Evidence for change. Explicit collaboration.
Holmes-Kit connects the reason for code changes. Agent Bridge connects explicitly enrolled CLI sessions. Choose the tool that fits your work.
Documentation reviewed 2026-11-05
Documentation basis 0.40.0
Holmes-Kit
For developers delegating implementation to an AI CLI who need requirements, design, tests and code connected with evidence for each change.
Understand the tool ↗Installation guide ↗Alpha · macOS · UNLICENSED
Agent Bridge
Local collaboration between enrolled Codex/Claude sessions and managed AGY processes, separating delivery from acknowledgement. An alpha for early evaluators.
Understand the tool ↗First-use guide ↗Start with a problem: engineering notes ↗
Start independently; combine when useful
Kit connects what changes, why and how it is verified. Bridge tracks explicit peer delivery and acknowledgement. Kit is not required by Bridge; a peer message is not a Kit approval or human authorization.
- Human intent and permission
- Kit specifications and checks
- Explicit Bridge delivery
- Observe actual outcome
Read a problem, then try a tool
What should an AI check before changing code?
Add whitespace handling and a default name to one greeting function. Follow the same three tests from failure to success, connecting requirements, design decisions and execution evidence.
How can different AI CLI sessions collaborate explicitly?
A review request sent to another CLI has no reply. Should you send it again? Follow one illustrative request to separate delivery, acknowledgement, work completion and decisions under uncertainty.