Durable agent memory with threads, runs and checkpoints
Save and restore workflow state over time: every query generates a thread, each run gets a run ID, and each node execution saves a checkpoint — so agents can recall past interactions across long engagements and recover seamlessly. Use SQLite locally and Cloud Spanner (or the Azure/AWS equivalents) in production.
online BOTH AI Agents & Automation
From AI Engineer — Paving the Road to Production: Governed Enterprise AI Agents — Harish Gaggar, Credit Karma at 17:00
Problem: Without memory management, agents cannot recall what was asked in past interactions or recover state across runs.
For: Teams building agents used across long, multi-session conversations
Products from this video
Amazon CloudWatch Cloud Spanner Elastic FastMCP Grafana Grafana Tempo JFrog Artifactory Kubernetes LangChain LangGraph Loki OpenTelemetry Prometheus Redis SQLite
Other takes on AI agent platforms and compute access
- Autonomous AI agents that perform administrative labor for underserved small businesses, starting with dental practices
- A personal, open-source AI agent that can be operated through messaging channels such as WhatsApp and Discord
- Enterprise AI concierge for customer, sales, and operational workflows
- AI appointment-scheduling assistant for healthcare providers
- Autonomous SEC-filing research desk with self-graded scorecards
- Production-ready inference hosting for open AI models