---
type: "raw_signal"
id: "context-engineering-with-deep-agents-how-to-remember-2b65e3"
slug: "context-engineering-with-deep-agents-how-to-remember-2b65e3"
title: "Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context"
description: "LangChain published a technical guide to context management in its open-source Deep Agents harness."
retrieval_nugget: "LangChain published a technical guide to context management in its open-source Deep Agents harness."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "LangChain published a technical guide to context management in its open-source Deep Agents harness. The post describes five techniques: offloading large tool results to files, summarizing older conversation messages, loading skills progressively, isolating noisy work in subagents, and persisting long-term memory in files. It gives implementation details, including offloading tool results above rou"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "langchain.com"
topics: ["context-engineering"]
entities: ["LangChain","Deep Agents","LangSmith"]
related_patterns: ["harness-architecture-outlives-model-choice","company-memory-needs-write-loops","skills-become-portable-capability-layer"]
source_url: "https://www.langchain.com/blog/context-engineering-deep-agents-remember"
source_urls: ["https://www.langchain.com/blog/context-engineering-deep-agents-remember"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:context-engineering-with-deep-agents-how-to-remember-2b65e3"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/context-engineering-with-deep-agents-how-to-remember-2b65e3/","markdown":"https://newruntime.com/signals/context-engineering-with-deep-agents-how-to-remember-2b65e3.md","json":"https://newruntime.com/signals/context-engineering-with-deep-agents-how-to-remember-2b65e3.json"}
---

# Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context

## Retrieval answer

LangChain published a technical guide to context management in its open-source Deep Agents harness.

LangChain published a technical guide to context management in its open-source Deep Agents harness. The post describes five techniques: offloading large tool results to files, summarizing older conversation messages, loading skills progressively, isolating noisy work in subagents, and persisting long-term memory in files. It gives implementation details, including offloading tool results above roughly 20,000 tokens and triggering summarization at 85% context-window usage by default. LangChain says memory is stored as plain files in storage controlled by the operator, allowing the same memory to be used across models or providers. The post presents a vendor-authored implementation guide, not an independent evaluation of effectiveness.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Context Engineering](https://newruntime.com/topics/context-engineering.md): Explore the context-engineering topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)