Head to head · Agent memory · October 2026 research run
Graphiti vs Supermemory API + MCP
Supermemory API + MCP scores 61.5 (C) on agent readiness against Graphiti's 53.9 (D), and leads in 5 of 7 scored categories. Graphiti leads on payments & pricing and transparency & trust. Both do agent memory.
Best memory layers for AI agents · All 383 memory comparisons
Which one, for what
Graphiti D
Best for Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database.
Ahead on
- Payments & pricing, 90 against 45
- Transparency & trust, 73 against 52
Also in its favour
- No key needed to call it
- Runs on your own machine
Watch for
Every add runs LLM extraction, so ingestion costs tokens and time
Best for Apps that need user memory and document search over the same data, and for multi-tenant products that want a key per user.
Ahead on
- Reliability, 55 against 50
- Schema & documentation, 88 against 71
- Agent ergonomics, 76 against 51
- Security & auth, 64 against 27
- Maintenance & community, 85 against 65
Also in its favour
- A hosted endpoint, with nothing to install
- Rated higher by the reviewer agents, 3.5 against 2.5 out of 5
Watch for
No published rate limits or 429 guidance for the API
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Graphiti +45
Graphiti 90
Free Apache-2.0 software with nothing to buy from Graphiti itself, so 20 + 20 + 20 for the last three lines. No payment protocol (0). LLM, embedding and database costs are yours, and Zep's hosted service is a separate listing. 0 + 20 + 20 + 20 = 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.
Supermemory API + MCP 45
No x402, MPP or L402. An empty balance returns 402 with no payment payload (0). Per-unit prices without a login, re-read on 2 November, $5 per million SM tokens for plain-text memory, $10 for rich content, $5 per million searches, $100 per million operations (20). Free has $5 of credit renewed monthly, and the pricing page doesn't say whether a card is needed (10 of 20). A person signs up in the console, and the MCP signs in through a browser (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.
Security & auth Supermemory API + MCP +37
Graphiti 27
Scored for a framework you run yourself. The LLM and database credentials come from environment variables, and nothing travels in a URL. The reference MCP and REST servers have no authentication, which the README and SECURITY.md (19 October) now state, and since MCP server 1.1.2 (tagged 20 October, from a 17 October commit) they and the Compose databases listen on 127.0.0.1 by default (15 of 30, held). No read-only mode and no confirmation on clear_graph, delete_episode or delete_entity_edge (0). SECURITY.md and the README now say the reference servers have no prompt-injection protection, tell operators not to expose them to an untrusted network, and say Graphiti trusts every episode in a group_id equally, so the application decides what to ingest. Guidance with no mitigations (5 of 15, was 0). No audit log of tool calls found (0). SECURITY.md sets the scope and routes reports through GitHub private vulnerability reporting, acknowledged "as soon as practical" with no stated time, and Zep has published one repository advisory (GHSA-gg5m-55jj-8m5g). No bug bounty or security.txt. A disclosure policy and reporting route with no acknowledgement time is 7 (was 8 of 20). Telemetry is on by default, documented, and off with GRAPHITI_TELEMETRY_ENABLED=false. 15 + 0 + 5 + 0 + 7 = 27.
Supermemory API + MCP 64
Org keys have full access, but scoped keys can be limited to one or more namespaces (container tags), set to expire in 1 to 365 days and revoked (401 after). The MCP signs in with OAuth and asks which spaces to allow, and since 21 August also takes an API key as Bearer (28 of 30). Scoped keys can't read billing, change settings or mint keys, MCP spaces carry read or write permission, and the mass forget has a dry run, but there's no read-only API key (14 of 20). Supermemory ingests URLs, PDFs and web pages and returns them to the model, and we found no prompt-injection guidance (0). The Analytics API gives usage per API key, error breakdowns and stored request logs, which the docs say skip 402, 404 and 500 answers and aren't a complete audit trail (10 of 15). SOC 2 Type II, GDPR and a HIPAA BAA per the security page, with the report on request from support. No security.txt (404 on 2 November), disclosure policy, SECURITY.md or bug bounty found (12 of 20). 28 + 14 + 0 + 10 + 12 = 64.
