How AI agents save memory: LangChain's approach
LangChain has shipped DeltaChannel in LangGraph 1.2, a new primitive that cuts memory use for long-running agents. Previously, the full state was saved at every step, which led to exponential growth. Now the system tracks only the changes (the delta) between steps and periodically writes full state snapshots. As a result, storage grows linearly, and Deep Agents v0.6 gets this by default with no reconfiguration needed.
AI-processed from LangChain Blog; edited by Hamidun News
Long-running AI agents run into a classic scaling problem: every step requires saving the full system state, so storage volumes grow exponentially as the agent keeps working.
What are long-running AI agents?
These are agents that run for hours or days. Under the traditional approach, they pile up tens of gigabytes of cached data as they execute each step.
- Nov 1, 2026Local models lose to Opus and Codex: 0.21 on a MacBook versus 1.00 for Codex
- Nov 1, 2026Adobe's EditAgent judge picks a usable edit 81.3% of the time, versus 74.8% for EditScore
- Nov 1, 202616 models tested on 7 search tools: Exa averaged 10.5 out of 14, SearXNG about 3
- Nov 1, 2026Google's StreamVibe video agent beats other models by 10.7% on response timing and quality
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.