LangChain's founder: Jev + LangGraph is the combo for modeling agents as complex systems
hwchase17 · x · 2026-09-26
LangChain founder Harrison Chase endorses Jev and LangGraph as a great combo: modeling agents as complex systems imbued with AI, with LangGraph as the best way to structure them and Jev inside LangGraph to turbo-charge the many small decisions agents must make.
- Jev, released last week by TypeSafe AI, is a new kind of model that doesn't generate text — it makes decisions your code can act on directly
- TypeSafe published an article on building production systems with Jev and LangGraph
More from coding & agent
- LangGraph maps well onto Jev, TypeSafe's new decision-making AI model — hwchase17 · 2026-09-26
- Claude Code dynamic workflow runs 3 hours using just 17% of weekly Opus 5.5 limit — daniel_mac8 · 2026-09-26
- A four-dimension eval framework for long-horizon agents: outcome, trajectory, experience, governance — sh_reya · 2026-09-26
- Databricks launches Unity Gateway CLI to centrally manage models across coding agents — matei_zaharia · 2026-09-26
- GitHub Cut Server Render Time 55% by Ditching CSS-in-JS, With Copilot Agents Finishing the Migration — DanWahlin · 2026-09-26
- Open-Source Lorca Launches: Native Mac Agent Client with iOS Pairing, Runs Agents Locally — dotey · 2026-09-26