← Back
VentureBeat AI

DeepSeek Harness launches as open source rival to Claude Code, alongside V4-Pro on API with higher prices

11 min read
#agents#llm#inference
DeepSeek Harness launches as open source rival to Claude Code, alongside V4-Pro on API with higher prices
Level:Advanced
For:AI Engineers
TL;DR

DeepSeek has launched DeepSeek-V4-Pro, an updated flagship model focused on agentic workloads, and DeepSeek Harness, an open-source agent harness that provides a modular alternative to integrated coding-agent environments like Anthropic's Claude Code. DeepSeek Harness is built on the Cordis framework and allows developers to mix, replace, and extend components such as models, tools, and user interfaces. The launch marks a broader developer push from DeepSeek, with V4-Pro available across its web interface, mobile app, and API, and Harness entering developer preview under the MIT license. The practical implication for engineers building AI systems is that they now have a more flexible and customizable option for assembling agent workflows.

⚡ Key Takeaways

  • DeepSeek-V4-Pro is available across DeepSeek's web interface, mobile app, and API, with native support for the OpenAI Responses API and integration with Codex.
  • DeepSeek Harness is an open-source agent harness built on the Cordis framework, with a modular design that allows developers to swap out components as plugins.
  • The API pricing for V4-Pro will change to peak and off-peak rates, with substantially higher prices for cache-miss and output prices.
  • DeepSeek Harness can inspect repositories, edit files, execute shell commands, search files and the web, maintain plans, invoke skills, delegate work to subagents, and enforce approval policies.
  • Harness is not yet a stable drop-in production platform, with compatibility-breaking changes expected.
💡 Why It Matters

The launch of DeepSeek Harness provides engineers with a more flexible and customizable option for building AI agent workflows, allowing them to mix and match components to suit their specific needs. This could lead to more efficient and effective development of AI-powered systems.

✅ Practical Steps

  1. Launch DeepSeek Harness from npm with `npx @deepseek-ai/dsh web`.
  2. Build DeepSeek Harness directly from source using the instructions provided by DeepSeek.
  3. Explore the capabilities of DeepSeek Harness, such as inspecting repositories, editing files, and executing shell commands.

Want the full story? Read the original article.

Read on VentureBeat AI

More like this

Building an AI Text Detector From Scratch

Ahead of AI#llm

GLM-5.3 is here with advanced cyber capabilities — and reportedly already found a 'serious vulnerability' in Cursor

VentureBeat AI#llm

Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge

AWS ML Blog#amazon

RAG Workflow and Loop Engineering: The Dispatcher That Decides When to Loop and When to Stop

Towards Data Science#rag

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING