DeerFlow 2.0 Custom Skills + MCP + Sandbox — Building Your Own Tools and Workflows
DeerFlow's markdown-based skills system, MCP server integration, Docker/K8s sandbox, and persistent memory system with practical code examples.
DeerFlow 2.0 Custom Skills + MCP + Sandbox — Building Your Own Tools and Workflows
In Part 2, we analyzed the Multi-Agent Workflow internals. This post covers how to actually extend DeerFlow.
We'll build custom skills, integrate MCP servers, and execute code safely in sandboxed environments.
1. Skills System
What is a Skill?
Related Posts
Inside Google COSMO — The New Architecture of On-Device AI Agents
Deep-dive into COSMO, Google's next-gen AI assistant accidentally leaked before I/O 2026. Full breakdown of the 3-mode architecture: Gemini Nano + PI server + Hybrid routing.
Self-Evolving AI Agents — The New Paradigm of 2026
GenericAgent, Evolver, Open Agents — comparing 3 self-evolving agent frameworks that learn, adapt, and grow without human coding.
Fine-tuning Gemma 4 MoE — Customizing Arena #6 with 3.8B Active Parameters
Apply QLoRA to Gemma 4 26B MoE. Expert layer LoRA strategies, Dense vs MoE comparison, MoE-specific training tips, and Ollama deployment. LoRA Series Part 4.