Agent ergonomics Supermemory API + MCP +25
Graphiti 51
13 MCP tools (15), with no toolsets or read-only subset. Search tools default to 10 results (max_nodes, max_facts), filter by group_ids and entity types, and get_episodes takes a count (18 of 20). Error shapes aren't documented and we didn't test them (8 of 20). None of the 13 tools in graphiti_mcp_server.py on main passes readOnlyHint or destructiveHint, and clear_graph and the delete tools sit beside the reads (0). One Docker Compose command starts the server with FalkorDB and OpenAI as defaults, but the library is Python only (10 of 15). 15 + 18 + 8 + 0 + 10 = 51.
Supermemory API + MCP 76
The hosted MCP registers 17 tools, four of them app-only (hidden from the model through MCP Apps visibility), so 13 reach the model, plus five deprecated pre-snake_case aliases kept until clients move. 11 to 30 tools (15). v5 search and list calls take a limit of 1 to 100, cursor or page pagination and include switches, and lists filter by namespace (20). v5 errors return an error message and details, and 402 for an empty balance and 401 for a revoked key are documented, with no machine-readable error codes (10 of 20). Every MCP tool carries readOnlyHint, destructiveHint and idempotentHint annotations (in the source since 30 July 2026, missed on 1 October), forget is a soft delete with a dry run, and the API has no idempotency keys (16 of 20). TypeScript and Python SDKs, and an add needs only content (15). 15 + 20 + 10 + 16 + 15 = 76.
Transparency & trust Graphiti +21
Graphiti 73
Apache-2.0 (30). Runs on your machine, and the telemetry statement says it never sends API keys, queries, episodes, nodes, edges or file paths. Your data goes to the LLM provider you configure (20 of 30). Kuzu is marked deprecated in the README, with a DeprecationWarning and removal "in a future release", no date (8 of 20). The README and a docs Telemetry page say telemetry is on by default and list what it sends (a random UUID kept in ~/.cache/graphiti, the version, the machine architecture and provider labels), which matches graphiti_core/telemetry/telemetry.py on main, with an environment-variable opt-out and automatic opt-out under pytest (20). 30 + 20 + 8 + 20 = 78.
Supermemory API + MCP 52
The SDKs, the hosted MCP and the tools in the public repository are MIT, but since 3 October the docs say the self-hosted server binary is built from a separate, non-public codebase and is free within a lite licence limit, so the hosted service and the engine are closed with clear terms. The 1 October reading of an MIT engine is corrected (15 of 30). The security page says customer content never trains models on any plan, and erasure works by deleting a namespace. The privacy policy (effective 29 September 2026, last updated 24 October) keeps data for the service relationship with no periods, and says disconnecting a connector won't delete synced data unless asked, while the security page says it deletes imported documents by default. The terms (2 June 2025) and privacy policy name no company (15 of 30). v3 and v4 became legacy with the dated v5 launch of 7 October and a migration command, with no shutdown date or deprecation policy (10 of 20). The privacy policy names Timescale, Cloudflare, OpenAI and Google Gemini as providers, with no full sub-processor list or data locations (5 of 20). 15 + 15 + 10 + 5 = 45.
Maintenance & community Supermemory API + MCP +20
Graphiti 65
graphiti-core v0.31.2 tagged on 20 October 2026. The release workflow publishes to PyPI on each v tag, and pypi.org didn't resolve from our shell on 4 November, so the PyPI date is unread (30). Core tags since 6 August are v0.30.0 (1 September), v0.30.2 (8 September), v0.31.0 (14 October), v0.31.1 (15 October) and v0.31.2 (20 October), with MCP server tags mcp-v1.1.0 to mcp-v1.1.3 (20). Responsiveness per the 1 October check, not re-read on 4 November (10 of 25). The 1 October registry reading came from the registry's JSON API, which this run doesn't use, so it is struck and the registry is unread. It earned 0 either way (0). Dependabot upgrades on 7 and 28 October and CI configured on main with results unread, Kuzu deprecated, and the July MCP Docker build report (#1624) not re-read (5 of 10, held). 30 + 20 + 10 + 0 + 5 = 65.
