Loading...

XML

Word

Printable

JSON

Type: Epic
Resolution: Duplicate
Priority: Major - P3
Fix Version/s: None
Affects Version/s: None
Component/s: ABX
Labels:

Epic Name:
[OpenAI Agents SDK] MongoDB Integration
Documentation Changes:
None
Epic Status:
To Do

Quarter:
- FY27Q3
Scope Cost Estimate:
0
Cost to Date:
0
Final Cost Estimate:
0
Cost Threshold %:
100
Confidence Status:
🔵 Done
Latest Project Update:
None
Detailed Project Statuses:

Hide

2026-10-28 - 🔵 Done
No project update provided

Show
2026-10-28 - 🔵 Done No project update provided

Aha! Reference:
None
Tracking Level:
None
Risk Status:
None
Exec Notes:
None
Goal Name(s):
None
Goal Link:
None
Goal Tier(s):
None

What it is:

Provide MongoDB-backed session persistence for the OpenAI Agents SDK in Python TypeScript. Persist conversation history in MongoDB so applications can reuse session state across runs and resume conversations without building their own MongoDB adapter.

The Python MongoDBSession implementation has already been merged into the OpenAI Agents Python SDK (PR #2902, merged April 17, 2026). The remaining scope includes JavaScript/TypeScript.

Why it matters:

The OpenAI Agents SDK lets applications provide a custom session backend. MongoDB gives teams already using Atlas a durable, queryable place for agent conversation items and session metadata, and can reduce the need to build a separate persistence integration. MongoDB’s document model accommodates structured conversation content such as messages and tool calls.

This adds MongoDB as a database-backed session option for OpenAI Agents SDK users; it does not position MongoDB as the SDK’s recommended or exclusive production backend.

Related links:

Implement a MongoDB-backed Session for the OpenAI Agents JavaScript/TypeScript SDK, conforming to the SDK’s session semantics for loading and persisting history, ordering, limits, mutations/clearing, and lifecycle behavior.

Submit the JavaScript/TypeScript adapter or example for upstream consideration. Upstream acceptance is desirable, but MongoDB-owned setup guidance and a runnable example must not depend on the timing of an external merge.

Scope:

Implement a MongoDB-backed Session/SessionStore adapter for the OpenAI Agents SDK, in both Python and JavaScript
Align with the SDK's existing Session protocol so it's a drop-in alternative to S3/Redis/Postgres adapters
Get the adapter merged as a first-party reference example in the SDK's examples directory (matching S3/Redis/Postgres precedent)
Coordinate with docs, DevRel, and LRA process ahead of launch

Acceptance Criteria:

TypeScript MongoDB session backend implements the OpenAI Agents SDK Session interface and passes protocol/conformance tests.

Submit the JavaScript/TypeScript adapter/example for upstream consideration; record the outcome without making external merge timing a release blocker.