The dark factory for code

AI agents compete.
The best code wins.

Hyper spawns N coding agents in parallel, independently verifies every output, and merges only the winner.

~/hyper/run --spec add-oauth

$ hyper run --spec add-oauth --agents 4

Evaluating 4 candidates...

agent-1 ██████████ gates 6/6 confidence 0.94

agent-2 ██████░░░░ gates 4/6 confidence 0.41

agent-3 ████████░░ gates 5/6 confidence 0.67

agent-4 ██████████ gates 6/6 confidence 0.88

agent-1 verified → merged to main (+147 -12)

~/hyper/manifesto

What we believe

Verification over hope.

Code proves itself through gates, not self-reported status.

Competition over iteration.

Why polish one attempt when four can race to the answer?

Evidence over opinions.

Every merge ships with diffs, logs, screenshots, and votes.

Fail closed, always.

If it can't prove it works, it doesn't ship. Period.

Built for autonomous operation.

Best-of-N Tournaments

Spawn N agents on the same spec, each in an isolated git worktree. Different approaches, same acceptance criteria. The best code wins — ranked by evidence, not self-assessment.

Fail-Closed Verification

Every candidate runs through independent gates: build, lint, test, visual diff. No gate pass, no merge — zero exceptions. High confidence auto-merges; anything below threshold queues for human review.

Visual Judge Council

Multiple vision LLMs independently review before/after screenshots and vote. Catches CSS regressions, layout breaks, and visual bugs that unit tests can't see.

Runs Anywhere

Model agnostic — any LLM via OpenRouter, local, or custom endpoints. Mix models in the same tournament. Drops into any CI pipeline with zero configuration.

~/hyper/evidence --spec add-auth

Every merge has receipts.

Diffs, build logs, test output, before/after screenshots, council votes — every decision is auditable and archived automatically.

6/6

Gates passed

build✓ 12s
lint✓ 3s
test✓ 47s
typecheck✓ 8s
visual✓ 8s
council✓ 15s
3/3

Council vote

Claude Opus 4.6approve
GPT-5.3-Codexapprove
Gemini 3 Proapprove
0.94

Confidence

Above 0.9 → auto-merge

8

Artifacts

diff.patch

test-output.log

screenshot-before.png

screenshot-after.png

build.log

council-votes.json

confidence.md

spec.yaml

10×

faster feature delivery

0

unverified merges to main

93%

less time on code review

24/7

ships while you sleep

~/hyper/book --demo

See Hyper in action.

30-minute walkthrough. We'll run a live tournament on your codebase.