# Amazon Bedrock AgentCore Memory vs LangMem (slim)

> Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against LangMem's 47.9 (D), and leads in 6 of 7 scored categories. LangMem leads on payments & pricing. Both do memory store. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.md (~2,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.json · canonical https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against LangMem's 47.9 (D), and leads in 6 of 7 scored categories. LangMem leads on payments & pricing. Both do memory store.

- Amazon Bedrock AgentCore Memory: A 79.4, rank #12 of 842 · https://www.anchorterminal.com/tools/agentcore-memory.min.md
- LangMem: D 47.9, rank #734 of 842 · https://www.anchorterminal.com/tools/langmem.min.md
- Amazon Bedrock AgentCore Memory, good for Teams already on AWS that want per-user memory under IAM, KMS and Regional controls, with extraction run for them. Ahead on Reliability, 88 against 32; Schema & documentation, 92 against 55; Agent ergonomics, 86 against 66; Security & auth, 87 against 45; Maintenance & community, 83 against 15; Transparency & trust, 76 against 59. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install; Runs on your own machine.
- LangMem, good for Teams already on LangGraph that want memory tools and background extraction over a store they run. Ahead on Payments & pricing, 60 against 30. Also No key needed to call it; Open source.

| Category | Amazon Bedrock AgentCore Memory | LangMem |
| --- | --- | --- |
| Reliability (16%) | 88 | 32 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 92 | 55 |
| Agent ergonomics (13%) | 86 | 66 |
| Security & auth (14%) | 87 | 45 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 83 | 15 |
| Transparency & trust (7%) | 76 | 59 |

| Fact (where they differ) | Amazon Bedrock AgentCore Memory | LangMem |
| --- | --- | --- |
| Kind | HTTP API | SDK + MCP |
| Vendor | Amazon Web Services | LangChain |
| Hosted endpoint | `https://bedrock-agentcore.{region}.amazonaws.com` | no (local only) |
| Transports | HTTP, stdio |  |
| Auth | OAuth or key | None |
| Pricing | Pay per use | Free |
| Licence | Proprietary service under the AWS Customer Agreement and Service Terms. The `bedrock-agentcore` Python SDK and the `@aws/agentcore` CLI are Apache-2.0 | MIT |
| Tools exposed | 21 | none |
| llms.txt | yes | no |
| Last release | 2026-10-06 | 2025-10-27 |
| Terms last updated | 2026-10-01 | no document linked |
| Privacy policy last updated | 2026-05-18 | no document linked |
| Customer content may train models | yes, with an opt-out |  |
| Terms restrict automated access | yes |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | yes |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 776 stars, 1.1M npm/wk | 1.7k stars, 214k PyPI/wk |