Open Source | MIT License

Bulk AI Security Scanning
for GitHub Organizations

The only AI Bill of Materials tool that bulk scans entire GitHub organizations. Inventory AI models, agents, and risks across hundreds of repos with drift detection, compliance exports, and automated gating. Works with Python, JavaScript, Java, Go, and .NET.

Scan Your First Repo in 30 Seconds
aibom scan-github --repo owner/repo --output-dir results
Or scan locally: aibom generate .
Also works locally with aibom generate . View all features →
Python
TypeScript
Java
Go
.NET
Competitive Edge

The Only AIBOM Tool with
Bulk GitHub Scanning

Stop scanning repositories one by one. AIBOM clones, analyzes, and aggregates AI inventories across your entire GitHub organization in one command.

aibom scan-github --repos-file repos.txt --output-dir audit/
Reading 47 repositories from repos.txt
[1/47] cloned: acme-corp/ai-gateway
[2/47] cloned: acme-corp/rag-pipeline
[3/47] cloned: acme-corp/chatbot-service
[4/47] cloned: acme-corp/embedding-api
[5/47] cloned: acme-corp/prompt-service
... (40 more repositories)
[46/47] cloned: acme-corp/nlp-service
[47/47] cloned: acme-corp/ml-ops
Analyzing Python files...
Analyzing TypeScript files...
Evaluating risk policies...
Scan Results Summary
Repositories Scanned: 47
AI Models Found: 156 (GPT-4, Claude, Llama)
External Providers: 23 using OpenAI/Anthropic
High/Critical Risks: 12 findings
Failed Drift Gates: 3 new external providers
Outputs written to audit/SUMMARY.md

Scan 100s of Repos in Minutes

Parallel cloning and analysis. No more manual inventory of AI usage across your org.

Organization-Wide Risk Gates

Fail scans when high-risk AI usage exceeds thresholds. Enforce policies across all repos.

Aggregate Reports

One Markdown summary across all repos. Perfect for security reviews and compliance audits.

Drift Detection at Scale

Compare current scan against baselines. Catch new AI providers and tools before they hit prod.

What AIBOM Detects

AIBOM finds AI components in your code and maps them to a structured inventory with OWASP LLM risk analysis.

your_code.py
from langchain import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4",
    temperature=0.7
)
gpt-4
OpenAI / LangChain
your_app.ts
import OpenAI from "openai";

const client = new OpenAI({
    model: "gpt-4o-mini"
});
gpt-4o-mini
OpenAI / TypeScript
Assistant.java
import dev.langchain4j.model.openai.OpenAiChatModel;

OpenAiChatModel model = OpenAiChatModel.builder()
    .modelName("gpt-4")
    .build();
gpt-4
OpenAI / LangChain4j
main.go
import "github.com/openai/openai-go"

client := openai.NewClient()
resp, err := client.Chat.Completions.New(
    ctx,
    openai.ChatCompletionNewParams{
        Model: "gpt-4",
    },
)
gpt-4
OpenAI / Go
your_code.py
from langchain.agents import initialize_agent

agent = initialize_agent(
    tools,
    llm,
    agent="zero-shot-react-description"
)
ReAct Agent
zero-shot-react-description
your_code.py
from langchain.tools import Tool

search = Tool(
    name="SerpAPI",
    func=search_run
)
SerpAPI
External Search Tool
9 Source Detectors
50+ Model Providers
5 Languages
4 Export Formats

Multi-Language Support

AIBOM detects AI components across your entire polyglot codebase with specialized parsers for each language.