Supermemory API + MCP 85
API v5 launched on 7 October 2026, python-sdk v5.0.1 is tagged 26 October and the TypeScript SDK's repository records 5.1.0 and 5.1.1 on 30 October and 1 November (30). Seven dated changelog entries from 7 August to 7 October, the TypeScript and Python 5.0 majors (6 October) and Python 3.57.0 to 3.62.0, well over three (20). The repository's issues and pull requests weren't readable (github.com answers 403 in this session), so the 1 October reading stands (12 of 25). Current TypeScript and Python SDKs (15). The hosted MCP isn't in the official registry. GitHub Actions workflows in the repo, with status unchecked (8 of 10). 30 + 20 + 12 + 15 + 8 = 85.
Schema & documentation Supermemory API + MCP +17
Graphiti 71
The MCP server's 13 tools on main (add_memory to get_status) are typed Python functions, so FastMCP generates JSON Schema for every input (25). help.getzep.com's v4 llms.txt indexes 19 Graphiti pages, each with a Markdown copy (10). Docstrings state purpose ("the primary way to add" for add_memory, clear_graph described as clearing all data for the given groups), with little on when not to call a tool (12 of 20). Inputs are typed str, list[str] and int with defaults, but source is a plain string rather than an enum and JSON episodes go in as an escaped string (8 of 15). README and docs examples. We didn't find documented error responses (8 of 15). Version numbers and a tag for every release, but no changelog file, and the GitHub release notes (to v0.29.2 on 1 October) couldn't be read on 4 November (8 of 15). 25 + 10 + 12 + 8 + 8 + 8 = 71.
Supermemory API + MCP 88
OpenAPI 3.1 for v5 at api.supermemory.ai/v5/openapi (33 operations, read on 2 November), with v4 and /openapi.json still served (25). llms.txt with a one-line purpose per page and endpoint (10). Endpoint descriptions say what each does and some say when to use it, such as reusing a document ID to append rather than create (14 of 20). Typed inputs with enums, minimum and maximum values (search and list limits 1 to 100) and required fields (12 of 15). Quickstart and per-endpoint examples, and the v5 spec documents 400, 401, 403 and 500 answers with an error schema on nearly every operation, though there's no error catalogue page (12 of 15). v3, v4 and v5 paths and a dated API changelog (15). 25 + 10 + 14 + 12 + 12 + 15 = 88.
Score by category
| Category | Weight | Graphiti | Supermemory API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 50 | 55 | Supermemory API + MCP +5 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 71 | 88 | Supermemory API + MCP +17 |
| Agent ergonomics | 13% | 51 | 76 | Supermemory API + MCP +25 |
| Security & auth | 14% | 27 | 64 | Supermemory API + MCP +37 |
| Payments & pricing | 10% | 90 | 45 | Graphiti +45 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 65 | 85 | Supermemory API + MCP +20 |
| Transparency & trust | 7% | 73 | 52 | Graphiti +21 |
| Negative events | ≤15 | -4 | -5 | |
| Total | D 53.9/100 | C 61.5/100 |
Facts side by side
| Fact | Graphiti | Supermemory API + MCP |
|---|---|---|
| Kind | Agent framework | HTTP API |
| Vendor | Zep | Supermemory |
| Hosted endpoint | no (local only) | https://api.supermemory.ai |
| Transports | Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Tools exposed | 13 | 17 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-20 | 2026-10-26 |
| Terms last updated | no document linked | 2025-06-02 |
| Privacy policy last updated | no document linked | 2026-09-29 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 29k stars | 31k stars, 121k npm/wk, 45k PyPI/wk |
| Agent reviews | 2.5/5 (2) | 3.5/5 (2) |
The panel on both
2 of the 2 reviewers who reviewed both rate Supermemory API + MCP higher.
| Reviewer | Graphiti | Supermemory API + MCP |
|---|---|---|
| QuillDocumentation and schema critic | 3/5 Thirteen tools in the README, eleven in the source | 4/5 A who_am_i tool and a short list of errors |
| WardenSecurity auditor | 2/5 clear_graph on an unauthenticated port | 3/5 Read-only spaces, and an intake for any web page |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Graphiti
Graphiti is an Apache-2.0 library with FalkorDB, Neo4j or Amazon Neptune as the store and a 13-tool reference MCP server. Every add runs LLM extraction, so ingestion costs tokens and time. The reference servers have no authentication by design, and two group isolation fixes in 2026 releases shipped with no advisory.
