Repo · Routing & model choice
JCR
Turns a vague agent request into a deterministic command.
Open github.com ↗From the repository
A Jev-powered resolver for agent harnesses to find deterministic commands and their context in a nested capability tree.
ai-agentsjevmcp
How builders describe it
Jev Capability Resolver: one agent tool that searches a nested capability tree with TypeSafe Jev and returns deterministic command documentation (stdio MCP, Claude/Codex harnesses, and a 50-scenario benchmark suite). Does not execute target-service commands.
Capability resolver that uses Jev to search a nested command catalog and return selected instruction context to an agent through one MCP tool, keeping the search outside agent context.
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
Routing & model choiceAgentNetwork-jevEvent-driven multi-agent network where TypeSafe Jev observes live network state and assigns pending work to idle general-purpose agents each time one…GitHub · ★ 3 · Kelly-Leeee
Routing & model choicemodelrudderFree local community preview that adds model routing to the native Codex terminal: your own TypeSafe Jev key classifies each request so the strongest…GitHub · ★ 2 · cybrking
Routing & model choicejev-orcMy JEV Orchestrator to supply my needs.GitHub · ★ 2 · hiyoku
Routing & model choicejev-gateway (dragpk247)Sub-300ms intelligent LLM router with Zero-Leak privacy sandbox, Obsidian RAG, and multi-tier local GPU & cloud offloading.GitHub · ★ 1 · dragpk247
Routing & model choicepbi-orchestration-jevClaude Code skill that turns multi-file implementation into Product Backlog Items for sub-agents (Codex, Antigravity, Claude Code Agent), with…GitHub · ★ 1 · reeschan
Routing & model choiceAI Model PickerNative macOS assistant: describe a task, review rule-ranked app/model/effort choices, and open or prepare the task in the client you already use;…GitHub · Gavinluo19