Get started

Agentic engineering recommendations

Wagtail works well with a wide range of LLMs and agentic tools, as models are highly proficient at code tasks in Python and Django. The heavily-opinionated recommendations below are for members of our community who want to follow our AI guiding principles.

Provider recommendations

Here are the options we recommend from our comparison of inference providers:

  • TensorX. EU company working with US (Ireland) and EU (Finland) data center providers. Wide range of models, very basic management features.
  • Neuralwatt. US company with a unique energy transparency and pricing model.

The focus is on capabilities, transparency, clear model lifecycle, sovereignty.

SWE harness recommendations

We recommend using a harness that has good support for multiple inference providers. This will allow you to easily switch between the models/offerings of different companies to test various capabilities.

CLI options

IDE options

Other options

There are a lot of other options out there. Here are our criteria for inclusion on this list:

  • Open source software that is free to install and use.
  • Supports multiple providers, including unknown/custom endpoints, with easy switch between them.

Let us know if you have other suggestions, on the Wagtail Slack.

SWE model recommendations

Expect to change models every 2-3 months. See comparing open weight AI models for the rationale.

Current recommendations:

  • GLM 5.3 Flash for 95% of tasks (capable, cheap, fast). Make sure your harness can set thinking/reasoning to "high" or "max" effort for the best results.
  • GLM 5.3 for the top 5% of more demanding tasks.

Monitor your usage and its cost

Make sure your harness is set up to report on tokens usage, cache hit rates, and costs, with the correct cost rates per TensorX docs. We recommend a personal budget of:

  • $100 per month
  • This translates to 1B+ total tokens per month with an efficient model
  • Or 30-50M tokens per month with a flagship model.

Use AgentsView to track your personal usage across projects / providers / models. Tips to more efficiently use AI:

  1. Write scripts with code for tasks that could be deterministic and AI-free.
  2. Use smaller models like GLM 5.3 Flash.
  3. Switch to more recent and efficient models.
  4. Provide automated verification for AI agents so they complete tasks more reliably.
  5. Use more advanced prompting techniques to get better results out of smaller models.

Note: AgentsView reports correct token counts for a wide range of agents. Costs are indicative only, they are based on manually-updated LiteLLM data that will always be out of sync with inference providers.

Harness configurations