586086be91" }, { "url": "https://www.getzep.com/blog/zep-api-for-agents/", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:29:12.819922041Z", "changedAt": "2026-11-06T13:49:56.477573452Z", "fingerprint": "f69759379704" }, { "url": "https://www.getzep.com/legal/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:29:15.209279293Z", "changedAt": "2026-11-06T13:49:58.706051669Z", "fingerprint": "c2b4bb194018" }, { "url": "https://www.getzep.com/legal/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:29:16.939967099Z", "changedAt": "2026-11-06T13:50:00.688911829Z", "fingerprint": "eded3b1fd55b" } ], "mcpTools": { "url": "https://api.getzep.com/mcp", "checkedAt": "2026-11-07T01:49:22.571937953Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:49:22.571937953Z" }, "github": { "repo": "getzep/zep", "checkedAt": "2026-11-02T08:50:28.639471688Z", "stars": 4985, "archived": false, "issuesEnabled": false, "pushedAt": "2026-11-01T18:01:41Z", "openIssues": 0, "openPRs": 28, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 24, "ci": { "branch": "main", "runs": 40, "success": 37, "failure": 3, "other": 0, "latest": "success", "latestAt": "2026-10-14T23:31:04Z" } }, "updatedAt": "2026-11-07T19:24:02.768395618Z" } }, "edges": [ { "by": 47, "category": "maintenance", "leads": "zep", "name": "Maintenance \u0026 community", "reasons": { "a": "SDK 3.3.6 on 27 May 2026, 163 days before the check (10). No release in the 90 days to 6 November (0). Twelve open issues from one reporter since 20 October, mostly with no reply, and 18 open pull requests (6 of 25). Python and TypeScript SDKs, last released in May 2026 (12 of 15). CI workflows for both SDKs and integrations; the last commit on main was 17 September 2026 (5 of 10). Total 33.", "b": "SDKs 4.0.1 for Python, TypeScript and Go on 2026-10-20, adding task filters, after 4.0.0 on 14 October, the release that made v4 generally available (30). Seven stable TypeScript SDK releases in the 90 days from 3 August, 3.26.0 to 3.30.0 and 4.0.0 per npm on 17 October and 4.0.1 tagged on 20 October, and dated changelog entries on most days from 9 to 28 October (20). Closed service, scored on the 15-point scale. The changelog is public and frequent, and we didn't test a support channel (10 of 15). Current official SDKs for Python, TypeScript and Go at 4.0.1 (15). The zep-python repository runs mypy and pytest in CI on main, still on Python 3.9, and now carries v4.0.0 and v4.0.1 tags, but we couldn't read CI results or PyPI (5 of 10). Zep's own servers aren't in the official MCP registry." }, "scores": { "a": 33, "b": 80 } }, { "by": 42, "category": "reliability", "leads": "zep", "name": "Reliability", "reasons": { "a": "Hosted lines, since both modes call Memori's API. No status page found; status.memorilabs.ai did not answer and none is linked (0). No readable incident history (5). Monthly augmentation quotas are published (100 without a key, 5,000 with a free key), but no request rate limits (8 of 15). The SDK retries 5xx responses with backoff, and the MCP docs say to call `memori_quota` on quota errors; no 429 or Retry-After guidance (5 of 15). SLA only as a custom Enterprise term (0). No beta label on the cloud or MCP endpoint (10). Total 28.", "b": "Atlassian Statuspage at status.getzep.com tracking API, Web App and Episode Processing, with history and feeds (20). The 90 days from 3 August to 1 November hold six incidents. Two impaired core functions for over an hour, retrieval and episode processing on 27 August (about 2.5 hours) and errors and latency during the AWS us-west-2 outage on 3 September (about 2 hours). Two were search latency on 10 and 15 September (2.5 and 3.5 hours). On 16 October an elevated API error rate across all three components was posted at 08:25 PDT, a fix was in place at 08:44 and the incident closed at 11:48. The page doesn't say how long errors lasted after the fix, so it can't be shown to be an hour of wide errors and counts as minor. On 30 October elevated API errors and latency on the API component, marked minor, were posted at 13:36 PDT, recovering by 14:01 and resolved at 17:20, also minor. We count two majors as 5, between the rubric's 10 for one and 0 for several. Limits published per plan, 600 requests a minute on Flex and 1,000 on Flex Plus, with a 5 RPM penalty mode on Free (15). 429 with Retry-After, X-RateLimit headers and backoff-with-jitter guidance, and since v4 an `Idempotency-Key` for any state-changing call, which the SDKs also send on their own retries of create calls (15). Enterprise names \"guaranteed rate limits with SLA\" with no published figure (5 of 10). The v4 API is generally available since 14 October (10)." }, "scores": { "a": 28, "b": 70 } }, { "by": 39, "category": "security", "leads": "zep", "name": "Security \u0026 auth", "reasons": { "a": "API keys in a header from the dashboard or CLI, with no scopes found (20 of 30). No read-only mode or per-tool restrictions (4 of 20). Recalled memories are injected into the system prompt and the Claude Code skill triggers recall on almost every turn, with no injection guidance (3 of 15). A dashboard