Memory 2: Compatibility and Configuration
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 101
- Forks
- 46
- Avg merge
- 6h 19m
- Merged PRs (30d)
- 23
Description
Before building endpoints:
- Pin
oracleagentmemoryto the exact initially validated release rather than the current open-ended>=26.6.0dependency inpyproject.toml. The repository generally pins server integrations, and the SDK already documents upcoming API removals. - Prove against the real Oracle database that:
- The existing async
oracledbpool works with the SDK's async APIs. - The configured database meets the SDK's required database capabilities.
- Schema creation and upgrades work under the intended schema owner.
- Existing LiteLLM model and OCI authentication settings can initialize the SDK LLM and embedder.
- The existing async
- Prefer
MemoryExtractionConfig; do not use the SDK's deprecated top-level extraction arguments. - Verify shutdown behavior for background extraction through
close_async().
Add a server-level AgentMemoryConfig, defaulting to disabled, containing:
- Enabled flag.
- Database alias.
- Memory LLM identity.
- Embedding model identity.
- OCI profile where applicable.
- Schema policy and table prefix or store ID.
- Semantic versus hybrid search strategy.
- Inline, background, or disabled extraction.
- Default and maximum TTL.
- Context-card and retrieval limits.
The database, embedding model, schema policy, and retention rules should remain operator-owned because changing them per browser session can create schema or index incompatibilities. Per-client settings may contain only consumption controls such as "use memory" and "automatically extract memories."
Use separate least-privilege identities:
- Migration or schema owner: permitted to create or upgrade the managed schema.
- Runtime user: only the DML and query privileges required for memory operations.
- Do not let every application startup perform opportunistic DDL. The SDK warns that schema upgrades can be long-running and that expiry cleanup may require scheduler privileges.
References:
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by inspecting pyproject.toml and the existing async oracledb, LiteLLM, and OCI configuration entry points, then read the referenced Stores and schema and time-to-live guides. Done means the validated SDK pin and server-level AgentMemoryConfig are defined, operator-owned settings and least-privilege identities are preserved, and the listed database, initialization, extraction, shutdown, and retention behaviors are verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, databases
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100