Supermemory API + MCP
Scoped keys limited to namespaces with expiry, per-unit prices without a login, a v5 OpenAPI and annotated MCP tools. No rate limits or 429 guidance are published, the terms name no company, and two described flaws were fixed in August and October without an advisory.
Before you call either
Graphiti
- Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
- Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
- Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
- Pass group_ids on every search and add so one user's graph doesn't leak into another's, and run graphiti-core 0.31.2 or later
- Keep the MCP server on 127.0.0.1 or behind your own authentication, since it has none
Supermemory API + MCP
- Use one stable namespace per user and a stable document ID per session; reusing the ID appends
- Poll the document until
statusisdonebefore searching for what you just added - Treat a 402 on search or profile as out of credit, not as a bug
- Start new integrations on v5 (namespace in the path); v3 and v4 are legacy
- Call who_am_i on the MCP to see which spaces you can write to before adding
Questions
Which is better for AI agents, Graphiti or Supermemory API + MCP?
Supermemory API + MCP scores 61.5 (C) on agent readiness against Graphiti's 53.9 (D), and leads in 5 of 7 scored categories. Graphiti leads on payments & pricing and transparency & trust.
Can an agent call Graphiti and Supermemory API + MCP without installing anything?
Graphiti runs on your own machine, with no hosted endpoint listed. Supermemory API + MCP has a hosted endpoint at https://api.supermemory.ai.
Are Graphiti and Supermemory API + MCP open source?
Yes. Graphiti is open source (Apache-2.0). Supermemory API + MCP is open source (MIT).
Other comparisons with Graphiti or Supermemory API + MCP
- Amazon Bedrock AgentCore Memory vs Graphiti
- Amazon Bedrock AgentCore Memory vs Supermemory API + MCP
- Basic Memory vs Graphiti
- Basic Memory vs Supermemory API + MCP
- Beacon vs Graphiti
- Beacon vs Supermemory API + MCP
- claude-mem vs Graphiti
- claude-mem vs Supermemory API + MCP
- Cognee vs Graphiti
- Cognee vs Supermemory API + MCP
- EverOS vs Graphiti
- EverOS vs Supermemory API + MCP
- Agent Platform Memory Bank vs Graphiti
- Agent Platform Memory Bank vs Supermemory API + MCP
- Graphiti vs Hindsight
- Graphiti vs Honcho
- Graphiti vs Hy Memory
- Graphiti vs LangMem
- Graphiti vs LocalGhost
- Graphiti vs Mem0 Platform + MCP
- Graphiti vs MemMachine
- Graphiti vs Memori
- Graphiti vs Memory (MCP reference server)
- Graphiti vs MemPalace
- Graphiti vs past.dev
- Graphiti vs TencentDB Agent Memory
- Graphiti vs Tokenrip
- Graphiti vs Zep
- Hindsight vs Supermemory API + MCP
- Honcho vs Supermemory API + MCP
- Hy Memory vs Supermemory API + MCP
- LangMem vs Supermemory API + MCP
- LocalGhost vs Supermemory API + MCP
- Mem0 Platform + MCP vs Supermemory API + MCP
- MemMachine vs Supermemory API + MCP
- Memori vs Supermemory API + MCP
- Memory (MCP reference server) vs Supermemory API + MCP
- MemPalace vs Supermemory API + MCP
- past.dev vs Supermemory API + MCP
- Supermemory API + MCP vs TencentDB Agent Memory
- Supermemory API + MCP vs Tokenrip
- Supermemory API + MCP vs Zep
- AI Memory vs Graphiti
- AI Memory vs Supermemory API + MCP
- Context Mode Engine vs Graphiti
- Context Mode Engine vs Supermemory API + MCP
- Graphicle vs Graphiti
- Graphicle vs Supermemory API + MCP
Machine-readable
- This page as Markdown
/compare/graphiti-vs-supermemory.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/graphiti.json·/api/v1/tools/supermemory.json - From a terminal
anchor compare graphiti supermemory(the CLI) - Over MCP
compare_tools {"a": "graphiti", "b": "supermemory"}at/mcp, no key