Open protocol from Krystal Unity

Krystal Loop Protocol

Hard-working agents. Big-brain control. No chaos.

Let fast, affordable AI agents do the heavy lifting while a stronger lead keeps the job focused, checks what comes back, and proves the product still does its main job when the work is finished.

Why it exists

More work done without losing the plot.

Agent loops can move incredibly fast. They can also burn through your best model's attention, wander away from the original job, or confidently tell you that broken work is finished while quietly removing features that worked before.

KLP freezes the product promise before work begins. The team defines the job, lets a worker build it, checks the result, gets a fresh second opinion, and repairs only what the evidence supports. The loop cannot finish until the product's important capabilities are proven again.

The loop

Six clear stages. One protected outcome.

Each stage has a purpose, no agent marks its own homework, and green technical checks cannot hide a broken product.

01

Promise

Record what the product must keep doing and the proof that it works now.

02

Scope

Define the outcome, boundaries, budget, checks, and stop conditions.

03

Build + check

Give a capable worker one bounded job, then run direct checks on its result.

04

Critique + repair

A fresh agent reviews the exact result; verified problems get bounded repairs.

05

Integrate

Treat the combined system as a new result and check it again.

06

Prove

Re-run the product proof. A lost or unproven core capability stops completion.

What changes

Vibe coding without the hangover.

Spend the big brain wisely

Use stronger models for planning, judgment, and hard decisions instead of making them carry every line of routine work.

Keep every agent on the same job

Clear boundaries and exact handovers stop workers from overlapping, reopening solved work, or quietly changing the brief.

Stop loops becoming endless

Repair limits and stop conditions prevent the team from polishing the same corner forever or spending beyond the value of the task.

Current release

A working reference, not a magic promise.

KLP Core v0.3 draft is public and provider-neutral. It adds a frozen Mission Contract and a capability gate that checks the product promise before and after agent work.

Release KLP Core v0.3 draft
Models Provider-neutral
Proof Offline repair and capability-regression fixtures
License Apache 2.0 code + CC BY 4.0 docs

Give it to your AI coding agent.

Ask what it would change about the way your agents plan, build, check, and repair work today.