It is indeed very good! Do not try it in claude code/codex – these harnesses are too tailored for their proprietary models. dcode (deepagents code) is a model-agnostic harness – try it there with @FireworksAI_HQ: dcode –model
@hwchase17
-
Harbor: standard framework for stateful agent evaluations
By
–
Harbor is an excellent framework for running longer, more stateful agent evaluations. It underpins Terminal Bench 2 and is becoming the industry standard. LangSmith sandboxes now integrate Harbor!
-
Increase in spending on coding agents and LLM gateway control
By
–
Like many organizations new to AI, our spending on coding agents has increased quite dramatically over the past few months. A key element of the LLM gateway we are developing (available in private preview right now) is the control of…
-
Arcade Launch: Thousands of Tools with LangChain No-Code
By
–
congrats to arcade for their launch!
— Harrison Chase (@hwchase17) 15 juin 2026
they make it super easy to use thousands of tools
if you want to try them out with langchain – easiest way is probably our no-code agent builder: https://t.co/jRHHHwQMHh https://t.co/WTlTJDkfnRCongratulations to Arcade for their launch! They make it super easy to use thousands of tools. If you want to try them with LangChain – the simplest way is probably our no-code agent builder: https://docs.langchain.com/langsmith/fleet/arcade …
-
Problem Detection in Agent Traces with Post-Trained Model
By
–
Detecting problems in agent traces in production is difficult. It must be done at low cost (due to volume) but also with accuracy (otherwise too much noise). We post-trained our own model for this. SOTA accuracy, at ~10-100x lower cost.
-
Model neutrality surpasses cloud neutrality as an offensive tool
By
–
Why model neutrality is more important than cloud neutrality was In the cloud era, companies opted for cloud neutrality as a defense mechanism Model neutrality can be an **offensive** mechanism. It is more
-
First technical blog on building LLM infrastructure
By
–
first in a series of technical blogs of how we build llm infra
-
DeepAgent for competitive analysis
By
–
deepagent for competitive analysis https://t.co/5WCFalQKTd
— Harrison Chase (@hwchase17) 8 juin 2026deepagent for competitive analysis
-
Costs matter: Uber caps tokens at $1500 per dev per month
By
–
we are seeing costs start to matter! uber just set limits of $1500 in tokens per developer per month i think we're going to start seeing more of this, and LangSmith Gateway is a great way to implement it
-
LangSmith Sandbox Gateway Observability
By
–
langsmith! Sandbox: https://
docs.langchain.com/langsmith/sand
boxes
… Gateway: https://
docs.langchain.com/langsmith/llm-
gateway
… Observability: https://
docs.langchain.com/langsmith/obse
rvability
…