shows memories, retrieval and usage (8 of 15). SECURITY.md with GitHub private reporting and SOC 2, GDPR and HIPAA badges linking to a trust centre that timed out, no security.txt. Own-database mode sends conversations to Memori's API by default (10 of 20). Total 45.", "b": "Project API keys can carry ABAC policies that limit which actions and context each agent reaches, and since 14 October graph selectors can limit a key to named standalone graphs. The MCP server uses OAuth 2.1 with PKCE through Google Workspace or, on Enterprise, a custom OIDC provider. We found no key expiry or rotation documentation (27 of 30). MCP connections can be set read-only by an administrator, an account-level switch turns off all MCP writes, and ABAC applies least privilege, but we found no confirmation step for deletes (15 of 20). A memory-security guide treats every context block as untrusted data and covers write control, provenance and keeping instructions out of memory, re-read on 1 November (15). Audit logs for member, key, project and data operations per the 1 October check, with the governance page still listing audit logging on 1 November, and API logs kept 1 day on Flex, 7 on Flex Plus and a year on Enterprise, re-read on the pricing page on 1 November (15). SOC 2 Type II, HIPAA BAA on Enterprise and BYOK, but no security.txt (404 on 1 November), disclosure policy or bug bounty found (12 of 20)." }, "scores": { "a": 45, "b": 84 } }, { "by": 25, "category": "schema", "leads": "zep", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI for the REST API, and the MCP tool schemas couldn't be read without opening a session, so the docs' parameter lists are what was scored (12 of 25). llms.txt with Markdown docs for both modes (10). Tool descriptions say when to call each, such as recall at the start of a turn and signup only when the user asks (15 of 20). Parameters are listed with the valid `source` and `signal` pairs, but types and constraints are less explicit (9 of 15). Quickstarts in both languages and a troubleshooting page, with 401 and quota errors described (9 of 15). Keep a Changelog with semantic versioning (13 of 15). Total 68.", "b": "OpenAPI 3.1 for v4 (147 paths, server api.getzep.com/api/v4) at help.getzep.com/openapi/sdk-reference.json, reached from the index at help.getzep.com/openapi.json that llms.txt names. The v3 link the listing carried returned 404 on 17 October (25). llms.txt per version, a Markdown copy of every page at `.md`, and a docs MCP server (10). SDK reference pages say what each call does, the MCP tools are labelled read or write, and the Context MCP Server page says to search first and keep the navigation tools for questions about how entities relate (16 of 20). Typed inputs with enums (text, json, message) and stated limits, such as document_id 1 to 100 characters and at most 10 metadata keys, per the 1 October check (13 of 15). Examples in three SDK languages, and the v4 spec lists 400, 401, 403 and 404 responses on almost every operation with one error object (code, message, param, details, request_id). We found no complete list of codes (14 of 15). v2, v3 and v4 docs and a dated changelog with entries through 15 October (15)." }, "scores": { "a": 68, "b": 93 } }, { "by": 22, "category": "ergonomics", "leads": "zep", "name": "Agent ergonomics", "reasons": { "a": "Seven MCP tools with short parameter lists (22 of 25). Recall filters by project, session, date range and source (14 of 20). 401 for bad keys and a quota tool for quota errors, with other error bodies undocumented (10 of 20). No idempotency guidance or tool annotations documented (4 of 20). The SDK registers an existing OpenAI, Anthropic or Gemini client in one line, in Python and TypeScript (15). Total 65.", "b": "The Context MCP Server (formerly Memory MCP) has 12 tools, 10 read and 2 write (15), and an administrator can switch a connection to read-only, with an account-level switch that turns off all writes (5 added back). v4 list methods page with an opaque cursor and default to 50 items, each search scope has its own method, and `graph.get_subgraph` reports `truncated` and the limit that stopped it (20). Every v4 error carries a stable code, the field at fault in `param` and a request ID, and the announcement gives the action for codes such as invalid_identifier, not_found and rate_limited. We didn't see the MCP server's error shape or a full code list (18 of 20). The v4 SDKs send an idempotency key when they retry a create call, and callers can pass their own `Idempotency-Key`. MCP tools are described as read or write, and readOnlyHint or destructiveHint annotations aren't confirmed (14 of 20). SDKs in Python, TypeScript and Go, and an episode add needs only `data` (15)." }, "scores": { "a": 65, "b": 87 } }, { "by": 15, "category": "payments", "leads": "memori", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0 of 40). Plan prices are public but sales-led, from $60,000 a year (10). A free key with 5,000 augmentations a month, with no card mentioned (20). The CLI and the `memori_signup` MCP tool request a key by email, so a person need not