The open reference architecture of the @nebiusai Agent Blueprint connects proven components at every layer of the agent stack. We are thrilled to have Deep Agents and LangSmith as integral parts. Full announcement.
@langchain
-
LangSmith Fleet template: Software Engineer coding agent from Slack, Linear, GitHub
By
–
LangSmith Fleet template spotlight: Software Engineer Ships code from Slack, Linear, and GitHub in a sandbox A coding agent that takes issues from @Linear
, writes and verifies the code, and opens a PR. Triggered directly from Slack. -
LLM Gateway integrates observability and application into a single tool
By
–
Obtaining both observability and application once meant assembling: A separate gateway, A guardrails platform, An observability stack… then correlating signals between the three when a problem occurred. LLM Gateway integrates both into
-
Full-text search JSON filtering with custom inverted index for SmithDB
By
–
How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latency of 400ms? Here’s an inside look at how we built a custom inverted index from scratch for SmithDB.
-
RubricMiddleware: defining the ‘done’ state for agents
By
–
IN CASE YOU MISSED IT: We added RubricMiddleware to Deep Agents. RubricMiddleware is the way to tell the agent what 'done' looks like — and to keep it going until it gets there.
-
LangSmith Sandboxes now GA for secure agent code execution
By
–
A quick refresher on LangSmith Sandboxes: Secure, scalable environments built for agent code execution Integrated with the Deep Agents SDK and the LangSmith platform Now GA
-
Managed Deep Agents via LangSmith: Managed Execution Infrastructure
By
–
If your team wants Deep Agents with a managed execution infrastructure by LangSmith, Managed Deep Agents is the fastest path forward. Keep the agent definition in your repository, then use the API to create and operate managed agents in
-
hwchase17 explains LangSmith LLM Gateway in less than 90 seconds
By
–
.@hwchase17 explains LangSmith LLM Gateway in <90 seconds. pic.twitter.com/rB7GanpxkY
— LangChain (@LangChain) 9 juin 2026@hwchase17 explains LangSmith LLM Gateway in
-
LangSmith Executive Assistant Template for Email and Calendar
By
–
LangSmith Fleet template spotlight: Executive Assistant Manages your inbox, calendar, and daily brief. An email agent that triages your inbox, briefs you every morning, schedules meetings, and learns your preferences over time. Try it today: https://
langchain.com/templates/exec
utive-assistant
… -
Experimenting with interpreter skills using TypeScript
By
–
—
TL;DR We are experimenting with interpreter skills: an extension of agent skills that allows you to include a TypeScript module with a skill. A brief overview by @huntlovell https://
langchain.com/blog/interpret
er-skills
…
—