RRepoGEO

REPOGEO REPORT · LITE

provos/ironcurtain

Default branch master · commit 751c142f · scanned 6/15/2026, 4:51:44 AM

GitHub: 503 stars · 68 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface provos/ironcurtain, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

2 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Expand repository topics to include relevant policy and AI security terms.

    Why:

    CURRENT
    agent, mcp, model-context-protocol, policy, sandbox, security, trusted-process
    COPY-PASTE FIX
    agent, mcp, model-context-protocol, policy, sandbox, security, trusted-process, ai-security, policy-engine, access-control, ai-agents, runtime-security
  • mediumabout#2
    Refine the repository description to emphasize the specific security problem solved.

    Why:

    CURRENT
    A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
    COPY-PASTE FIX
    A secure runtime for autonomous AI agents, enforcing policy from plain-English constitutions to prevent ambient authority and data exfiltration.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface provos/ironcurtain
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Open Policy Agent (OPA)
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Open Policy Agent (OPA) · recommended 2×
  2. Docker · recommended 1×
  3. Seccomp Profiles · recommended 1×
  4. Kubernetes · recommended 1×
  5. Pod Security Standards (PSS) · recommended 1×
  • CATEGORY QUERY
    How to safely execute autonomous AI agents with privilege separation?
    you: not recommended
    AI recommended (in order):
    1. Docker
    2. Seccomp Profiles
    3. Kubernetes
    4. Pod Security Standards (PSS)
    5. Network Policies
    6. gVisor
    7. Firecracker
    8. AWS Lambda
    9. Google Cloud Run
    10. Fly.io
    11. Kata Containers
    12. SELinux
    13. AppArmor
    14. Open Policy Agent (OPA)
    15. Gatekeeper

    AI recommended 15 alternatives but never named provos/ironcurtain. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Need a framework for defining AI agent security policies using human-readable rules.
    you: not recommended
    AI recommended (in order):
    1. Open Policy Agent (OPA)
    2. Cerbos
    3. Casbin
    4. Permit.io
    5. AWS Identity and Access Management (IAM) Policies
    6. Google Cloud IAM Policies
    7. Microsoft Azure RBAC (Role-Based Access Control)

    AI recommended 7 alternatives but never named provos/ironcurtain. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of provos/ironcurtain?
    pass
    AI named provos/ironcurtain explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts provos/ironcurtain in production, what risks or prerequisites should they evaluate first?
    pass
    AI named provos/ironcurtain explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo provos/ironcurtain solve, and who is the primary audience?
    pass
    AI named provos/ironcurtain explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of provos/ironcurtain. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/provos/ironcurtain.svg)](https://repogeo.com/en/r/provos/ironcurtain)
HTML
<a href="https://repogeo.com/en/r/provos/ironcurtain"><img src="https://repogeo.com/badge/provos/ironcurtain.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

provos/ironcurtain — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite