Obot

Purpose: Governing enterprise AI agents and MCP tool access without losing visibility, security, or developer choice.

Inferred · not functionally tested

Audience: enterprise AI, security, and platform engineering teams

Inferred · not functionally tested

Functions: agents, monitoring, workflow_automation

Inferred · not functionally tested

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

Recorded constraints: pricing: freemium · license: Proprietary · platforms: WEB · deployment: browser, embeddable, cloud_managed, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: obot.ai · github.com · github.com. These links do not verify the individual claims.

In the AI security & guardrails space, Obot takes a focused approach. Inferred · not functionally tested: It focuses on governing enterprise AI agents and MCP tool access without losing visibility, security, or developer choice. Inferred · not functionally tested: It is built as a B2B product for enterprise AI, security, and platform engineering teams. Basis unknown · not verified: There is a free tier. Basis unknown · not verified: It runs on the web and embeddable surfaces, and it can be self-hosted.

Behind Obot is Obot AI, and it first shipped in 2025. Development happens publicly on GitHub with 13 stars and 39 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are agent governance, policy enforcement, and audit trails. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.

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