agent-harness-aibom

Purpose: Documenting the components and integration surfaces used by AI agent harnesses.

Inferred · not functionally tested

Audience: AI agent developers and security teams

Inferred · not functionally tested

Functions: data_extraction

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

agent-harness-aibom is an AI security & guardrails project. Inferred · not functionally tested: It focuses on documenting the components and integration surfaces used by AI agent harnesses. Inferred · not functionally tested: agent-harness-aibom is an open-source project aimed at AI agent developers and security teams. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: agent-harness-aibom is available on the command line, and it can be self-hosted.

Behind agent-harness-aibom is Aj7Ay, and it first shipped in 2026. The project is developed in the open on GitHub with 63 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are AIBOM generation, agent harness scanning, and model inventory. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.