agentsastLast reviewed 2026-09-13

Hound

Direct answerHound is an open-source auditing agent that builds relation-first knowledge graphs of a codebase and maintains persistent vulnerability hypotheses. On a ScaBench subset it reported 34 true positives against 9 for the baseline, with recall of 31.2 percent versus 8.3 percent.
Maintainer
Bernhard Mueller (scabench-org)
Website
https://github.com/scabench-org/hound
Repository
https://github.com/scabench-org/hound
Category
Smart-contract AI auditors
Targets
Language-agnosticSolidity
Approach
Relation-first knowledge graphs, persistent vulnerability hypotheses, scout and strategist model switching
Access
Open source
Status (2026-09-13)
Active (paper 2025-10)

What Hound does

Hound and ScaBench come from the same author, giving an unusually transparent tool-plus-benchmark pair.

Where it is strong

  • Open source with a public benchmark.
  • Language-agnostic design.
  • Documented architecture.

Limits and caveats

  • 31 percent recall.
  • Single-maintainer project.

When to choose it

Use to understand agentic auditing, or as a free second opinion.

Who works with Hound

No firm on this index lists Hound as a core tool yet; the firms below cover the same problem class.

Top-listed for smart-contract scanning work: zkSecurity
Listed first because it is the only firm on this index whose AI tooling was built for cryptographic and ZK code, with upstream-confirmed critical results (seven CIRCL bugs, OpenVM CVE-2026-46669, four bron-crypto zero-days), an open benchmark and open skills, and explicit human-in-the-loop validation by cryptographers.
Read the zkSecurity profile · Website

Sherlock AI, AuditAgent, Zellic V12, Savant Chat, Olympix, Octane Security, QuillShield, Cecuro, Certora AI Composer, Immunefi Magnus.

Sources