jev-router
★ 673▲ 6gargpratyush/jev-router
Per-turn model routing for Claude Code and Codex. Simple work goes to the fast tier and difficult work to the strong tier.
Routes each agent step to a model, subagent, Skill, MCP tool, or CLI with one Jev Choice, requiring confirmation for risky capabilities and keeping decision receipts.
View on GitHub →Hands-on review
Routes a request across models, subagents, skills, MCP tools and CLIs with one Jev call. Its quickstart shape silently drops a candidate's risk level.
Good for
Watch out for
Tested Sep 20, 2026 at 3c558a78edf5 · Node 24 in Docker, offline, using the project's own demo provider; 69 tests run with no network
How we reviewed this: we built it in Docker on Node 24, ran its test suite offline, and drove its route command with the bundled demo provider — no Jev calls needed to see how the policy layer behaves. We did not run agent start, which launches a host CLI, or the live provider.
JevRouter, by BillionsBobby, treats every capability an agent has — models, subagents, skills, MCP tools, CLIs — as options in one Choice question:
Which single capability should handle this request? Choose only from the supplied options.
Jev returns probabilities; local policy does the rest. Availability, permissions, risk level and confirmation requirements are all applied in code, and by default the router only decides: mode: decision_only, execution not started. There are two-stage and hierarchical paths for more than 32 candidates, a plan mode that batches every step’s question into one request, and a decompose mode that asks per sub-goal.
Its test suite — 69 tests — passed offline with no network and no key. The demo provider makes the whole flow runnable before you spend anything, which is the right thing to ship.
A candidate can be given in full manifest form, or in the short form the quickstart uses: a name and a description. In src/manifest.ts, anything with a name and no id is turned into a manifest with hard-coded values:
risk: { level: "low", categories: ["agent_tool"] },
availability: { available: true },
...
A risk or policy block you supplied in that shape is dropped, silently, and no warning is printed. We fed it a single candidate declaring the opposite:
{ "name": "drop_production_database",
"description": "Permanently delete the production database and all backups",
"risk": { "level": "critical", "categories": ["data_loss"] },
"policy": { "requires_confirmation": true } }
and the decision came back:
status: selected | selected: drop_production_database
input declared: risk=critical, policy.requires_confirmation=true
router used: risk_level=low, requires_confirmation=false
The README’s own summary says medium, high and critical capabilities require confirmation. They do — if the candidate reaches the router as a full manifest. In the shape the quickstart teaches, every candidate is low risk. One of the cookbooks mentions this in a footnote; the README does not.
Nothing here executes by default, so this is not a “it deleted my database” bug. It is a bug in the layer you would rely on before wiring execution, which is where a router of this kind earns its place. Listing capabilities with id and a full risk block avoids it entirely. We’ve reported it upstream.
{request, actor, context} when you supply those, with no redaction and no truncation. Candidate descriptions become the Choice criteria; the router deliberately does not forward the help_excerpt it captures when discovering CLIs, which is a good instinct.--provider openrouter posts to OpenRouter’s decisions endpoint rather than TypeSafe. Worth knowing which key you are spending and whose logs your request lands in..jevrouter/decisions/<id>.json holds the request, the context and the raw model answer, in plain text, with default permissions. agent setup does not add .jevrouter/ to your project’s .gitignore, so a routine git add . can commit your prompts."${KEY}" placeholder rather than the value. The README’s claim that keys are never written to manifests or decision files held up.discover --cli executes <command> --help, and discover --mcp spawns the servers in your config with your full environment to enumerate their tools. Documented, and reasonable for a discovery step, but it means “finding capabilities” starts processes with your keys in their environment.A few smaller edges: the cache key doesn’t include the model, so switching models can serve a previous model’s answer; serve binds to localhost with no authentication, so any local process can spend your quota; and JEV_API_URL isn’t checked for a scheme, so a mistyped http:// would send a bearer token in clear text.
61 commits in two days, MIT licensed, three open issues, several outside contributors, and version 0.1.0 with no npm release — installation is npx github:BillionsBobby/JevRouter. The README carries a benchmark of its own routing on an agent benchmark; those are the author’s numbers, and the raw data is in an issue rather than the repository.
The idea is right, and the shape is right: one question over every capability you have, probabilities from the model, and every filter — availability, permissions, risk, confirmation — applied in code afterwards. Decision-only by default is the correct posture for something this young.
Give your candidates full manifests with explicit risk blocks rather than the quickstart’s short form, add .jevrouter/ to your .gitignore, and treat the decision files as prompt logs, because that is what they are.
For per-turn model routing instead of capability routing, see jev-router and Jev Codex Router. Our Best Jev Tools roundup compares what each tool sends.
See how it compares with other tools in Best Jev tools, tested hands-on.
Review updated Sep 20, 2026. Numbers quoted from the project are its author's own; we don't publish our own measurements of Jev.
gargpratyush/jev-router
Per-turn model routing for Claude Code and Codex. Simple work goes to the fast tier and difficult work to the strong tier.
higress-group/HiRoute
Local-first routing and coordination engine for long-running agent work, with a jev-decider extension that routes on typed decisions.
HeyCubit/effortless
Claude Code mod that picks the reasoning effort for every prompt, shows prompt-cache and context state, and hands off or compacts in one click; Haiku by default, Jev with a TypeSafe key.
New Jev releases, pricing changes, and the best new projects, once a week. No spam; unsubscribe anytime.
Powered by Buttondown. See our privacy policy.