LangChain releases Deep Agents v0.6 with streaming, code interpreter, and delta channels

LangChain Blog

Deep Agents v0.6 introduces a code interpreter, harness profiles for per-model tuning, streaming support, and delta channels that reduce checkpoint storage by up to 100x. Harness profiles enable production-grade performance from open-weight models at 20x+ lower cost than closed frontier APIs.

langchain

See 14 more sources

Tuning Deep Agents to Work Well with Different Models8 days ago

Interpreters in Deep Agents: Code Between Tool Calls and Sandboxes8 days ago

Delta Channels: How We’re Evolving our Runtime for Long-Running Agents8 days ago

From Token Streams to Agent Streams8 days ago

Managed Deep Agents is built to handle real-world interactions: 30+ endpoints for agents,...1 day agoLangChain

Deep Agents v0.6 makes harness profiles a first-class abstraction. Now, you can get...12 days agoLangChain

Deep Agents v0.6 brings Delta channels, reducing checkpoint storage by up to 100x for long-running...14 days agoLangChain

1.Cure all diseases 2.Automate scientific research, helping us solve challenges such as energy...20 days agoKimmonismus

Norway's 2 petabytes of Huawei flash storage and LLM training16 days agorbanffyDiscuss

Managed Deep Agents keeps the project shape you already know: ↳ AGENTS.md, skills/, subagents/, +...9 days agoLangChain

New in Deep Agents: Agent Rubrics! Attach a rubric to your agent invocation, and a grader...8 days agoLangChain

Managed Deep Agents = The best of both worlds. Deep Agents - Your open source harness LangSmith -...7 days agoLangChain

The @nebiusai Agent Blueprint’s open reference architecture connects proven components at each...6 hours agoLangChain

Deep Agents: An open-source harness for building agents that can plan, use tools, delegate to...2 days agoLangChain

LangChain Blog

8 days ago