tuning-engines

MCP serverDatabases & data

tuning-engines lets you set the rules your AI's models, agents, and skills must follow, and shows you what they actually did. Once added, your AI can work within your policies, pause for approval before important changes, and keep a record of each run. You can also see how much each workflow is being used.

Unavailable. This server has no hosted endpoint yet, so Ahel can't serve it.

Add to setup to save this item as a reference. Ahel cannot run it, and signing in will not install it.

What your AI can do with it

  • Apply your policies to model, agent, and skill workflows
  • Require approval before a change goes ahead
  • Keep a step-by-step trace of each run
  • See how often each workflow is used

Getting started

  1. Save this item in Your setup as a reference.
  2. Read the source or reference documentation for its setup requirements. Saving it here does not connect it to your AI.
  3. Check this page for availability before trying to install it through Ahel.

From the project's README

As published by cerebrixos-org/tuning-engines-cli in README.md. This repository publishes several servers, so only the opening is shown here.

Govern every AI workflow through one API.

Tuning Engines is a governed AI runtime for model, agent, skill, and MCP workflows. Route inference through one OpenAI-compatible API, apply RBAC and traffic policies, request approvals for high-risk actions, inspect traces and usage, and connect durable orchestration frameworks such as LangGraph and Temporal. The same CLI and MCP server also manage domain-specific fine-tuning of open-source models.

Training Agents

Shortened here. Read the whole README on GitHub.

Signals

GitHub stars
6
Forks
4
Last commit
Aug 2026
Weekly downloads
178
Weekly_downloads
214 weekly_downloads
Advanced
Delivery
tuning-engines MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-cerebrixos-org-tuning-engines
Source
github.com/cerebrixos-org/tuning-engines-cli