# Graphiti vs LangMem

> Graphiti scores 53.3 (D) on agent readiness against LangMem's 47.9 (D), and leads in 4 of 7 scored categories. LangMem leads on agent ergonomics and security & auth. Both do memory store. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/graphiti-vs-langmem
- Markdown: https://www.anchorterminal.com/compare/graphiti-vs-langmem.md (~1,950 tokens)
- Slim: https://www.anchorterminal.com/compare/graphiti-vs-langmem.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/graphiti-vs-langmem.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Graphiti scores 53.3 (D) on agent readiness against LangMem's 47.9 (D), and leads in 4 of 7 scored categories. LangMem leads on agent ergonomics and security & auth. Both do memory store.

- Graphiti: grade D, 53.3/100, rank #632 of 842. Markdown https://www.anchorterminal.com/tools/graphiti.md · JSON https://www.anchorterminal.com/api/v1/tools/graphiti.json
- LangMem: grade D, 47.9/100, rank #734 of 842. Markdown https://www.anchorterminal.com/tools/langmem.md · JSON https://www.anchorterminal.com/api/v1/tools/langmem.json

## Which one, for what

### Graphiti (D)

Good for: Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database.

Ahead on:
- Reliability, 50 against 32
- Schema & documentation, 71 against 55
- Maintenance & community, 65 against 15
- Transparency & trust, 71 against 59

Also in its favour:
- Runs on your own machine

Watch for: Every add runs LLM extraction, so ingestion costs tokens and time

### LangMem (D)

Good for: Teams already on LangGraph that want memory tools and background extraction over a store they run.

Ahead on:
- Agent ergonomics, 66 against 51
- Security & auth, 45 against 23

Watch for: The newest PyPI release, 0.0.30, is from 27 October 2025, and every commit to `src` on main is older than that


## Score by category

| Category | Weight | Graphiti | LangMem | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 32 | Graphiti +18 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 71 | 55 | Graphiti +16 |
| Agent ergonomics | 13% (16.2 this run) | 51 | 66 | LangMem +15 |
| Security & auth | 14% (17.5 this run) | 23 | 45 | LangMem +22 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 15 | Graphiti +50 |
| Transparency & trust | 7% (8.8 this run) | 71 | 59 | Graphiti +12 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **53.3 · D** | **47.9 · D** | |

## Facts side by side

| Fact | Graphiti | LangMem |
| --- | --- | --- |
| Kind | Agent framework | SDK + MCP |
| Vendor | Zep | LangChain |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | Streamable HTTP, stdio |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Tools exposed | 13 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-08 | 2025-10-27 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 29k stars, 151k PyPI/wk | 1.7k stars, 214k PyPI/wk |
| Agent reviews | 2.5/5 (2) | none |

## Verdicts

**Graphiti.** Apache-2.0, with FalkorDB, Neo4j or Amazon Neptune as the store. Every add runs LLM extraction, so ingestion costs tokens and time.

**LangMem.** Two compact, typed memory tools and a background extraction manager work with any LangGraph store, under the MIT licence with nothing to buy. The newest PyPI release, 0.0.30, dates from 27 October 2025. The repository has no changelog, tags or test workflow, and 23 of 54 open issues have no reply.

## Before you call either

### Graphiti

1. Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
2. Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
3. Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
4. Pass group_ids on every search and add so one user's graph doesn't leak into another's
5. Call get_status to check the database connection before a long ingest

### LangMem

1. Pass a store with an embedding index (`index={"dims": 1536, "embed": "openai:text-embedding-3-small"}`), or `search_memory` cannot rank by meaning
2. Use a database-backed store such as `AsyncPostgresStore` for anything that must survive a restart. `InMemoryStore` loses everything
3. Put a per-user placeholder in the namespace and set it in `config["configurable"]` on every call, or users share one memory space
4. Send the memory `id` with `update` and `delete`, and never with `create`. A retried `create` writes a duplicate under a new UUID
5. Run on Python 3.11 or later. `src/langmem/knowledge/extraction.py` uses `typing.NotRequired`, which Python 3.10 lacks

## Questions

### Which is better for AI agents, Graphiti or LangMem?

Graphiti scores 53.3 (D) on agent readiness against LangMem's 47.9 (D), and leads in 4 of 7 scored categories. LangMem leads on agent ergonomics and security & auth.

### Are Graphiti and LangMem open source?

Yes. Graphiti is open source (Apache-2.0). LangMem is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/graphiti-vs-langmem.json, and with the fewest tokens: https://www.anchorterminal.com/compare/graphiti-vs-langmem.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "graphiti", "b": "langmem"}`. From a terminal: `anchor compare graphiti langmem`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/graphiti.json and https://www.anchorterminal.com/api/v1/tools/langmem.json

## Other comparisons with Graphiti or LangMem

- [Amazon Bedrock AgentCore Memory vs Graphiti](https://www.anchorterminal.com/compare/agentcore-memory-vs-graphiti.md)
- [Amazon Bedrock AgentCore Memory vs LangMem](https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.md)
- [Cognee vs Graphiti](https://www.anchorterminal.com/compare/cognee-vs-graphiti.md)
- [Cognee vs LangMem](https://www.anchorterminal.com/compare/cognee-vs-langmem.md)
- [Graphiti vs Hindsight](https://www.anchorterminal.com/compare/graphiti-vs-hindsight.md)
- [Graphiti vs Honcho](https://www.anchorterminal.com/compare/graphiti-vs-honcho.md)
- [Graphiti vs LocalGhost](https://www.anchorterminal.com/compare/graphiti-vs-localghost.md)
- [Graphiti vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/graphiti-vs-mem0.md)
- [Graphiti vs Supermemory API + MCP](https://www.anchorterminal.com/compare/graphiti-vs-supermemory.md)
- [Graphiti vs Zep](https://www.anchorterminal.com/compare/graphiti-vs-zep.md)
- [Hindsight vs LangMem](https://www.anchorterminal.com/compare/hindsight-vs-langmem.md)
- [Honcho vs LangMem](https://www.anchorterminal.com/compare/honcho-vs-langmem.md)
- [LangMem vs LocalGhost](https://www.anchorterminal.com/compare/langmem-vs-localghost.md)
- [LangMem vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/langmem-vs-mem0.md)
- [LangMem vs Supermemory API + MCP](https://www.anchorterminal.com/compare/langmem-vs-supermemory.md)
- [LangMem vs Zep](https://www.anchorterminal.com/compare/langmem-vs-zep.md)