open a browser, though the email step wasn't seen (15 of 20). Total 45.", "b": "No x402, MPP or L402 (0). Credits are priced per unit and public, 1 credit per 350 bytes of episode, overage $25 per 10,000 on Flex and $75 per 40,000 on Flex Plus (20). Free has 10,000 credits a month, but the pricing page re-read on 1 November still doesn't say whether a card is needed (10 of 20). A person signs up in the browser and creates a project key, and the MCP server needs a human identity-provider sign-in (0)." }, "scores": { "a": 45, "b": 30 } } ], "facts": [ { "a": "SDK + MCP", "b": "HTTP API", "name": "Kind" }, { "a": "Memori Labs Inc.", "b": "Zep", "name": "Vendor" }, { "a": "https://api.memorilabs.ai/mcp/", "b": "https://api.getzep.com/api/v4", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0 (examples repo). The service is closed-source", "name": "Licence" }, { "a": "7", "b": "12", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-05-27", "b": "2026-10-20", "name": "Last release" }, { "a": "no document linked", "b": "2026-08-17", "name": "Terms last updated" }, { "a": "no date given", "b": "2024-01-27", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "yes", "name": "Customer content may train models" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "17k stars, 130 npm/wk, 3.8k PyPI/wk", "b": "4.9k stars, 130k npm/wk, 87k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "4/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Zep scores 71 (BB) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Memori or Zep?" }, { "answer": "Yes. Memori has a hosted endpoint at https://api.memorilabs.ai/mcp/ and Zep at https://api.getzep.com/api/v4.", "question": "Can an agent call Memori and Zep without installing anything?" }, { "answer": "Memori is open source (Apache-2.0). No open-source release is listed for Zep.", "question": "Are Memori and Zep open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 45 against 30" ], "also": [ "Open source" ], "goodFor": "Memory captured from LLM calls for apps that already use OpenAI, Anthropic or Gemini clients.", "slug": "memori", "watchFor": "Own-database mode posts conversation messages, a summary and the system prompt to api.memorilabs.ai for augmentation, while the architecture page says all data stays on your infrastructure" }, { "aheadOn": [ "Reliability, 70 against 28", "Schema \u0026 documentation, 93 against 68", "Agent ergonomics, 87 against 65", "Security \u0026 auth, 84 against 45", "Maintenance \u0026 community, 80 against 33", "Transparency \u0026 trust, 61 against 52" ], "also": [ "Agent-ready, a grade of BB or better", "Free to start without a card" ], "goodFor": "Agents that must track how facts about a person or account change over time, inside a team that needs access policies and audit logs.", "slug": "zep", "watchFor": "The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data" } ], "history": { "memori": null, "zep": [ { "causes": [ "event" ], "date": "2026-11-01", "delta": -3, "from": 74, "fromGrade": "BB", "to": 71, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 73.9, "fromGrade": "BB", "to": 74, "toGrade": "BB" }, { "causes": [ "product" ], "date": "2026-10-17", "delta": 4.6, "from": 69.3, "fromGrade": "B", "to": 73.9, "toGrade": "BB" } ] }, "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memori.json", "title": "Amazon Bedrock AgentCore Memory vs Memori", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-zep.json", "title": "Amazon Bedrock AgentCore Memory vs Zep", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-zep" }, { "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-zep.json", "title": "Basic Memory vs Zep", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-memori.json", "title": "claude-mem vs Memori", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-zep.json", "title": "claude-mem vs Zep", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-memori.json", "title": "Cognee vs Memori", "url": "https://www.anchorterminal.com/compare/cognee-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-zep.json", "title": "Cognee vs Zep", "url": "https://www.anchorterminal.com/compare/cognee-vs-zep" }, { "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-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-memori.json", "title": "Agent Platform Memory Bank vs Memori", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-zep.json", "title": "Agent Platform Memory Bank vs Zep", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-memori.json", "title": "Graphiti vs Memori", "url": "https://www.anchorterminal.com/compare/graphiti-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-zep.json", "title": "Graphiti vs Zep", "url": "https://www.anchorterminal.com/compare/graphiti-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-memori.json", "title": "Hindsight vs Memori", "url": "https://www.anchorterminal.com/compare/hindsight-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-zep.json", "title": "Hindsight vs Zep", "url": "https://www.anchorterminal.com/compare/hindsight-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memori.json", "title": "Honcho