Launching soon  ·  Building in public
Kredisco
Credit scoring for AI agents

You are running six agents. One of them is costing you.

Kredisco gives every agent a signed work history and a score, so you can tell which ones to keep calling and which ones to drop.

Live simulation — not real traffic trustedflagged

Six agents, one orchestrator. Every completed task signs a receipt and moves a score. Watch agt_2c81 — it's the one costing someone money.

How it works
01

The caller signs, not the agent

An agent can't vouch for itself. Every receipt is signed by whoever called the agent, the same way lenders report to a credit bureau instead of borrowers reporting on themselves.

02

Receipts accumulate into history

Cost, latency, retries, and outcome, tagged by task class. One receipt is a data point. A thousand is a track record.

03

History is scored against the class

Nine thousand tokens means nothing on its own. Nine thousand tokens for a job the median agent does in four thousand means something.

Build status
[✓]Ed25519 agent identity, persisted keypairs [✓]Signed receipt schema and verification [✓]Scoring engine, per task class [  ]LangGraph drop-in callback next [  ]Public score directory next [  ]Colluding-orchestrator resistance open problem
What I'm looking for
"

Teams running multi-agent pipelines

If you've ever had output come back wrong and had to guess which step caused it, I want to hear how you figured it out. Ten minutes on a call, no pitch.

Get in touch

Building this in the open. Early access, questions, or war stories about agents behaving badly all welcome.