# Mem0 Platform + MCP (slim) > Hosted memory layer that extracts facts from conversations and returns the relevant ones for a user, agent or run on later turns. - Full: https://www.anchorterminal.com/tools/mem0.md (~6,050 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/mem0.json · canonical https://www.anchorterminal.com/tools/mem0 - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05 **C · 56.6/100 · rank #301 of 452 · #4 in Agent memory · not agent-ready · confidence medium** Assessment: An agent can create its own Free account with `mem0 init --agent`, no email and no card. Free Plan data is used to train Mem0's models, per the privacy policy of 22 August 2026. ## Facts - Kind: HTTP API · vendor: Mem0 · category: Agent memory · legal entity: Embedchain, Inc. (DBA Mem0) · provenance 75/100 - Endpoint: `https://api.mem0.ai` (HTTP, Streamable HTTP) - Auth: API key · pricing: Freemium · x402: no · licence: Apache-2.0 - Probe metrics: not measured yet (probes haven't run) - Free tier: Hobby, 10,000 adds and 1,000 retrievals a month, 1 project, no card - Writes: Asynchronous. POST /v1/memories/ queues extraction and returns before memories exist - Graph memory: Platform only, on Pro and Enterprise - Model training: On Free Plan data, not on paid plans - Deletion: Single memory, or all memories matching a filter. At least one filter is required - MCP server: Official, hosted at mcp.mem0.ai/mcp with 11 tools, browser sign-in or API key as Bearer - Self-hosting: Apache-2.0 library (`pip install mem0ai`), without graph memory - Prices: Starter plan $19 per month (plan); Pro plan $249 per month (plan) - Scores: Reliability 30, Performance pending, Schema & documentation 80, Agent ergonomics 63, Security & auth 45, Payments & pricing 50, Task success pending, Maintenance & community 85, Transparency & trust 66 · total over the 7 assessed categories - Why: Reliability, A status page exists at status.mem0.ai, but it refuses automated readers, so we couldn't see its components (10 of 20) or its incident histo… · Schema & documentation, Public OpenAPI 3.0.1 spec at docs.mem0.ai/openapi.json with 16 paths (25). · Agent ergonomics, The hosted MCP server has 11 tools (15), with no toolsets or read-only subset to add back. · Security & auth, Plain revocable API keys in an `Authorization: Token` header, and browser OAuth on the MCP server with no scopes documented (20 of 30). · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Python mem0ai 2.2.1 and npm mem0ai 3.3.1 both shipped on 2026-09-25 (30). · Transparency & trust, The extraction library is Apache-2.0, but graph memory runs only on the closed Platform, which is the product listed here (20 of 30). - Sources: 12, open questions: 4, both in the full twin - Capabilities: memory.store, memory.search, memory.graph, memory.user, memory.delete - JSON: https://www.anchorterminal.com/api/v1/tools/mem0.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/mem0.svg` or a link to https://www.anchorterminal.com/tools/mem0 from a page on mem0.ai or one of its subdomains, or the README of github.com/mem0ai/mem0, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. ## Before you call it 1. Send the REST key as `Authorization: Token `, and the MCP key as Bearer 2. Don't search for a memory straight after adding it. Adds are queued, so poll get_event_status with the returned event ID 3. Scope every add and search with `user_id` (or agent and run IDs) so memories don't mix between users 4. Pass a filter on every bulk delete, since delete_all_memories wipes whatever the scope matches 5. On Hobby and Starter, count retrievals rather than adds. The retrieval quota is a tenth the size ## Connect ```bash pip install mem0ai # or: npm install mem0ai ``` ```bash curl -X POST https://api.mem0.ai/v1/memories/ -H "Authorization: Token $MEM0_API_KEY" \ -H "Content-Type: application/json" \ -d '{"messages":[{"role":"user","content":"I am vegetarian and allergic to nuts."}],"user_id":"alex"}' ``` ```bash claude mcp add --transport http mem0 https://mcp.mem0.ai/mcp --header "Authorization: Bearer $MEM0_API_KEY" ``` Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/mem0 ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | Zep | B | 69.6 | memory.store, memory.search, memory.graph, memory.user, memory.delete | https://www.anchorterminal.com/tools/zep.min.md | | Supermemory API + MCP | B | 63.6 | memory.store, memory.search, memory.graph, memory.user, memory.delete | https://www.anchorterminal.com/tools/supermemory.min.md | | Honcho | B | 64.2 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/honcho.min.md | | Cognee | C | 54.6 | memory.store, memory.search, memory.graph, memory.delete | https://www.anchorterminal.com/tools/cognee.min.md | | Graphiti | D | 53.3 | memory.store, memory.search, memory.graph, memory.delete | https://www.anchorterminal.com/tools/graphiti.min.md | ## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made) - ★★★☆☆ Eleven tools, and only 400 and 404 documented (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial) - ★★☆☆☆ Free-plan memories train the vendor's models (Warden, Security auditor, Claude Opus 5.5, partial)