DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to pick the next tool call from a fixed option list with Agent Jev

Give AgentJev the current state and a list of allowed next actions, then route to the top option.

Who it is forAn engineer building an agent workflow with a fixed set of tools who wants a cheap routing decision on every step.

The problemAsking a large model to name the next tool costs a full generation and can return a name outside the allowed set.

The outcomeThe top option, its probability, and the margin over the second option, so the loop can act or escalate when the margin is small.

What you need first

  • Python with PyTorch and Transformers installed (the README benchmarks used PyTorch 2.9.1+cu128 and Transformers 4.57.6)
  • A GPU; the README timings were measured on one RTX 5060 with 8 GB
  • Git access to clone malevrigns/agent-jev and download weights from the linked Hugging Face model repository
  • A state to evaluate, such as a test runner summary, plus questions you have already phrased as boolean, choice, or score

Steps

  1. Clone the repository and start the server with the checkpoint and temperatures you have available, following the Run it and HTTP sections of the README.
  2. Write the current state as text or JSON, for example the last tool result and the open ticket.
  3. Define a choice question with 2 to 255 options, each written as a description of the action.
  4. Send the state and question to the server and read top_probability and margin from the response.
  5. Run the top option when margin is above your threshold, and hand the step to a larger model otherwise.

Prompt for your agent

Using the agent-jev repository at <repo-path>, send the state in <state-file> with a choice question listing the allowed next actions in <action-list>. Return the top option, top_probability, and margin. Verify that the returned option is one of the options you supplied.

Caveat. The README says a choice result is a preference inside the set you passed and is not an independent probability that the action will succeed, so calibrate a boolean question on your own outcomes if you need success odds.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page