← all releases
LangChain·Jun 29, 2026·Beta·open source
Dynamic Subagents
Dynamic Subagents is a feature within the Deep Agents framework that allows agents to programmatically orchestrate sub-tasks by writing and executing scripts in a lightweight, secure interpreter. This enables agents to perform complex, multi-phase, and conditional workflows—such as fan-out/synthesis or loops—more reliably than standard turn-by-turn tool calling.
AI AgentsOpen SourceMulti-agent SystemsOrchestration
overview
Dynamic Subagents is a feature within the Deep Agents framework that allows agents to programmatically orchestrate sub-tasks by writing and executing scripts in a lightweight, secure interpreter. This enables agents to perform complex, multi-phase, and conditional workflows—such as fan-out/synthesis or loops—more reliably than standard turn-by-turn tool calling.
key features
- 01Programmatic orchestration via a secure JavaScript-based (QuickJS) code interpreter
- 02Deterministic execution of complex patterns like fan-out/synthesis, looping, and conditional branching
- 03Isolated context windows for subagents to maintain main agent performance
- 04Simplified task dispatching using a built-in task() global function
- 05Structured output support via optional responseSchema for typed results
- 06Native compatibility with dcode terminal coding agent and existing Deep Agents toolsets
related productsbrowse all →
MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.