--- title: New in Deep Agents v0.6 | daily.dev description: Deep Agents v0.6 ships five major features focused on performance and scalability. A new code interpreter enables Programmatic Tool Calling (PTC) and recursive... canonical: https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: New in Deep Agents v0.6 | daily.dev og:description: Deep Agents v0.6 ships five major features focused on performance and scalability. A new code interpreter enables Programmatic Tool Calling (PTC) and recursive... og:url: https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj og:image: https://api.daily.dev/og/posts/Xnv5yNlsj.png og:image:alt: New in Deep Agents v0.6 og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # New in Deep Agents v0.6 **[LangChain](https://daily.dev/sources/langchain)** · 11 min read · 0 upvotes · 0 comments ## Summary Deep Agents v0.6 ships five major features focused on performance and scalability. A new code interpreter enables Programmatic Tool Calling (PTC) and recursive workflows, letting agents compose tools and manage state without routing every step through the model. Harness profiles provide per-model tuning that unlocks production-grade performance from open-weight models like Kimi, Qwen, and DeepSeek at 20x+ lower cost than closed frontier APIs. Streaming v3 introduces typed, subscribable event projections for messages, tool calls, and subagents, with frontend integrations for React, Vue, Svelte, and Angular. Delta channels replace full-snapshot checkpointing with diff-based storage, reducing checkpoint size by up to 100x for long-running agents (5.27 GB down to 129 MB in a 200-turn coding session example). Finally, ContextHubBackend provides a versioned, LangSmith-backed filesystem for storing agent skills, policies, and memories across runs. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Deep Agents v0.5](https://daily.dev/posts/deep-agents-v0-5-x8sraelyt) · LangChain · 1 upvotes · 0 comments - [Doubling down on DeepAgents](https://daily.dev/posts/doubling-down-on-deepagents-nng5qiavu) · LangChain · 10 upvotes · 0 comments - [DeepSeek-V4: a million-token context that agents can actually use](https://daily.dev/posts/deepseek-v4-a-million-token-context-that-agents-can-actually-use-uczd4kivx) · Hugging Face · 27 upvotes · 2 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain), [#langgraph](https://daily.dev/tags/langgraph) [View this post on daily.dev](https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"New in Deep Agents v0.6","url":"https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj"},"datePublished":"2026-07-08T19:23:03.046Z","dateModified":"2026-08-24T07:10:33.267Z","description":"Deep Agents v0.6 ships five major features focused on performance and scalability. A new code interpreter enables Programmatic Tool Calling (PTC) and recursive...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/df87b8c75c016d66875187fdfe259baf?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/df87b8c75c016d66875187fdfe259baf?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/new-in-deep-agents-v0-6-xnv5ynlsj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,langchain,langgraph","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"New in Deep Agents v0.6"}]} ```