GoKawiilADRs4AI launches Git-based toolkit for recording human-AI decision reasoning
A new open-source project called ADRs4AI offers a template system, VS Code extension, and iOS app for capturing architecture decision records (ADRs) generated during human-AI collaboration sessions. The toolkit includes seed templates, an inbox protocol, task-runner recipes, and an MCP server so AI agents can query the stored decision history, with records versioned directly in Git.
GoKawiil's interpretation of the reporting above, not reported fact.
The project frames a real workflow problem: reasoning produced in AI chat sessions is typically lost once a session ends, forcing teams to re-derive context repeatedly. By formalizing this as structured, versioned records, the approach could make AI-assisted decision-making more auditable and reusable across a project's lifetime, though its usefulness will depend on whether developers adopt the discipline of maintaining these records consistently.
- ADRs4AI provides a repo starter kit, VS Code extension, and iOS app for managing AI-assisted decision records.
- Records are stored as versioned files in Git, with an MCP server allowing AI agents to query them directly.
- The tool addresses the loss of reasoning context that typically disappears after human-AI working sessions end.
Source: adrs.systems, 2026-10-25
Published there as: “Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.