Repo · Routing & model choice

Jevex

Combine Jev control decisions with an LLM writer.

Open github.com ↗

How builders describe it

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

Experiment where Jev controls the tool loop and a LangChain chat model only fills argument values and final prose, using 12 local read-only MCP tools across documents, math, and calendar.

Double barrel ReACT agent architecture: LLM does the writing. Jev does all the deciding. Tool call decisions and agent loop state are all decided by Jev. LLM writes user output, and tool inputs, where needed. Included real-world benchmarks against basic ReACT agent architecture. The strongest…

The decision Jev makes

Pick an agent, a model, a skill from a catalog, or a function and its arguments.

Where it fits

Deciding which agent, model, skill or function should handle a request. Jev is a natural router: the options are fixed and the confidence tells you when to fall back. All 348 routing & model choice projects →

Related projects