Why it matters
This project empowers builders to automate complex security tasks by leveraging AI agents. It provides a framework for continuous vulnerability management, allowing developers to integrate security checks directly into their workflows. The ability to deploy agents across diverse assets offers a comprehensive approach to securing modern software stacks.

What changed

The 0security project, an open-source AI cybersecurity harness, has recently released version v0.30.0 on November 15, 2026. This release signifies ongoing development and updates to its capabilities for building and deploying continuous security agents. The project is written in TypeScript and is available under the Apache 2.0 license.

Why it matters for builders

Builders can utilize 0security to automate the discovery, proof, remediation, and monitoring of vulnerabilities. The harness supports the creation of specialized AI agents that can operate across code, binaries, dependencies, infrastructure, and even other AI agents. This allows for a proactive and continuous security posture, integrating security directly into development and operational pipelines.

Key Features:

  • Continuous Security Agents: Agents designed for ongoing vulnerability management.
  • Broad Scope: Covers code, binaries, dependencies, infrastructure, and AI agents.
  • Integrated Tools: Offers Web UI, CLI, and CI integration.
  • Self-Hosted: Runs on your own infrastructure for greater control and privacy.
  • MCP Support: Integrates with Multi-Agent Coordination Protocols.

Practical impact

Developers and security professionals can leverage 0security to enhance their application security testing and continuous monitoring efforts. The project's focus on AI agents for vulnerability detection and remediation offers a novel approach to cybersecurity. Builders can explore deploying these agents to automate penetration testing, code reviews, and infrastructure security audits. The availability of a Web UI and CLI facilitates easier integration and management of these security workflows.

Caveats and source limits

The provided repository metadata indicates a recent release (v0.30.0) and a strong developer utility score, suggesting active development. However, specific details regarding the performance benchmarks of the AI agents, the exact requirements for deployment, or comprehensive documentation are not detailed in the provided source. The readme_summary mentions "5 AI signals, 5 developer signals" and "9 developer signals" in repo_intelligence, but the specific nature of these signals beyond the general description is not elaborated. Further investigation into the repository's documentation and examples would be necessary to fully understand its operational nuances and advanced use cases.

Sources

Written with AI assistance from the linked sources; every claim below was checked against them automatically. How we produce articles.

Claim check: 12/12 supported claims - 12 evidence links - 100% avg confidence
  • 0security is an open-source AI cybersecurity harness.supported - github.com
  • It enables building and deploying continuous security agents.supported - github.com
  • Agents can find, prove, fix, and monitor vulnerabilities.supported - github.com
  • Vulnerabilities are monitored across code, binaries, dependencies, infrastructure, and AI agents.supported - github.com
  • The project offers Web UI, CLI, and CI integration.supported - github.com
  • It runs on user-provided infrastructure.supported - github.com
  • The project is written in TypeScript.supported - github.com
  • The latest release is v0.30.0.supported - github.com
  • The latest release was on November 15, 2026.supported - github.com
  • The project has 1356 stars.supported - github.com
  • The project has 179 forks.supported - github.com
  • The project is licensed under Apache 2.0.supported - github.com

Caveats

  • Single-source caution: verify critical details at the linked source.
Radar score 88/100 - how it was calculated
Reliability82
Freshness100
Novelty77
Technical85
Developer96
Ecosystem72
Confidence100
  • Reliability 82: GitHub metadata supports source trust
  • Freshness 100: Fresh GitHub release date
  • Novelty 77: Fresh GitHub release
  • Technical 85: Repository technical metadata
  • Developer 96: Developer tooling signals
  • Ecosystem 72: Fresh GitHub release
  • Confidence 100: Claims have reliable evidence
Share
XLinkedInHacker News

Discussion

Loading comments...

Related articles

AI Tools - Nov 14, 20260sec-labs/0 Cybersecurity Harness with Agent CapabilitiesThe 0sec-labs/0 repository offers an open-source cybersecurity harness. It features a web interface for code analysis, pentesting, vulnerability research, reverse engineering, verification, and fixing, alongside CLI and MCP for agent integration.Agents - Nov 16, 20260security: Open-Source AI Cybersecurity Harness0security is an open-source framework for building continuous security agents. These agents can identify, prove, fix, and monitor vulnerabilities across code, dependencies, infrastructure, and AI agents, running on user-provided infrastructure with chosen LLMs.Agents - Nov 15, 2026OfficeAgent.NET v1.3.0: Structured Office Automation for .NET AgentsOfficeAgent.NET has released version 1.3.0, offering structured automation for Word, PowerPoint, and Excel within .NET applications. This library supports coding agents with validated plans, Model-Context Protocol (MCP), and SharePoint integration.Agents - Nov 15, 2026Couchbase MCP Server Connects LLMs to Couchbase DataCouchbase has released an MCP Server that enables AI agents and LLMs, such as Claude and Copilot, to interact with data stored in Couchbase or Capella. The server supports various tools for cluster health, data schema, and query analysis, with built-in safety features.Agents - Nov 15, 202667.js: 3D Engine Driven by AI Agents67.js is a JavaScript-based 3D engine designed to be driven by AI agents. It supports WebGL2 and PBR rendering, with recent activity including a fresh release of v0.18.0.Agents - Nov 14, 2026Expo Exact: Cross-Platform App Development with AI AgentsExpo Exact is a Rust-based project enabling developers to write an application once, which then runs natively across web, macOS, iOS, and Linux. An AI agent can build, run, and test these applications on all supported platforms.