Technical analysis of the stateful orchestration required for agents. Discusses sub-millisecond state access, memory architecture (short/long-term), and sub-millisecond vector retrieval for RAG.
Related Articles
Deploying Long-Horizon Agents in Production with Durable Execution and Deepagents Deploy
Learn how to deploy long-running AI agents reliably using purpose-built runtime infrastructure. This guide explains durable execution for resuming agent workflows after failures, checkpoint-based memory for short- and long-term state, human-in-the-loop interruption and resumption, and production-grade observability with tracing and replay. It details how LangSmith Deployment (LSD) and Agent Server provide primitives like task queues, persistence via PostgreSQL, RBAC-based multi-tenancy, middleware guardrails, streaming, and cron scheduling. Discover how deepagents deploy packages these capabilities to eliminate infrastructure overhead and enable scalable, fault-tolerant agent systems.
Continual Learning in AI Agents Happens Across Model, Harness, and Context Layers
Learn how AI agents improve over time by optimizing three distinct layers: model weights, harness infrastructure, and external context/memory. The piece breaks down techniques like SFT and RL for model updates, harness optimization via trace analysis and systems like Meta-Harness, and dynamic context learning through persistent memory, tenant-level configuration, and runtime updates. It highlights practical strategies such as offline evaluation loops, agent trace logging, and 'dreaming' workflows to iteratively refine agent performance without retraining models, emphasizing scalable alternatives to weight updates.
Autonomous context compression
Deep Agents introduces a tool in its Python SDK and CLI that allows agents to autonomously compress their context windows at optimal moments. Instead of relying on fixed token thresholds, agents can now summarize older context when it becomes less relevant—such as at task boundaries, before large context ingestion, or after extracting key insights. This improves efficiency, reduces context rot, and aligns memory management with the agent’s reasoning process. The system retains recent messages (about 10% of context) while summarizing older interactions, enabling better long-horizon performance without manual intervention or rigid harness tuning.