Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Secbot (Python)

PyPI version Python versions PyPI downloads License

Secbot is an AI-powered security automation CLI for authorized security testing, research, and education.

Security notice: use this tool only in environments where you have explicit authorization. Unauthorized scanning, exploitation, and control actions may violate laws or regulations.

Secbot main UI

Why This Package

  • CLI-first workflow built on Typer + Rich, with one-shot and interactive operation.
  • Optional FastAPI server mode for REST/SSE integration in automation pipelines.
  • Multi-agent execution flow (secbot-cli and superhackbot) for plan, execute, and summarize loops.
  • Security toolchain covering network, web, OSINT, defense scan, reporting, and system utilities.
  • Multi-provider LLM backends including Ollama, DeepSeek, OpenAI-compatible APIs, and more.

Requirements

  • Python >= 3.10
  • pip (or uv)
  • Optional: Ollama for local models

Install

Install from PyPI (recommended)

pip install secbot

If you want beta/pre-release versions:

pip install --pre secbot

Install with uv

uv pip install secbot

Install from source

git clone https://github.com/iammm0/secbot.git
cd secbot
uv sync
uv pip install -e .

Quick Start

1. Configure environment variables

Create a .env file in your working directory:

# Cloud model backend (recommended)
LLM_PROVIDER=deepseek
DEEPSEEK_API_KEY=sk-your-api-key
DEEPSEEK_MODEL=deepseek-reasoner

# Optional local backend (Ollama)
# LLM_PROVIDER=ollama
# OLLAMA_BASE_URL=http://localhost:11434
# OLLAMA_MODEL=gemma3:1b
# OLLAMA_EMBEDDING_MODEL=nomic-embed-text

2. Run the CLI

# Interactive mode
secbot

# One-shot task
secbot "扫描 192.168.1.1 的开放端口"

# Q&A mode
secbot --ask "什么是 XSS 攻击?"

# Expert agent
secbot --agent superhackbot

# Switch backend/model
secbot model

3. Start API server (optional)

secbot server

CLI Commands

Command Description
secbot Start interactive mode
secbot "<task>" Run a single task
secbot --ask "<question>" Ask security questions
secbot --agent superhackbot Use expert agent mode
secbot model Configure provider/model/API keys
secbot server Run FastAPI backend
secbot version Show installed version

Common Environment Variables

Variable Purpose Default
LLM_PROVIDER Active model provider deepseek
DEEPSEEK_API_KEY DeepSeek API key None
DEEPSEEK_MODEL DeepSeek model deepseek-reasoner
OLLAMA_BASE_URL Ollama endpoint http://localhost:11434
OLLAMA_MODEL Ollama generation model gemma3:1b
OLLAMA_EMBEDDING_MODEL Ollama embedding model nomic-embed-text
DATABASE_URL SQLite database URL sqlite:///./data/secbot.db
LOG_LEVEL Log level INFO

Documentation

Project Links

License

This project is licensed under MIT. See LICENSE for details.

Metadata

Release files for secbot 1.10.1b2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for secbot 1.10.1b2
File Size Uploaded
secbot-1.10.1b2.tar.gz 363.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for secbot 1.10.1b2
File Interpreter ABI Platform
secbot-1.10.1b2-py3-none-any.whl Python 3 none any Details

Total release size: 789.8 kB

Release files / secbot-1.10.1b2.tar.gz

Download URL secbot-1.10.1b2.tar.gz
Size 363.4 kB
Tags Source
SHA-256 checksum
How to use checksums
133632e8240fe75bb715428ff0c059e4e7d6441cd0bcffc8118d4428de72c9cd
BLAKE2b-256 checksum
How to use checksums
9f3d84ca18415834ab99580329ae7b7a21f1eba8f2fba5959d578307cca9032f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Release files / secbot-1.10.1b2-py3-none-any.whl

Download URL secbot-1.10.1b2-py3-none-any.whl
Size 426.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a3ccb6073f7822ba10ceab647e52266d9dffbd8c6362c71e0df2e1bc2a30c8cd
BLAKE2b-256 checksum
How to use checksums
b7ae4d3c54430ff0094a7cf14a0283195c3db30e8c90ad9187de8ddbc811055b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Release history Release notifications | RSS feed

This release

1.10.1b2 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page