LangSmith Sandboxes gives agents access to the systems they need, while keeping credentials and network policy under platform control.
AGENTS
-
Mirage: Latent Spatial Memory for Video World Models
By
–
“Latent Spatial Memory for World Models” world models need a 3D memory to avoid drift, but RGB point cloud caches are slow because each step renders pixels and re-encodes them into latents via a VAE. The Mirage approach
-
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 …
-
Apps & Agents for Good Hackathon at DataAISummit using Databricks and OpenAI
By
–
Builders are gathering for the Apps & Agents for Good Hackathon at #DataAISummit! Using Lakebase, Agent Bricks, Databricks Apps, and @OpenAI
, teams will spend the next two days building agentic data apps for social impact. Good luck to all the participants — we're excited to see -
Speed, latency, natural conversation vital for voice agents
By
–
Speed, latency, and natural conversation matter more than ever for voice agents.
-
OrcaRouter detects hallucinations and ensures reliability
By
–
A model has a bad day and your output collapses.
OrcaRouter makes reliability structural, not a matter of luck.
If a leg hallucinates, the judge detects it and provides the answer that holds the road. -
Gemma 4 31B runs fastest on SambaCloud, over 30% faster
By
–
Gemma 4 31B is running fastest on SambaCloud ⚡
— SambaNova (@SambaNovaAI) 15 juin 2026
As verified by @ArtificialAnlys, SambaCloud delivers Gemma 4 31B over 30% faster than the next provider.
Same model. More speed. Better agent experiences.
Read more: https://t.co/Y61VK1AiOJ pic.twitter.com/QDkY6vpdAMGemma 4 31B is running fastest on SambaCloud As verified by @ArtificialAnlys
, SambaCloud delivers Gemma 4 31B over 30% faster than the next provider. Same model. More speed. Better agent experiences. Read more: https://
sambanova.ai/blog/gemma-4-3
1b-running-fastest-on-sambacloud?utm_source=x&utm_medium=organic&utm_content=blog-announcement
… -
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.
-
10 GitHub repositories that automate your work in 2026
By
–
10 GitHub repositories that automate your work while you sleep in 2026. Save this list. 1. OpenHands Autonomous coding agent. 76,500 stars. Used by engineers from Apple, Google, Amazon, Netflix, and NVIDIA. Repo → https://
github.com/OpenHands/Open
Hands
… 2. Hermes
— -
Free guide: from vibe coding to agentic engineering with AI
By
–
We just dropped a 50-page guide on the shift from vibe coding to agentic engineering. It covers the new Software Development Life Cycle with AI Agents. 100% free.