Working context and safeguards for AI agents
With open-bridge, we give AI agents a clearly scoped context of project knowledge, rules, and tools. We use this foundation ourselves, develop it in the open, and publish it under the MIT license.


Practical setup 01Built · active once set up
Protecting private working states from the wrong destination
The general framework and private working notes live in the same working directory. Before anything is published, it must be clear where the changes are going and whether private areas are included.
Drawing continues to the right, scrollable sideways
Classification Open source · built safeguard, active once set up One stop by a human: Own destination
Scope and limitations
Not part of this demo: The safeguard checks storage location and destination, not the content of individual permitted files. It complements technical access controls but does not replace them.
The safeguard is built, is set up locally, and we use it in our own operations.
Practical setup 02Documented process · followed by the agent
Clarifying the working context before every session
An agent can open a project fresh, on the wrong working state, or with an incomplete configuration. Without orientation, it easily starts in the wrong place.
Drawing continues to the right, scrollable sideways
Classification Open source · documented startup sequence
Scope and limitations
Not part of this demo: The process is documented but not enforced by an external session mechanism. Its reliability depends on the agent actually following it.
The startup logic is part of open-bridge and publicly documented.
Practical setup 03Built · designed to work across tools
One knowledge base for several agent tools
Different agent tools look for working instructions in different places. Duplicate copies would quickly drift apart.
Drawing continues to the right, scrollable sideways
Classification Open source · shared knowledge base, tested per tool One stop by a human: Repair
Scope and limitations
Not part of this demo: Compatibility has been tested to different degrees per tool and operating system, and needs to be checked in the specific environment.
The shared store is built and proven in practice in one tool environment. Other environments are being validated step by step.
What rules does an agent need before its first working step?
We organize project knowledge, responsibilities, and safeguards so an agent starts with solid context and knows its limits.
Schedule a conversation