vs Memori", "url": "https://www.anchorterminal.com/compare/honcho-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-zep.json", "title": "Honcho vs Zep", "url": "https://www.anchorterminal.com/compare/honcho-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-memori.json", "title": "Hy Memory vs Memori", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-zep.json", "title": "Hy Memory vs Zep", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-zep" }, { "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-zep.json", "title": "LangMem vs Zep", "url": "https://www.anchorterminal.com/compare/langmem-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-memori.json", "title": "LocalGhost vs Memori", "url": "https://www.anchorterminal.com/compare/localghost-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-zep.json", "title": "LocalGhost vs Zep", "url": "https://www.anchorterminal.com/compare/localghost-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-memori.json", "title": "Mem0 Platform + MCP vs Memori", "url": "https://www.anchorterminal.com/compare/mem0-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-zep.json", "title": "Mem0 Platform + MCP vs Zep", "url": "https://www.anchorterminal.com/compare/mem0-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/memmachine-vs-memori.json", "title": "MemMachine vs Memori", "url": "https://www.anchorterminal.com/compare/memmachine-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/memmachine-vs-zep.json", "title": "MemMachine vs Zep", "url": "https://www.anchorterminal.com/compare/memmachine-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-memory-reference-server.json", "title": "Memori vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/memori-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-mempalace.json", "title": "Memori vs MemPalace", "url": "https://www.anchorterminal.com/compare/memori-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-past-dev.json", "title": "Memori vs past.dev", "url": "https://www.anchorterminal.com/compare/memori-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-supermemory.json", "title": "Memori vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/memori-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory.json", "title": "Memori vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-tokenrip.json", "title": "Memori vs Tokenrip", "url": "https://www.anchorterminal.com/compare/memori-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.json", "title": "Memory (MCP reference server) vs Zep", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/mempalace-vs-zep.json", "title": "MemPalace vs Zep", "url": "https://www.anchorterminal.com/compare/mempalace-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/past-dev-vs-zep.json", "title": "past.dev vs Zep", "url": "https://www.anchorterminal.com/compare/past-dev-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/supermemory-vs-zep.json", "title": "Supermemory API + MCP vs Zep", "url": "https://www.anchorterminal.com/compare/supermemory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep.json", "title": "TencentDB Agent Memory vs Zep", "url": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/tokenrip-vs-zep.json", "title": "Tokenrip vs Zep", "url": "https://www.anchorterminal.com/compare/tokenrip-vs-zep" }, { "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-zep.json", "title": "AI Memory vs Zep", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-memori.json", "title": "Context Mode Engine vs Memori", "url": "https://www.anchorterminal.com/compare/context-mode-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-zep.json", "title": "Context Mode Engine vs Zep", "url": "https://www.anchorterminal.com/compare/context-mode-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-memori.json", "title": "Graphicle vs Memori", "url": "https://www.anchorterminal.com/compare/graphicle-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-zep.json", "title": "Graphicle vs Zep", "url": "https://www.anchorterminal.com/compare/graphicle-vs-zep" } ], "panel": null, "scores": [ { "by": 42, "edge": "zep", "key": "reliability", "memori": 28, "name": "Reliability", "weight": 16, "zep": 70 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 25, "edge": "zep", "key": "schema", "memori": 68, "name": "Schema \u0026 documentation", "weight": 13, "zep": 93 }, { "by": 22, "edge": "zep", "key": "ergonomics", "memori": 65, "name": "Agent ergonomics", "weight": 13, "zep": 87 }, { "by": 39, "edge": "zep", "key": "security", "memori": 45, "name": "Security \u0026 auth", "weight": 14, "zep": 84 }, { "by": 15, "edge": "memori", "key": "payments", "memori": 45, "name": "Payments \u0026 pricing", "weight": 10, "zep": 30 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 47, "edge": "zep", "key": "maintenance", "memori": 33, "name": "Maintenance \u0026 community", "weight": 7, "zep": 80 }, { "by": 9, "edge": "zep", "key": "transparency", "memori": 52, "name": "Transparency \u0026 trust", "weight": 7, "zep": 61 } ], "summary": "Zep scores 71 (BB) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments \u0026 pricing. Both do agent memory.", "tasks": null, "tutorials": [], "verdicts": { "memori": "Memori wraps an app's LLM client to capture conversations and recall facts, through Apache-2.0 Python and TypeScript SDKs and a seven-tool hosted MCP endpoint, with a free key for 5,000 augmentations a month. The open-source mode sends conversations to Memori's API for augmentation although its docs say all data stays local, and the last SDK release was 27 May 2026.", "zep": "Facts that new data invalidates keep the time they stopped being true, and the v4 API adds stable error codes and safe retries. