Tool and skill selection with decision models
Deciding which tool, skill or MCP server an agent should use for the next step. Weak matches can be declined instead of guessed.
128 public projects · page 5 of 5
Python library and CLI that turns noisy sources like CI logs, diffs and web pages into small, traceable Jev briefings.
BenchmarkbetaPythonIndependent evaluation of Jev on MetaTool, When2Call and BFCL V4 tool selection, abstention and tool-use decisions.
BenchmarkresearchPythonOpen framework and preprint benchmarking typed decision models such as Jev, pplx-decider, Liquid D1 and Clef in six clusters.
BenchmarkresearchPythonCode Mode for MCP where retrieval shortlists tools and Jev picks one or says none fits, benchmarked on several tool-use suites.
BenchmarkresearchPythonKorean tutorial: 13 notebooks and a sample app attaching Jev to DeepAgents for tool choice, guardrails and risky-action gates.
ArticleprototypePythonPage companion where a site's actions are WebMCP tools and Jev picks the action a visitor's request means, asking back when unsure.
LibraryprototypeTypeSafe's official cookbook for a two-stage skill-suggestion workflow that selects a skill and can reject the shortlist.
ArticleproductionInfoWorld article (2026-09-17) on TypeSafe's models for machines, listing decisions like which tool to invoke or whether to approve.
Articlediscussion