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.
If the evidence shows the product will fail at a job it promises to handle, the team cannot call it finished just because the failure has not happened in production yet. Hypothetical edge cases do not automatically block completion or send agents into endless repair loops.
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.
Promise
Record what the product must keep doing and the proof that it works now.
Scope
Define the outcome, boundaries, budget, checks, and stop conditions.
Build + check
Give a capable worker one bounded job, then run direct checks on its result.
Critique + repair
A fresh agent reviews the exact result; verified problems get bounded repairs.
Integrate
Treat the combined system as a new result and check it again.
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
Keep stronger models focused on planning and review. Give suitable bounded jobs to a lower-cost capable worker. Model choice can reduce cost, but review and repair effort still count.
Keep every agent on the same job
Give each agent the context its assignment needs, not the entire project history. Keep the full job requirements and evidence. Explicit task IDs and revisions make handover mismatches easier to catch.
Stop loops becoming endless
Set one shared effort budget and a repair limit. Include extra reads, reviews and retries, then stop or reassess when the agreed limits are reached.
Measured on 19 October 2026
Less context. Fewer update checks.
Two small comparisons, measuring different things. These are our recorded results, not a promise about your bills or every future task.
20.99% fewer reported input tokens
On one real documentation assignment, compact packets used 82,601 worker-plus-critic input tokens versus 104,544 with the full reference bundle. Repairs and review rechecks are included. Both versions passed final review after one repair each.
21 update reads down to 3
In one controlled local comparison, event-based waking used 85.71% fewer transport reads than polling. Both jobs received the same prompt. This measured fewer update checks, not token savings; neither waiting path called a model.
Do not add these percentages together. Token totals span different model tokenizers; coordinator usage and monetary cost were unavailable. These results do not establish a subscription discount, general quality equivalence or production-wide performance.
Clear messages, not magic symbols.
The optional Semio adapter labels what a message means and which task and revision it belongs to. Receivers check those fields. That reduces ambiguity about the job being discussed, but it does not make the message true or give an agent permission to act. The wake bridge starts a preconfigured job; it does not use message text as launch instructions. This is a bounded protection, not prompt-injection immunity.
Current release
A working reference, not a magic promise.
KLP Core v0.3.1 draft is public and provider-neutral. It protects a frozen Mission Contract, checks the product promise before and after agent work, and sets shared effort limits so unsuccessful approaches get reassessed.
Give it to your AI coding agent.
Ask what it would change about the way your agents plan, build, check, and repair work today.