LangChain Releases Open Source Models and Memory Updates
hwchase17 · x · 2026-07-11
LangChain's updates this week are divided into two parts: open-source models and memory.
- In collaboration with NVIDIA, they released a NemoClaw DeepAgents blueprint, combining LangChain's open-source, model-agnostic Deep Agents runtime framework with Nemotron 3 Ultra and the enterprise-focused OpenShell runtime.
- Another highlight is the new version of OpenWiki, focusing on "personal brains": organizing sources like Gmail and the internet into a personal knowledge base/wiki.
- They conclude that open-source models + memory are ideal for enterprises seeking full-stack ownership and control, offering greater manageability from the model layer down to execution.
Related event: LangChain Releases Open-Source Agent and Memory Updates(3 posts)→
More from coding & agent
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11