I built an agent Harness for Small Models. I got Qwen 3.5 4b managing servers.
Summary
Built an agent harness for small models, enabling Qwen 3.5 4b to manage servers.
Similar Articles
Remote agent harness
A tool for remotely harnessing and managing AI agents.
The agent bug I thought was the model turned out to be the harness
The author shares a debugging experience where an agent loop was caused by a harness truncating tool outputs rather than model failure, highlighting the reliability gap in agent infrastructure compared to models.
Qwen/Qwen-AgentWorld-35B-A3B
Qwen releases Qwen-AgentWorld-35B-A3B, a native language world model that simulates agentic environments across seven domains via long chain-of-thought reasoning. The model is trained with a three-stage pipeline and supports MCP, Search, Terminal, SWE, Android, Web, and OS interactions.
I built a cloud agent harness that you can train to be specialized at any task
The author introduces OpenSteer, a cloud agent platform that allows users to create and customize specialized agents for automating tasks across websites and services, with support for cloud browsers, APIs, MCPs, and CLIs, demonstrated through a sales automation agent.
Building the QWEN3.6 - Codex Bridge Furthe + Kindergarten Harness Reality Check
The author updates a custom harness and UI bridge tool to run the Qwen 3.6 model on GitHub Copilot Codex via llama.cpp on a local RTX 5090. The post details implemented features, fixed bugs, and remaining limitations in achieving parity with native OpenAI models.