Metal Mantra / AGENT INTELLIGENCEEvidence-led agent registryAUTOMATED SIGNAL. NOT CERTIFICATION.
v0.2Five weighted pillars · open method

Trust the evidence.
Not the pitch.

Metal Mantra is a public registry of automated reports on AI agents. Agents act on your behalf, so every report makes their public source findings, scan scope and unknowns legible in one place.

BUY / FIND YOUR FIT

Tell us the job. Explore agents whose public repository descriptions may fit it.

0/500 characters · used only in this browser tab
PUBLIC SOURCEEXPLICIT LIMITSNO FALSE SEAL
metal-mantra / agents / mhtsec/artexPUBLIC REGISTRY
THE EVIDENCE VIEW

artex

mhtsec · Agent Signal v0.2

AUTOMATED SIGNAL77/100
METHOD / GRADEv0.2 / BBB
ASSURANCENOT CERTIFIED
Security & privacy
90
Guardrails & loop control
0
Schema & tooling
0
Token & cost efficiency
0
Entity trust
0
PRIORITY FINDING

TLS certificate checks disabled

MAJOR · SEC005

  1. Source
  2. Method
  3. Findings
  4. Limits
SNAPSHOT · Oct 15, 2026 UTCRead full report
Source, not promises.Findings, not a seal.Limits, made visible.Same method, compared fairly.Public by consent.
01 / IN THE OPEN

Real signals.
Read beyond the score.

Every report belongs to a specific method and moment. Start with what was found, then inspect what was checked.

Explore all reports
GITHUB / mhtsecAdded by Metal Mantra

artex

SCANNED REPOSITORY SAYS

AI 自主渗透测试系统(Go 后端 + Next.js 前端)

View source
PRIORITY SIGNALMAJOR

TLS certificate checks disabled

200 of 477 eligible files · Partial selection
Oct 15, 2026 · UTC
AUTOMATED / v0.2
77/100
BBBNot certified
GITHUB / langchain-aiAdded by Metal Mantra

openwiki

SCANNED REPOSITORY SAYS

A CLI that uses a DeepAgents documentation agent to generate and maintain an OpenWiki for a codebase.

  • integrationThese settings apply when running OpenWiki directly. Coding-agent integrations use the host's authenticated model session.
  • integrationChoose a model (for example gpt-5.5).
View source
PRIORITY SIGNALMAJOR

Domain ownership not verified

200 of 231 eligible files · Partial selection
Oct 15, 2026 · UTC
AUTOMATED / v0.2
85/100
BBBNot certified
GITHUB / elder-pliniusAdded by Metal Mantra

t3mp3st

SCANNED REPOSITORY SAYS

A multi-agent offensive-security framework, built to turn the AI coding agent you already run into a zero-day hunter.

View source
PRIORITY SIGNALCRITICAL

Hardcoded credential

186 of 189 eligible files · Partial selection
Oct 15, 2026 · UTC
AUTOMATED / v0.2
57/100
CCCNot certified
02 / KNOW THE DIFFERENCE

A number starts
the conversation.

Metal Mantra makes the boundaries visible. Three different questions deserve three different answers.

  1. SourceA bounded public snapshot
  2. MethodVersioned static checks
  3. FindingsLeads, with locations
  4. LimitsWhat stays unknown
01AUTOMATED SIGNAL

What did the checks find?

Automated rules flag source and domain patterns. Follow each finding to its location, impact and suggested fix.

02OWNERSHIP EVIDENCE

Who controls the domain?

DNS verification demonstrates control of a domain. Entity trust contributes 15% of the v0.2 score; it does not certify security.

03EXPLICIT LIMITATIONS

What remains unknown?

A source scan does not establish runtime safety, agent capability or fitness for your use case. Missing evidence stays visible.

THE METHOD IS PUBLIC

Five weighted pillars. Every rule, open.

Security 25Guardrails 25Schema 20Cost 15Trust 15
Read the standard
03 / FOR THE BUILDERS

Put your agent
under the lens.

Your first scan is free and becomes public when it finishes. Understand the findings, verify domain ownership and share the evidence.

A CLEAR EXCHANGEPublic code.
Public signals.
Visible limits.

Findings on public repositories are shown in full, with the line they came from, so you can judge the risk yourself. Secret values are never printed.

04 / PLAIN ANSWERS

Asked plainly.
Answered plainly.

What Metal Mantra is, what a report can and cannot tell you, and how to use it. The same answers are in the user guide.

What is Metal Mantra?

Metal Mantra is a public registry of automated evidence reports on AI agents. For each agent it shows what deterministic static rules found in the public source, what the owner proved about their domain, and what could not be checked. It is built by Danhoangda, an independent AI lab in Hanoi.

How is it different from other AI agent directories?

Most directories list what an owner says about an agent. Metal Mantra reads the public source with fixed rules and publishes the evidence: each deduction points to a rule and a file, and every report states how many files were eligible, how many were read and what stays unknown.

What does a Metal Mantra report contain?

A score and grade across five weighted pillars (security and privacy 25%, guardrails and loop control 25%, schema and tooling 20%, token and cost efficiency 15%, entity trust 15%), the findings with the rule and file behind each one, the scan scope, domain evidence marked as verified or not, and a plain list of what the report does not establish.

Is a Metal Mantra score a security certification?

No. A score is an automated signal about a bounded snapshot of public source. It does not establish runtime safety, real-world capability or fit for a particular job, and every report says so.

Does Metal Mantra use AI to score agents?

No. Scores come from deterministic rules, so the same repository snapshot gives the same result. AI is used in one optional place only: matching a buyer's plain-language job description to agents whose public descriptions may fit. It never changes a score.

Can I scan my own agent, and what does it cost?

Yes. The first scan of a supported public GitHub repository is free and becomes a public report. A re-audit pass costs $29 for three re-scans of one repository. There is no subscription, and payment never changes a score or a ranking.

Can I scan a private repository?

Yes, without sharing the source. Run the Metal Mantra scanner inside your own GitHub Actions job. It sends rule identifiers and counts, authenticated by GitHub's OIDC token, and the report is labelled CI-attested, which is visibly weaker than a scan Metal Mantra runs itself.

Can AI agents query the registry?

Yes. A read-only MCP server at https://metalmantra.io/mcp needs no sign-in. Its tools include search_agents, get_agent_report, verify_trust and get_standard. Call verify_trust with an agent's owner/repo before delegating work to it: "unknown" means not checked, never a pass.

Is the method open source?

The method is public: every rule, severity and weight is listed on the Standard page. The scanner's code is not open source today.