introducing @LangChain × kapa your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system) your agent gets
@hwchase17
-
A Fireside Chat Connects Agent Observability With Post Training
By
–
Excited to participate in this SPC fireside chat and talk about the intersection of agent observability and post training!
-
A Discussion Examines Agent Traces for Training and Evaluation
By
–
Traces are the new oil… or so says my X feed. But how are people using them? Why are they valuable? How are they connected to training, or evals? @vatsalbajaj and I are hosting @ankush_gola11
, co-founder and CTO of @LangChain
, for a fireside next Thursday to explore questions -
Persistent Memory Becomes a Key Layer for Agent Systems
By
–
Why the memory layer will become more and more important and how Instinct crushed it
— Harry Stebbings (@HarryStebbings) 17 octobre 2026
“One thing about agents that is rare today but will be incredibly common in the next few years is this memory layer.
If you look at Instinct or Muse, one of the things that they have nailed is… https://t.co/3qyXupi3M2 pic.twitter.com/LDghjWrsXZWhy the memory layer will become more and more important and how Instinct crushed it “One thing about agents that is rare today but will be incredibly common in the next few years is this memory layer. If you look at Instinct or Muse, one of the things that they have nailed is
-
Neutral Harnesses Enable Model Switching and Portable Agent Memory
By
–
Why harnesses need to be neutral
— Harry Stebbings (@HarryStebbings) 17 octobre 2026
“You want to be able to switch models. The harness can be very tied to the model, or it can be neutral.
The harness’s job is to take the model and interact with everything else, including data, APIs and memory.
If you build memory in a way that… https://t.co/3qyXupi3M2 pic.twitter.com/xlwSZnYwsSWhy harnesses need to be neutral “You want to be able to switch models. The harness can be very tied to the model, or it can be neutral. The harness’s job is to take the model and interact with everything else, including data, APIs and memory. If you build memory in a way that
-
Deepagents Adds Gemini Argon With Long Context and Video Understanding
By
–
deepagents now supports gemini 4 argon from @GoogleDeepMind
! it supports 1M input tokens, long decode (up to 1M), and agentic video understanding! docs: https://
docs.langchain.com/oss/python/int
egrations/providers/google
…
release blog: https://
blog.google/innovation-and
-ai/models-and-research/gemini-models/introducing-gemini-4-argon/
… -
Agent Harness Infrastructure Adds Memory, Heartbeats and Asynchronous Subagents
By
–
Most of the interesting agent harness work is happening at intersection of harness and infra: 1/ dreaming 2/ async subagents
3/ heartbeats
4/ letting agent schedule reminders Part of reason im so bullish on managed agents platforms! All of these in managed deep agents! -
Framework Traces a Shift From Coding Agents to Company Operating Systems
By
–
Coding agents (Claude code, codex) -> personal agents (instinct, muse) -> companyOS (???)
-
Harness Based Model Routing Uses Task Context
By
–
router lives in the harness, not a gateway, bc the harness knows the task blog: https://
langchain.com/blog/how-to-bu
ild-a-model-router-in-the-harness
… -
Deepagents Explores Asynchronous Subagent Completion Notifications
By
–
we are thinking a lot about how to make deepagents more async native. specifically about making async subagents work better/more prominent one key question is how does a finished subagent "notify" the parent agent? some default behaviors we're considering for when the parent is