# LangChain on Amazon Bedrock — companion artifacts

Companion artifacts for the FactualMinds post
**Building AI Applications and Agents with LangChain on AWS**.

**Public URLs:** `https://www.factualminds.com/examples/architecture-blog-2026/langchain-bedrock/{path}`

## Demo disclaimer

These files are **architecture diagrams and syntax-checkable stubs**, not a production deploy and **not** an anonymized client engagement.

- Account IDs, model IDs, Knowledge Base IDs, and Gateway ARNs are placeholders.
- Do **not** treat stub latencies or cost numbers as measured outcomes.
- First-party platform signals cited in the post (Gateway ~180→95 ms canary, AgentCore TCO worksheet) come from earlier published FactualMinds AgentCore posts — not from these stubs.

## Status snapshot (verify before you build)

Checked **August 27, 2026** against AWS and LangChain docs:

| Capability | Status |
| ---------- | ------ |
| `ChatBedrockConverse` in `langchain-aws` | Documented — AWS Database Blog + `langchain-aws` package |
| `create_agent` (model + tools + prompt + middleware) | Current LangChain OSS docs |
| AgentCore Runtime is framework-agnostic | Documented — [What is AgentCore](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html) |
| AgentCore Memory + LangChain / LangGraph | Documented — [Memory integrate](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory-integrate-lang.html) |
| Named LangChain section on AWS “Use any agent framework” page | **LangGraph is the named LangChain-ecosystem sample**; LangChain apps still deploy as BYO Runtime containers / CLI scaffolds |
| Runtime architecture | **ARM64** containers; x86 images will not start |

## Versions (assumed)

| Component | Assumed version / note |
| --------- | ---------------------- |
| Python | 3.12+ |
| `langchain` | `create_agent` |
| `langchain-aws` | `ChatBedrockConverse` |
| `bedrock-agentcore` | `BedrockAgentCoreApp` when hosting on Runtime |
| `boto3` | ≥ 1.38.0 |
| Default model in stub | Cross-region inference profile `us.anthropic.claude-sonnet-4-6` — **swap** to a model your account allows |

## Layout

| Path | Purpose |
| ---- | ------- |
| [`architecture.drawio`](architecture.drawio) | App → LangChain → tools → AgentCore → Bedrock → enterprise systems |
| [`langchain_bedrock_stub.py`](langchain_bedrock_stub.py) | `ChatBedrockConverse` + `create_agent` + Runtime entrypoint sketch |
| [`monday-checklist.md`](monday-checklist.md) | Ship-this-week gate list |

## Local checks

```bash
python3 -m py_compile langchain_bedrock_stub.py
```

## Related posts

- [LangChain + Bedrock](https://www.factualminds.com/blog/langchain-aws-bedrock-2026/)
- [LangGraph + AgentCore](https://www.factualminds.com/blog/langgraph-aws-bedrock-agentcore-2026/)
- [AgentCore production guide](https://www.factualminds.com/blog/amazon-bedrock-agentcore-production/)
- [RAG on Bedrock Knowledge Bases](https://www.factualminds.com/blog/how-to-build-rag-pipeline-amazon-bedrock-knowledge-bases/)
- [AgentCore pricing calculator](https://www.factualminds.com/tools/amazon-bedrock-agentcore-pricing-calculator/)