Claude Code Dynamic Workflows: Parallel Subagents & UltraCode Mode

Claude Code now supports dynamic workflows that let the agent orchestrate tens to hundreds of parallel subagents in a single session, checking work before anything reaches you. Available in research preview in the CLI, Desktop, and VS Code extension for Max, Team, and Enterprise plans, plus the API (Amazon Bedrock, Vertex AI, Microsoft Foundry).
How to use
- Ask directly: "Create a workflow"
- Enable UltraCode via the effort menu (sets effort to
xhigh), letting Claude auto-decide when to spawn a workflow.
Workflows consume substantially more tokens than a typical session — start scoped.
Capabilities shown in early access
- Codebase-wide bug hunts: parallel search across a repo, then independent verification on every finding.
- Large migrations: framework swaps, API deprecations, language ports spanning thousands of files end-to-end.
- Double-checked results: independent solution attempts and adversarial agents that try to break the result before delivering it.
Real-world example: Bun rewrite
Jarred Sumner used dynamic workflows to port Bun from Zig to Rust — ~750,000 lines of Rust in 11 days, with 99.8% of existing tests passing. Workflow steps:
- Map Rust lifetimes for every struct field.
- Write every
.rsfile via hundreds of parallel agents, each with two reviewers. - Fix loop driving build/test until clean.
- Overnight workflow to eliminate unnecessary data copies, opening a PR for each fix.
How it works
Claude plans dynamically from your prompt, breaks the task into subtasks, fans work across parallel subagents, checks results independently, and iterates until answers converge — producing a single coordinated answer.
📖 Read the full source: HN AI Agents
👀 See Also

Open-source tool enables Claude to control Unreal Engine directly
soft-ue-cli is a Python tool with a C++ plugin that allows Claude Code and Claude Desktop to execute commands in Unreal Engine without editor interaction, featuring 60+ operations including blueprint editing, actor spawning, and performance profiling.

2026 Hermes Agent Alternatives Roundup: Self-Hosted Options from OpenClaw to memU Bot
A developer who has been running Hermes since launch tested every self-hosted and managed alternative after the ClawHub security mess. Key findings: OpenClaw (370k stars) but 9 CVEs in 4 days and ~20% malicious packages; TrustClaw rebuilt with OAuth/sandboxing; nanobot at ~4K lines Python with MCP; memU Bot with unique structured memory. Managed options include Perplexity Computer (19 models, $200/mo), Claude Cowork (opens real Mac apps), and KimiClaw (40GB RAG, locked to K2.5, Chinese data law). Full roundup at source.

DELIGHT: Local Orchestrator Uses Multiple ChatGPT Sessions as Coordinated Agents
DELIGHT is a local orchestrator that runs multiple hidden ChatGPT browser sessions simultaneously, coordinating them like a team of agents without requiring API keys or GPU resources. It connects to OpenClaw as an action layer to apply changes to real files and run tests.

Claude IDE Bridge: MCP Tool for Remote Editor Access
Claude IDE Bridge is an open-source tool that provides Claude AI with remote control access to code editors via MCP (Model Context Protocol). It exposes editor knowledge like live type information and debugger state as callable tools.