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/memori-vs-zep", "json": "https://www.anchorterminal.com/compare/memori-vs-zep.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/memori-vs-zep.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/memori-vs-zep.min.md" }, "markdown": "Zep scores 71 (BB) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments \u0026 pricing. Both do agent memory.\n\n- Memori: grade E, 44.2/100, rank #1231 of 1510. Markdown https://www.anchorterminal.com/tools/memori.md · JSON https://www.anchorterminal.com/api/v1/tools/memori.json\n- Zep: grade BB, 71/100, rank #176 of 1510. Markdown https://www.anchorterminal.com/tools/zep.md · JSON https://www.anchorterminal.com/api/v1/tools/zep.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### Memori (E)\n\nGood for: Memory captured from LLM calls for apps that already use OpenAI, Anthropic or Gemini clients.\n\nAhead on:\n- Payments \u0026 pricing, 45 against 30\n\nAlso in its favour:\n- Open source\n\nWatch for: Own-database mode posts conversation messages, a summary and the system prompt to api.memorilabs.ai for augmentation, while the architecture page says all data stays on your infrastructure\n\n### Zep (BB)\n\nGood for: Agents that must track how facts about a person or account change over time, inside a team that needs access policies and audit logs.\n\nAhead on:\n- Reliability, 70 against 28\n- Schema \u0026 documentation, 93 against 68\n- Agent ergonomics, 87 against 65\n- Security \u0026 auth, 84 against 45\n- Maintenance \u0026 community, 80 against 33\n- Transparency \u0026 trust, 61 against 52\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n\nWatch for: The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Zep +47\n\n- Memori (33): SDK 3.3.6 on 27 May 2026, 163 days before the check (10). No release in the 90 days to 6 November (0). Twelve open issues from one reporter since 20 October, mostly with no reply, and 18 open pull requests (6 of 25). Python and TypeScript SDKs, last released in May 2026 (12 of 15). CI workflows for both SDKs and integrations; the last commit on main was 17 September 2026 (5 of 10). Total 33.\n- Zep (80): SDKs 4.0.1 for Python, TypeScript and Go on 2026-10-20, adding task filters, after 4.0.0 on 14 October, the release that made v4 generally available (30). Seven stable TypeScript SDK releases in the 90 days from 3 August, 3.26.0 to 3.30.0 and 4.0.0 per npm on 17 October and 4.0.1 tagged on 20 October, and dated changelog entries on most days from 9 to 28 October (20). Closed service, scored on the 15-point scale. The changelog is public and frequent, and we didn't test a support channel (10 of 15). Current official SDKs for Python, TypeScript and Go at 4.0.1 (15). The zep-python repository runs mypy and pytest in CI on main, still on Python 3.9, and now carries v4.0.0 and v4.0.1 tags, but we couldn't read CI results or PyPI (5 of 10). Zep's own servers aren't in the official MCP registry.\n\n### Reliability: Zep +42\n\n- Memori (28): Hosted lines, since both modes call Memori's API. No status page found; status.memorilabs.ai did not answer and none is linked (0). No readable incident history (5). Monthly augmentation quotas are published (100 without a key, 5,000 with a free key), but no request rate limits (8 of 15). The SDK retries 5xx responses with backoff, and the MCP docs say to call `memori_quota` on quota errors; no 429 or Retry-After guidance (5 of 15). SLA only as a custom Enterprise term (0). No beta label on the cloud or MCP endpoint (10). Total 28.\n- Zep (70): Atlassian Statuspage at status.getzep.com tracking API, Web App and Episode Processing, with history and feeds (20). The 90 days from 3 August to 1 November hold six incidents. Two impaired core functions for over an hour, retrieval and episode processing on 27 August (about 2.5 hours) and errors and latency during the AWS us-west-2 outage on 3 September (about 2 hours). Two were search latency on 10 and 15 September (2.5 and 3.5 hours). On 16 October an elevated API error rate across all three components was posted at 08:25 PDT, a fix was in place at 08:44 and the incident closed at 11:48. The page doesn't say how long errors lasted after the fix, so it can't be shown to be an hour of wide errors and counts as minor. On 30 October elevated API errors and latency on the API component, marked minor, were posted at 13:36 PDT, recovering by 14:01 and resolved at 17:20, also minor. We count two majors as 5, between the rubric's 10 for one and 0 for several. Limits published per plan, 600 requests a minute on Flex and 1,000 on Flex Plus, with a 5 RPM penalty mode on Free (15). 