skills.rest
RamVegiraju
RamVegirajuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-openai-memory

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

4|4|Updated Jan 5, 2026
Search Tags:#memory#openai#session#memory-management#databricks#conversation-history#lakebase
One-click install
npx skills add https://github.com/RamVegiraju/databricks-samples --skill agent-openai-memory
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-openai-memory
Source: https://github.com/RamVegiraju/databricks-samples/tree/main/.claude/skills/agent-openai-memory
Command: npx skills add https://github.com/RamVegiraju/databricks-samples --skill agent-openai-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Keeps conversation history for OpenAI agents by persisting memory to Databricks Lakebase, enabling long-running and context-aware interactions without manual state management.

Core Features & Use Cases

  • Session persistence with AsyncDatabricksSession
  • Context retrieval across requests
  • Lakebase-backed long-term memory for user preferences
  • Multi-turn conversations in production apps

Quick Start

Start the server and send your first user message to create a persistent memory-enabled session.

Frequently Asked Questions about agent-openai-memory

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

FAQPage Schema
How do I add memory to OpenAI agents for multi-turn conversations?▼

To add memory to OpenAI agents, you can use Lakebase-backed sessions to store and retrieve conversation history across requests. This requires the databricks-openai[memory] package and an AsyncDatabricksSession to persist context for interactive apps.

What is Lakebase used for in OpenAI session management?▼

Lakebase is used to persist conversation history for OpenAI agents, enabling long-running and context-aware interactions. It stores multi-turn memory so production workflows can retain user preferences without manual state management.

Do I need a specific environment variable to use Lakebase for conversation history?▼

Yes, you need to configure the LAKEBASE_INSTANCE_NAME environment variable to use Lakebase for conversation history. You also need the databricks-openai[memory] dependency and an AsyncDatabricksSession instance.

Can I use Databricks Lakebase to store user preferences across OpenAI agent requests?▼

Yes, you can use Databricks Lakebase to store user preferences across OpenAI agent requests. Lakebase-backed long-term memory retains context across requests, improving context retention in interactive applications.

What are the limitations of using Lakebase for OpenAI agent memory?▼

Lakebase for OpenAI agent memory requires a configured LAKEBASE_INSTANCE_NAME and the databricks-openai[memory] dependency. It is specifically designed for Databricks environments, meaning it may not suit workflows outside this ecosystem.

Related Skills

Explore More Software Engineering Skills→
databricksdatabricks
183

agent-openai-memory

Persist multi-turn conversation history using OpenAI Agents SDK Sessions and Databricks Lakebase.

Official
Intermediate
victorlouvictorlou
4

agent-openai-memory

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

Community
Intermediate
databricks-solutionsdatabricks-solutions
5

lakebase-memory-patterns

Implement Databricks Lakebase memory patterns for stateful LangGraph agents.

Official
Advanced
AshDaxAshDax

agent-openai-memory

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

Community
Advanced