skills.rest
AshDax
AshDaxCOMMUNITY
Explore all skills by this author →
GitHub

agent-openai-memory

Persist conversation history for multi-turn OpenAI Agents SDK sessions using Databricks Lakebase.

Updated Mar 17, 2026
Search Tags:#memory#persistence#session#databricks#openai-agents-sdk#lakebase
One-click install
npx skills add https://github.com/AshDax/sec_scrapper_agent --skill agent-openai-memory-ashdax
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-openai-memory
Source: https://github.com/AshDax/sec_scrapper_agent/tree/main/agent-openai-agents-sdk-long-running-agent/.claude/skills/agent-memory
Command: npx skills add https://github.com/AshDax/sec_scrapper_agent --skill agent-openai-memory-ashdax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Stateful Memory with OpenAI Agents SDK Sessions skill provides persistent conversation history by using AsyncDatabricksSession to connect to a Databricks Lakebase instance, enabling multi-turn interactions without losing context.

Core Features & Use Cases

  • Session-backed memory: automatically retrieves prior messages and prepends them to new inputs to maintain context.
  • Seamless integration: uses OpenAI Agents SDK Sessions with Lakebase for durable storage of conversation history and session data.
  • Easy configuration: relies on LAKEBASE_INSTANCE_NAME and standard databricks.yml resources to deploy memory-enabled agents.

Quick Start

Create an AsyncDatabricksSession with a unique session_id and pass it to the agent runner to enable memory across requests.

Frequently Asked Questions about agent-openai-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I persist conversation history for OpenAI Agents SDK across multiple requests?▼

You can persist conversation history for OpenAI Agents SDK by using AsyncDatabricksSession to connect to a Databricks Lakebase instance, which stores session data and maintains context across multi-turn interactions.

How does session-backed memory work with Databricks Lakebase?▼

Session-backed memory automatically retrieves prior messages from Databricks Lakebase and prepends them to new inputs, allowing the agent to maintain context without losing previous conversation history.

Do I need a LAKEBASE_INSTANCE_NAME to enable persistent memory for AI agents?▼

Yes, you need to configure the LAKEBASE_INSTANCE_NAME environment variable to connect to your Databricks Lakebase instance and deploy memory-enabled agents successfully.

Can I use OpenAI Agents SDK Sessions with Databricks for durable conversation storage?▼

Yes, OpenAI Agents SDK Sessions integrates directly with Databricks Lakebase to provide durable storage of conversation history and session data for long-running agent conversations.

What is the best way to maintain multi-turn context in AI agent sessions?▼

The best way to maintain multi-turn context is creating an AsyncDatabricksSession with a unique session_id and passing it to the agent runner, which automatically retrieves and prepends prior messages to new inputs.

Related Skills

Explore More Software Engineering Skills→
RamVegirajuRamVegiraju
4

agent-openai-memory

Store and retrieve multi-turn conversation history for OpenAI agents using Lakebase-backed sessions.

Community
Advanced
victorlouvictorlou
4

agent-openai-memory

Store and retrieve multi-turn conversation history using OpenAI Agents SDK sessions.

Community
Intermediate
hafiznaveedchuhan-ctrlhafiznaveedchuhan-ctrl

scaffolding-openai-agents

Scaffold production AI agents with the OpenAI Agents SDK using async/await patterns.

Community
Advanced
sarimofficialsarimofficial

manage-conversation-db

Implement stateless conversation persistence with async database queries and user isolation.

Community
Intermediate