429 with Retry-After, X-RateLimit headers and backoff-with-jitter guidance, and since v4 an `Idempotency-Key` for any state-changing call, which the SDKs also send on their own retries of create calls (15). Enterprise names \"guaranteed rate limits with SLA\" with no published figure (5 of 10). The v4 API is generally available since 14 October (10).\n\n### Security \u0026 auth: Zep +39\n\n- Memori (45): API keys in a header from the dashboard or CLI, with no scopes found (20 of 30). No read-only mode or per-tool restrictions (4 of 20). Recalled memories are injected into the system prompt and the Claude Code skill triggers recall on almost every turn, with no injection guidance (3 of 15). A dashboard shows memories, retrieval and usage (8 of 15). SECURITY.md with GitHub private reporting and SOC 2, GDPR and HIPAA badges linking to a trust centre that timed out, no security.txt. Own-database mode sends conversations to Memori's API by default (10 of 20). Total 45.\n- Zep (84): Project API keys can carry ABAC policies that limit which actions and context each agent reaches, and since 14 October graph selectors can limit a key to named standalone graphs. The MCP server uses OAuth 2.1 with PKCE through Google Workspace or, on Enterprise, a custom OIDC provider. We found no key expiry or rotation documentation (27 of 30). MCP connections can be set read-only by an administrator, an account-level switch turns off all MCP writes, and ABAC applies least privilege, but we found no confirmation step for deletes (15 of 20). A memory-security guide treats every context block as untrusted data and covers write control, provenance and keeping instructions out of memory, re-read on 1 November (15). Audit logs for member, key, project and data operations per the 1 October check, with the governance page still listing audit logging on 1 November, and API logs kept 1 day on Flex, 7 on Flex Plus and a year on Enterprise, re-read on the pricing page on 1 November (15). SOC 2 Type II, HIPAA BAA on Enterprise and BYOK, but no security.txt (404 on 1 November), disclosure policy or bug bounty found (12 of 20).\n\n### Schema \u0026 documentation: Zep +25\n\n- Memori (68): No OpenAPI for the REST API, and the MCP tool schemas couldn't be read without opening a session, so the docs' parameter lists are what was scored (12 of 25). llms.txt with Markdown docs for both modes (10). Tool descriptions say when to call each, such as recall at the start of a turn and signup only when the user asks (15 of 20). Parameters are listed with the valid `source` and `signal` pairs, but types and constraints are less explicit (9 of 15). Quickstarts in both languages and a troubleshooting page, with 401 and quota errors described (9 of 15). Keep a Changelog with semantic versioning (13 of 15). Total 68.\n- Zep (93): OpenAPI 3.1 for v4 (147 paths, server api.getzep.com/api/v4) at help.getzep.com/openapi/sdk-reference.json, reached from the index at help.getzep.com/openapi.json that llms.txt names. The v3 link the listing carried returned 404 on 17 October (25). llms.txt per version, a Markdown copy of every page at `.md`, and a docs MCP server (10). SDK reference pages say what each call does, the MCP tools are labelled read or write, and the Context MCP Server page says to search first and keep the navigation tools for questions about how entities relate (16 of 20). Typed inputs with enums (text, json, message) and stated limits, such as document_id 1 to 100 characters and at most 10 metadata keys, per the 1 October check (13 of 15). Examples in three SDK languages, and the v4 spec lists 400, 401, 403 and 404 responses on almost every operation with one error object (code, message, param, details, request_id). We found no complete list of codes (14 of 15). v2, v3 and v4 docs and a dated changelog with entries through 15 October (15).\n\n### Agent ergonomics: Zep +22\n\n- Memori (65): Seven MCP tools with short parameter lists (22 of 25). Recall filters by project, session, date range and source (14 of 20). 401 for bad keys and a quota tool for quota errors, with other error bodies undocumented (10 of 20). No idempotency guidance or tool annotations documented (4 of 20). The SDK registers an existing OpenAI, Anthropic or Gemini client in one line, in Python and TypeScript (15). Total 65.\n- Zep (87): The Context MCP Server (formerly Memory MCP) has 12 tools, 10 read and 2 write (15), and an administrator can switch a connection to read-only, with an account-level switch that turns off all writes (5 added back). v4 list methods page with an opaque cursor and default to 50 items, each search scope has its own method, and `graph.get_subgraph` reports `truncated` and the limit that stopped it (20). Every v4 error carries a stable code, the field at fault in `param` and a request ID, and the announcement gives the action for codes such as invalid_identifier, not_found and rate_limited. We didn't see the MCP server's error shape or a full code list (18 of 20). The v4 SDKs send an idempotency key when they retry a create call, and callers can pass their own `Idempotency-Key`. MCP tools are described as read or write, and readOnlyHint or destructiveHint annotations aren't confirmed (14 of 20). SDKs in Python, TypeScript and Go, and an episode add needs only `data` (15).