Agents

DeepSeek Harness With Local Models: Live Test

I test the DeepSeek Harness on local models through Ollama. The Trajectory view shows every agent step. The web search test timed out because no search tool was set up.

39 min · 2026-08-17 · Watch on YouTube

The main idea

DeepSeek launched its own agent harness, and it reached about 130,000 GitHub stars in 3 days. In this live stream I tested it against local models instead of their API.

Setup is one command. Ollama launched DeepSeek Harness, and I used Qwen 3.8 27B MLX. The harness is a web UI. Claude Code and Codex started in the terminal, and DeepSeek chose the browser. I like the Trajectory tab, because it shows each step the agent took, including time to first token. The settings have presets for standard, code, minimal and creator modes. Permission defaults to workspace write.

The tests did not go well on my machine. My Minecraft clone task stalled, and OBS slowed my local models. I switched to Gemma 4 E2B, then asked the harness to search the web. The search tool timed out because I had not set up a search API key. Hermes agent can write its own script to search the web when it has no search tool. Part 1 ends before a verdict, so I will keep testing.

Key points

Chapters

  1. 0:45Ollama launch and setup
  2. 6:50Web UI and Trajectory tab
  3. 8:46Settings and agent presets
  4. 25:22Web search test
  5. 36:01Switching to DeepSeek V4 Flash
Free live lesson · Nov 24Stop Measuring AI by Tokens. Measure What It EarnsOne hour, live, with Saurav. Bring your own bill. Free.
Save my free seat →
Get new videos and tips by emailOne short email when there is something new. Unsubscribe any time.

More CloudYeti videos