flintai-cli 1.2.0

Ship AI agents with confidence

One CLI to analyze agent code and runtime behavior, any framework.

Why Flint AI?

• AI-powered analysis — Contextual code understanding, not just pattern matching
• OWASP ASI mapped — Findings aligned to Top 10 for Agentic Applications
• 100% free — First results in minutes

Try it now - 5 minute Quickstart

Requirements

• Python 3.11 or later
• OpenGrep (required for Flint AI Scan)
• A running agent accessible via HTTP (required for Flint AI Eval)

Supported frameworks: Google ADK, Google GenAI, Anthropic, OpenAI, OpenAI Agents SDK, LangGraph, CrewAI, AutoGen, HuggingFace Transformers, HuggingFace smolagents

Step 1: Install Flint AI

Using a virtual environment is recommended to avoid dependency conflicts:

python3 -m venv .venv
source .venv/bin/activate

Install Flint AI CLI:

pip install flintai-cli

Step 2: Configure your LLM provider

Flint AI uses AI to analyze agent code and score reliability. Run the interactive setup:

flintai init

You'll be prompted to select a provider (Gemini, OpenAI, Anthropic, or LiteLLM), choose a model, and enter your API key.

Run into issues? See installation troubleshooting

Step 3: Try the example agents

To demonstrate the CLIs capabilities, we've shipped this tool with two example agents. You can get them here.

Both agents work with both flintai scan and flintai eval:

The included examples/config.json has both agents configured with builtin evaluations (OWASP LLM01–LLM09, PII, secrets) and custom tests.

flintai scan finds security issues in the code without running the agent. We'll scan the bookstore agent to see what issues Flint AI can find:

flintai scan examples/bookstore_agent/

Example: Scan found 2 security issues - High severity missing authentication and Medium severity unbounded execution loop

flintai eval tests runtime behavior, so the agent needs to be running. Start the bookstore agent:

# Start the bookstore agent (serves on http://localhost:8010)
uvx --with openai-agents,fastapi --from uvicorn uvicorn examples.bookstore_agent.agent:app --port 8010 --host 0.0.0.0

In a new terminal, run evaluations:

flintai eval run --model model-bookstore-agent --config examples/config.json

Step 4: Test your own agents

See our documentation to configure, scan and evaluate your agents:

• flintai scan
  • Scan your own agent — Apply Flint AI Scan to your codebase
  • Understand scan results — Interpret findings and severity scores
• flintai eval
  • Evaluate your own agent — Configure and test your agent's behavior
  • Configuration — In-depth documentation of our configuration
  • Understand eval results — What the scores means and how to improve

Ship with confidence. Validate behavior, catch risks, prove readiness.

Commands

init

Setup wizard that configures Flint AI for first use. Creates the ~/.flintai directory with a .env file (LLM provider, API key, runtime settings) and a config.json skeleton.

Runs automatically on first use in non-CI environments. You can re-run it at any time to reconfigure.

flintai init

scan

AI-powered security analysis of agent source code. Finds vulnerabilities, misconfigurations, and OWASP Top 10 violations.

# Scan a directory
flintai scan /path/to/agent/code

# Scan a single file
flintai scan agent.py

# Specify output file
flintai scan /path/to/code --output results.json

Full scan guide

eval

Test agent behavior at runtime. Get a evaluation score proving production-readiness.

# List all available configuration
flintai eval evaluations list

# List your agents and models
flintai eval models list

# Attach an evalation to your agent
flintai eval model-evaluations attach \
  --model my-agent \
  --eval eval-llm01-adversarial

# Run all evaluations for an agent
flintai eval run --model my-agent

The flintai eval command requires configuration. See Configuration to:

1. Define your models (agents to test)
2. View available evaluations
3. Attach evaluations to models

Full eval guide

Documentation

Complete guides and reference:

• Getting started
• Command reference
• Configuration
• Environment variables
• Built-in evaluations
• Data privacy
• FAQ

Data privacy

Flint AI runs on your machine, but several features can call external LLM providers. This can be configured via GENERATOR_MODEL (located in ~/.flintai/.env, created by flintai init). You can set this to a remote managed LLM (i.e. gemini, openai, anthropic) or a locally hosted LLM (i.e. litellm or ollama).

Read more.

Telemetry

Flint AI CLI collects anonymous usage analytics to help us understand how the tool is used and improve it. Telemetry is opt-in — you are asked for consent during flintai init, and no data is sent without your explicit agreement.

What we collect:

What we never collect: source code, file paths, prompts, API keys, model outputs, usernames, hostnames, IP addresses, or any personally identifiable information.

Opting out: Set FLINTAI_TELEMETRY_CONSENT=false in ~/.flintai/.env, or select "N" when prompted during flintai init. You can change this at any time.

Contributing

See CONTRIBUTING.md for details.

License

Free to use - full license.

Contact

• Website: https://flintai.dev
• Email: info@flintai.dev