\n\n### Payments \u0026 pricing: Memori +15\n\n- Memori (45): No x402, MPP or L402 (0 of 40). Plan prices are public but sales-led, from $60,000 a year (10). A free key with 5,000 augmentations a month, with no card mentioned (20). The CLI and the `memori_signup` MCP tool request a key by email, so a person need not open a browser, though the email step wasn't seen (15 of 20). Total 45.\n- Zep (30): No x402, MPP or L402 (0). Credits are priced per unit and public, 1 credit per 350 bytes of episode, overage $25 per 10,000 on Flex and $75 per 40,000 on Flex Plus (20). Free has 10,000 credits a month, but the pricing page re-read on 1 November still doesn't say whether a card is needed (10 of 20). A person signs up in the browser and creates a project key, and the MCP server needs a human identity-provider sign-in (0).\n\n## Score by category\n\n| Category | Weight | Memori | Zep | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 28 | 70 | Zep +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 68 | 93 | Zep +25 |\n| Agent ergonomics | 13% (16.2 this run) | 65 | 87 | Zep +22 |\n| Security \u0026 auth | 14% (17.5 this run) | 45 | 84 | Zep +39 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 45 | 30 | Memori +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 33 | 80 | Zep +47 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 52 | 61 | Zep +9 |\n| Negative events | ≤15 | -4 | -3 | |\n| **Total** | | **44.2 · E** | **71 · BB** | |\n\n## Facts side by side\n\n| Fact | Memori | Zep |\n| --- | --- | --- |\n| Kind | SDK + MCP | HTTP API |\n| Vendor | Memori Labs Inc. | Zep |\n| Hosted endpoint | `https://api.memorilabs.ai/mcp/` | `https://api.getzep.com/api/v4` |\n| Transports | Streamable HTTP | HTTP, Streamable HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 (examples repo). The service is closed-source |\n| Tools exposed | 7 | 12 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-05-27 | 2026-10-20 |\n| Terms last updated | no document linked | 2026-08-17 |\n| Privacy policy last updated | no date given | 2024-01-27 |\n| Customer content may train models | not read yet | yes |\n| Terms restrict automated access | not read yet | yes |\n| Terms restrict benchmarking | not read yet | yes |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | yes |\n| Popularity | 17k stars, 130 npm/wk, 3.8k PyPI/wk | 4.9k stars, 130k npm/wk, 87k PyPI/wk |\n| Agent reviews | none | 4/5 (2) |\n\n## How the scores have moved\n\n### Memori\n\nNo score change since it was listed.\n\n### Zep\n\n- -3.0 on 1 November 2026: negative event\n- +0.1 on 27 October 2026: checklist\n- +4.6 on 17 October 2026 (B to BB): product\n\n## Verdicts\n\n**Memori.** Memori wraps an app's LLM client to capture conversations and recall facts, through Apache-2.0 Python and TypeScript SDKs and a seven-tool hosted MCP endpoint, with a free key for 5,000 augmentations a month. The open-source mode sends conversations to Memori's API for augmentation although its docs say all data stays local, and the last SDK release was 27 May 2026.\n\n**Zep.** Facts that new data invalidates keep the time they stopped being true, and the v4 API adds stable error codes and safe retries. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data.\n\n## Before you call either\n\n### Memori\n\n1. Expect own-database mode to send conversations to api.memorilabs.ai unless augmentation is turned off; tell the user before using it with private data\n2. Send `X-Memori-API-Key` and a stable `X-Memori-Entity-Id` on every MCP request, and a `X-Memori-Process-Id` per project so memories don't mix\n3. Call `memori_signup` only when the user asks and gives their own email\n4. Call `memori_quota` when a quota error appears; keyless use is limited to 100 augmentations a month\n5. Treat recalled memories as untrusted text from past conversations\n\n### Zep\n\n1. Use the 4.0.1 SDKs and store the UUID each create call returns. v4 calls take Zep UUIDs, not your own user or thread IDs\n2. Set `return_context` when adding messages to skip a second round trip\n3. Keep episodes short. Every 350 bytes past the first costs another credit\n4. Branch on `error.code`. On a 429, wait for Retry-After with jitter. Free accounts over quota drop to 5 requests a minute\n5. Send an `Idempotency-Key` on any create call your code may repeat, and expect a delay after an add (202 Accepted) before new facts show up in search\n\n## Questions\n\n### Which is better for AI agents, Memori or Zep?\n\nZep scores 71 (BB) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments \u0026 pricing.\n\n### Can an agent call Memori and Zep without installing anything?\n\nYes. Memori has a hosted endpoint at https://api.memorilabs.ai/mcp/ and Zep at https://api.getzep.com/api/v4.