CLI Agents

‍

Compatibility notice

This documentation requires the following mStudio features which might not be available in all hosting plans: AI/LLM hosting‍.

Command-line coding agents run in your terminal rather than inside an editor. They read and write files, run commands, and call tools on their own, driven by a model you point them at. Because mittwald AI Hosting speaks the OpenAI API, any agent that accepts a custom OpenAI-compatible endpoint works with it — with your code and prompts staying on infrastructure in Germany.

For agents that live inside an editor instead, see IDE Integration‍.

What an agent needs from the endpoint

A coding agent needs three things beyond plain chat, and mittwald AI Hosting provides all three:

• An OpenAI-compatible /v1/chat/completions endpoint. This is what the baseURL or base_url setting in each agent points at.
• Streaming responses, so output appears as it is generated instead of arriving in one block at the end.
• Tool calling. This is the one that matters most and the one that most often breaks against non-OpenAI endpoints. An agent without tool calling cannot read a file or run a command — it can only talk. Verified working on Qwen3.5-122B-A10B-FP8, Qwen3.8-27B-NVFP4, Qwen3.6-35B-A3B-FP8 and gpt-oss-120b.

Examples of supported agents

These three are documented here because they were verified end to end against mittwald AI Hosting. Any agent that lets you point it at a custom OpenAI-compatible endpoint works the same way.

Agent	Config file	MCP support	Skills
Hermes Agent‍	~/.hermes/config.yaml	Built in (hermes mcp add)	Built in, plus registries
Pi‍	~/.pi/agent/models.json	Built in (pi mcp add), since 0.99.0	Directory discovery or --skill
opencode‍	~/.config/opencode/opencode.json	Built in (mcp config block)	~/.config/opencode/skills/

Choosing a model

All models are listed in the AI models documentation‍. For agentic work:

Use for	Model	Context
Main driver	Qwen3.8-27B-NVFP4	256,000
Subagents, cheap turns	Qwen3.6-35B-A3B-FP8	256,000
Reasoning-heavy work	gpt-oss-120b	131,072
Routing, classification	Qwen3.5-0.8B	262,144
Documents and images	GLM-OCR	see model page

Image understanding (vision) isn't limited to one entry here — Qwen3.8-27B-NVFP4 and Qwen3.6-35B-A3B-FP8 both accept image input as Base64-encoded data URLs, though Qwen3.8-27B-NVFP4 caps requests at 5 images.

Start with Qwen3.8-27B-NVFP4 as the driver and leave thinking on, which is its default. With thinking off, agents on this model can get stuck repeating the same tool call — see Agent loops in non-thinking mode‍. If an agent supports per-subagent model overrides, point the subagents at Qwen3.6-35B-A3B-FP8 — the work they do is mostly search and summarising, and the faster model keeps long sessions responsive.

Qwen3.5-122B-A10B-FP8 will be disabled on 28.12.2026. If your agents still use it, move them to Qwen3.8-27B-NVFP4.

Quick start

1. Get an AI Hosting API key from the AI-Hosting section of your mStudio project — see Gaining access‍.
2. Pick an agent from the table above and follow its page.
3. Configure the endpoint as https://llm.aihosting.mittwald.de/v1.
4. Verify tool calling works before starting real work. Each guide has a verification step for this.

Keeping context under control

Large context windows are not a reason to send more. Agents burn context fastest on file contents and command output.

• Point the agent at specific files and functions rather than whole repositories.
• Use the sampling parameters recommended on the model's page. Don't lower temperature to 0: greedy decoding makes the models repeat themselves.
• Set a step limit where the agent has one, so a run that loops ends early instead of using up your token quota.
• Raise max_tokens only when a reply is actually being truncated.
• Where the agent supports compaction or summarisation, leave it enabled for long sessions.

Disclaimer

Third-party tools, MCP servers and external links are provided for convenience without endorsement or warranty. Use them at your own risk, review licenses and privacy policies, and scope access conservatively (least privilege). Avoid sending sensitive data to external services unless required and permitted.