
Software infrastructure to build and deploy sovereign, persistent AI security agents that continuously find, prove and fix security risks. Open source. Web UI, CLI, CI and MCP.
By the Swiss Applied AI & Cybersecurity Research Lab
0security is software infrastructure to deploy sovereign, persistent AI security agents that find and fix security risks across any tech stack, work with any model, and run anywhere.
curl -fsSL https://raw.githubusercontent.com/0sec-labs/0security/main/install.sh | bash
0
Prefer the terminal?
export OPENAI_API_KEY="your-api-key"
0 threads send new "Review ./your-repo for security problems"
0 findings list
Any supported provider works: set its key instead (Anthropic, OpenRouter, DeepSeek and more, see Models), or connect one in the browser with 0.
0-windows-x64.exe from Releases.docker run --rm ghcr.io/0sec-labs/0security:latest --help. See the Docker guide.pnpm install --frozen-lockfile && pnpm build.install.sh supports Apple Silicon macOS and x64/ARM64 Linux. Set INSTALL_DIR to change the location.Only point 0 at systems you own or are authorized to test. See Scope.
0 agents run <id> --task "Review this pull request" --yes
0 lab mcp-server --automations --workspace /absolute/path/to/repo
See extensions and MCP and the command reference.
0 is built in the open. Huge thanks to everyone who has filed a bug, fixed a doc or sent a patch.
Start with the contributing guide. Run pnpm install and pnpm dev to work on the engine. Open an issue before large changes.