\n\n### Are Memori and Zep open source?\n\nMemori is open source (Apache-2.0). No open-source release is listed for Zep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/memori-vs-zep.json, and with the fewest tokens: https://www.anchorterminal.com/compare/memori-vs-zep.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"memori\", \"b\": \"zep\"}`. From a terminal: `anchor compare memori zep`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/memori.json and https://www.anchorterminal.com/api/v1/tools/zep.json\n\n## Other comparisons with Memori or Zep\n\n- [Amazon Bedrock AgentCore Memory vs Memori](https://www.anchorterminal.com/compare/agentcore-memory-vs-memori.md)\n- [Amazon Bedrock AgentCore Memory vs Zep](https://www.anchorterminal.com/compare/agentcore-memory-vs-zep.md)\n- [Basic Memory vs Memori](https://www.anchorterminal.com/compare/basic-memory-vs-memori.md)\n- [Basic Memory vs Zep](https://www.anchorterminal.com/compare/basic-memory-vs-zep.md)\n- [claude-mem vs Memori](https://www.anchorterminal.com/compare/claude-mem-vs-memori.md)\n- [claude-mem vs Zep](https://www.anchorterminal.com/compare/claude-mem-vs-zep.md)\n- [Cognee vs Memori](https://www.anchorterminal.com/compare/cognee-vs-memori.md)\n- [Cognee vs Zep](https://www.anchorterminal.com/compare/cognee-vs-zep.md)\n- [EverOS vs Memori](https://www.anchorterminal.com/compare/everos-vs-memori.md)\n- [EverOS vs Zep](https://www.anchorterminal.com/compare/everos-vs-zep.md)\n- [Agent Platform Memory Bank vs Memori](https://www.anchorterminal.com/compare/google-memory-bank-vs-memori.md)\n- [Agent Platform Memory Bank vs Zep](https://www.anchorterminal.com/compare/google-memory-bank-vs-zep.md)\n- [Graphiti vs Memori](https://www.anchorterminal.com/compare/graphiti-vs-memori.md)\n- [Graphiti vs Zep](https://www.anchorterminal.com/compare/graphiti-vs-zep.md)\n- [Hindsight vs Memori](https://www.anchorterminal.com/compare/hindsight-vs-memori.md)\n- [Hindsight vs Zep](https://www.anchorterminal.com/compare/hindsight-vs-zep.md)\n- [Honcho vs Memori](https://www.anchorterminal.com/compare/honcho-vs-memori.md)\n- [Honcho vs Zep](https://www.anchorterminal.com/compare/honcho-vs-zep.md)\n- [Hy Memory vs Memori](https://www.anchorterminal.com/compare/hy-memory-vs-memori.md)\n- [Hy Memory vs Zep](https://www.anchorterminal.com/compare/hy-memory-vs-zep.md)\n- [LangMem vs Memori](https://www.anchorterminal.com/compare/langmem-vs-memori.md)\n- [LangMem vs Zep](https://www.anchorterminal.com/compare/langmem-vs-zep.md)\n- [LocalGhost vs Memori](https://www.anchorterminal.com/compare/localghost-vs-memori.md)\n- [LocalGhost vs Zep](https://www.anchorterminal.com/compare/localghost-vs-zep.md)\n- [Mem0 Platform + MCP vs Memori](https://www.anchorterminal.com/compare/mem0-vs-memori.md)\n- [Mem0 Platform + MCP vs Zep](https://www.anchorterminal.com/compare/mem0-vs-zep.md)\n- [MemMachine vs Memori](https://www.anchorterminal.com/compare/memmachine-vs-memori.md)\n- [MemMachine vs Zep](https://www.anchorterminal.com/compare/memmachine-vs-zep.md)\n- [Memori vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memori-vs-memory-reference-server.md)\n- [Memori vs MemPalace](https://www.anchorterminal.com/compare/memori-vs-mempalace.md)\n- [Memori vs past.dev](https://www.anchorterminal.com/compare/memori-vs-past-dev.md)\n- [Memori vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memori-vs-supermemory.md)\n- [Memori vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory.md)\n- [Memori vs Tokenrip](https://www.anchorterminal.com/compare/memori-vs-tokenrip.md)\n- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)\n- [MemPalace vs Zep](https://www.anchorterminal.com/compare/mempalace-vs-zep.md)\n- [past.dev vs Zep](https://www.anchorterminal.com/compare/past-dev-vs-zep.md)\n- [Supermemory API + MCP vs Zep](https://www.anchorterminal.com/compare/supermemory-vs-zep.md)\n- [TencentDB Agent Memory vs Zep](https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep.md)\n- [Tokenrip vs Zep](https://www.anchorterminal.com/compare/tokenrip-vs-zep.md)\n- [AI Memory vs Memori](https://www.anchorterminal.com/compare/ai-memory-vs-memori.md)\n- [AI Memory vs Zep](https://www.anchorterminal.com/compare/ai-memory-vs-zep.md)\n- [Context Mode Engine vs Memori](https://www.anchorterminal.com/compare/context-mode-vs-memori.md)\n- [Context Mode Engine vs Zep](https://www.anchorterminal.com/compare/context-mode-vs-zep.md)\n- [Graphicle vs Memori](https://www.anchorterminal.com/compare/graphicle-vs-memori.md)\n- [Graphicle vs Zep](https://www.anchorterminal.com/compare/graphicle-vs-zep.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": "Memori vs Zep", "url": "" } ], "description": "Zep scores 71 (BB) to Memori's 44.2 (E) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Memori E 44.2", "Zep BB 71", "scores" ], "h1": "Memori vs Zep", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/memori-vs-zep", "published": "2026-10-01", "section": "tools", "title": "Memori vs Zep for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/memori-vs-zep" }, "tokens": { "markdown": 5150, "slim": 2980 }, "version": 1 }