ADRs4AI keeps the reasoning behind human and AI work instead of letting it evaporate with the session. It ships a repository starter with ADR and seed templates, the directives, an inbox protocol and task-runner recipes that you can adopt whole or feature by feature. A VS Code extension, also on Open VSX, gives tree views of your open questions, diagnostics that catch malformed records as you type, deep links, and an MCP server so your agents can query the record. An iOS client lets you sign in, import a repo, review, and one-tap Accept so a real answer lands as a commit.
Be the first to rate ADRs for AI. Your feedback helps other users decide.
Start from the template repository and write the question, why you are asking, the options and the recommendation.
Use the VS Code extension, which flags malformed records as you type and shows open questions as a tree.
Open the iOS client, review the open questions and accept an answer so it commits to the repo.
Similar tools in the same category โ compare side-by-side
Zephium is an open-source browser and work environment built for humans and agents on the same surfa...
Jukebox OS is a deterministic flight recorder, ACID tool sandbox and time-travel runtime for multi-a...
Junior is an open-source AI junior engineer that runs on your Mac. It watches GitHub, Slack, Linear ...
Guides and comparisons about code tools
Seven launches for the edges of the tool set: decision records, calibrated decision models, interpretability, teaching apps and agent marketplaces.
Eight new tools that decide where a coding agent runs, how many run at once, and how you keep working in the same file it is editing.
Eight new tools for what sits under an agent: deterministic memory, an agentic database, distributed inference, hardware checks and spend guards.
Nine new tools that put something deterministic between an agent and what it touches: gateways, policy firewalls, AST breakers, SQL guards and usage ceilings.
Nine new tools for evidence rather than dashboards: signed records, decision logs, MCP analytics, protocol tests, sandboxes and long-running agent supervision.