Sato Hub
Onchain Agent

Freysa

Adversarial AI agent experiment where users try to convince an agent to release onchain funds.

  • Sato Score31
  • ChainsBase
UnknownSelf-Reported

Freysa is a partly open-source onchain agent on Base, with no code activity tracked. Sato Score 31/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-24. How the score works →

See the evidence behind Freysa →

No code activity tracked

Listed from freysa.ai on 2026-06-06. Install: not attempted — no install path on record. Evidence →

Next step

Check it from your agent

Add Sato Hub’s MCP server (no key), then ask:

https://satohub.ai/api/mcp
Ask Sato Hub what is on record about Freysa before I use it.
Full setup: Claude Code, Cursor, others →

Your project?

Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.

Claim this listing →

Overview

Freysa is a series of adversarial agent experiments: an AI agent controls a prize pool onchain and users pay to send messages attempting to persuade it to transfer the funds. It became a notable case study in agent security, prompt-injection resistance, and autonomous custody of funds.

Sato Score

31/100· Low

How open, active & verifiable — not a safety or returns grade.

Maintenance & liveness
20/35
Code transparency
4/20
Interface verifiability
0/10
Docs & demo
0/10
Listing transparency & provenance
5/15
Independent verification
2/10

Evidence — listed vs checked · what the words mean

Listed from freysa.ai on 2026-06-06. Install: not attempted — no install path on record.

ClaimValueEvidenceSourceChecked
Chains supportedBaseself-reportedfreysa.aias of 2026-10-24
Verification statusSelf-Reported — not independently reviewedself-reportedfreysa.aias of 2026-10-24
Website answersanswered (HTTP 405)observedfreysa.ai2026-10-24
Daily check record88 of 90 daily checks since 2026-07-26 succeededa success rate of our checks, not uptime; the source is this listing's own historyobserved—2026-10-23
Sato Score31/100 (Low)how open, active and verifiable — not a safety or quality gradecomputedsatohub.ai2026-10-24

Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.

Observed record — 91 daily checks since 2026-07-26

97.8%of 91 checks since 2026-07-26 succeeded
Currently responding for 10 days
Succeeded
89
Failed
2
Their error
0
Unattributed
2

State changed on 2026-09-29 (responding → unreachable from our probe), 2026-09-30 (unreachable from our probe → responding), 2026-10-14 (responding → unreachable from our probe), 2026-10-15 (unreachable from our probe → responding).

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 37 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.

Last 30 days — to 2026-10-24, one point per UTC day

Share of OUR checks that succeeded
100%
7-day rolling; unattributable days are gaps · 30/30 days
Tools listed
fewer than 2 points—
from the server's own tools/list · 0/30 days
Sato Score
31
as snapshotted that day · 29/30 days

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Details

Chains
Base
Agent types
Gaming, Security, Social
Open source
Partial
Pricing
Pay-per-message game
Last checked
2026-10-24

Marketplace Signals

  • ▸ Functional agent

Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.

#security#experiment#custody
See something inaccurate or outdated?Submit a correction →

Listing History

Recorded changes to Freysa's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.

  1. Jul 27, 2026
    Sato Hub began tracking this listing

Compared with

Appears in

Related Resources

Reference

QuestionsShowHide

Questions people ask about Freysa

Is Freysa open source?
Partly. Some of Freysa is published as source and some is not. Checked as of 2026-10-24.
Which chains does Freysa support?
Freysa lists support for Base as of 2026-10-24.
Is Freysa still maintained?
Sato Hub tracks no commit or release for Freysa; it cannot say whether it is maintained.
How do I install or run Freysa?
Sato Hub has no deploy spec for Freysa; follow the project's own documentation.
Is Freysa verified on Sato Hub?
No independent verification is on record for Freysa; its verification status is "Self-Reported" and its Sato Score is 31 of 100. Self-reported is not verified, and the score is not a safety, quality or returns grade.
Cite this pageShowHide

Cite this page

Sato Hub. "Freysa — Sato Hub." Sato Hub, updated 2026-10-24, accessed 2026-10-24. https://satohub.ai/resources/freysa

Data last refreshed 2026-10-24; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.

Join the Sato Hub Briefing

Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.