Python

Full AST parsing for LangChain, OpenAI, Anthropic, and more

AST Analysis Jupyter Notebooks

TypeScript

Pattern-based detection for OpenAI SDK, LangChain.js

JS/TS AST Package.json

Java

Detect LangChain4j, Spring AI, and OpenAI integrations

LangChain4j Spring AI

Go

Find OpenAI and Anthropic SDK usage in Go applications

OpenAI Go LangChain Go

.NET

Scan C# projects for Semantic Kernel and AI integrations

Semantic Kernel Azure AI

Example Output

AIBOM generates a structured JSON document mapping all AI components in your codebase with risk findings and provenance tracking.

aibom generate .
$ aibom generate . --output AI_BOM.json --audit-mode
Scanning repository...
Analyzing 247 Python files
Analyzing 56 TypeScript files
Parsing runtime manifests
Detecting AI components
Evaluating risk policies
Generated AI_BOM.json
Project: customer-support-agent
AI Components Detected:
Models:
- gpt-4 (OpenAI)
- text-embedding-3-small
Frameworks:
- langchain
- openai
Agent:
- react-agent
Tools:
- serpapi
- wikipedia
Risk Findings:
- 2 third-party provider warnings
- 1 exfil surface detected

Enterprise-Grade AI Security

From single-repo scanning to organization-wide AI inventory, AIBOM scales with your needs.

OWASP LLM Risk Analysis

Built-in heuristics aligned with OWASP LLM Top 10. Detect third-party providers, exfiltration surfaces, and prompt injection risks.

Multi-Language Support

Detect AI components in Python, Jupyter notebooks, JavaScript, TypeScript, Java, Go, and .NET codebases.

Cryptographic Attestation

Sign evidence bundles with X.509 certificates. Verify provenance, certificate chains, and enforce signer allowlists.

Drift Detection

Compare AIBOM versions to detect new models, tools, or external providers. Gate CI/CD pipelines on unauthorized changes.

Custom Risk Policies

Define organization-specific risk rules with allowlists, thresholds, and severity overrides in JSON or YAML format.

Periodic Scanning

Schedule recurring scans with trend analysis. Track novel components over time and maintain historical snapshots.

AI BOM-Like Profile

Generate executive-friendly reports with risk highlights, asset summaries, and detector coverage metrics.

Built for Security Teams at Scale

Other AIBOM tools make you scan repos one by one. AIBOM is built for organizations that need visibility across hundreds of repositories without the manual work.

01

Hidden Dependencies

Models, prompts, tools, datasets, and APIs form complex dependency graphs that are invisible to traditional SBOM tools.

02

Security Risks

Prompt injection, model poisoning, and data leakage require visibility into how AI components interact with your systems.

03

Governance

Organizations need to track AI usage for compliance, risk management, and responsible AI practices.

04

Scale Problem

Large organizations have AI spread across hundreds of repos. Manual inventory is impossible. AIBOM scans them all in one command.

Traditional SBOM Dependencies Libraries AI Models Prompts & Agents AIBOM Dependencies Libraries AI Models Prompts & Agents + = Complete visibility Security coverage Compliance ready

How It Works

Scale from a single repo to your entire GitHub organization in minutes.

1

Install AIBOM

One command to install. Works locally or in CI/CD pipelines.

pip install aibom
3

Enforce & Export

Set risk thresholds, detect drift, and export to SPDX, CycloneDX, SARIF, or VEX for compliance.

# Fail on new external AI providers
aibom diff baseline.json new.json --fail-on new-external-provider

Get Started in Seconds

One tool. Two workflows. Scan locally or bulk scan your entire GitHub organization.

Local

Scan a Single Repository

pip install aibom && aibom generate .

Common Workflows

aibom scan-github --repos-file repos.txt --baseline base.json Use case: Organization audit with drift detection
aibom generate . --audit-mode --bundle-out evidence.zip Use case: Create signed compliance bundle
aibom export --input AI_BOM.json --format spdx-json Use case: Export to SPDX for compliance tools

Built for Scale. Open Source.

AIBOM is the only open-source AIBOM tool with native bulk GitHub scanning. Join us in building the future of AI supply chain security, whether you are adding new language detectors, risk rules, or scaling features for enterprise use.

Add Detectors

Build support for new AI frameworks and languages

Risk Rules

Implement new OWASP LLM-aligned risk detections

Export Formats

Add new SBOM and compliance export formats

Bug Reports

Help us improve by reporting issues and edge cases

Free. Open Source. Enterprise-Ready.

AIBOM is MIT licensed and free forever. Get started with a single repo, or scale to scan your entire GitHub organization with no licensing tiers, no limits.

Copied to clipboard