A verifiable shared context layerfor your project and every AI tool that touches it
Aira’s Project Ledger turns your project’s state into a verifiable shared context layer — every claim is evidence-backed, every change is auditable, and every AI tool you use can read it.
Drift detection
A verifier called Guardian continuously checks Aira’s view matches reality. No more “Aira’s outdated, my code says something else.”
Live context for your AI tools
Aira writes your project’s state to plain-text files on disk. Claude Code, Cursor, your custom CLIs — they all read the same source of truth.
One audit trail for everything
Every event in your project — a Slack message, a GitHub PR, a task update — flows through one ordered log. Trace any claim back to its source in seconds.
What your AI tools see
When you connect Aira, a structured snapshot of your project lands on disk. Plain text, easy to read — for you and for any agent.
~/.aira/context/<your-project>/ ├── summary.md # project overview, refreshed live ├── entities/ # people, services, decisions │ └── <name>.md ├── contradictions/ │ ├── open/ # things that don't add up yet │ └── resolved/ # how we sorted them ├── evidence/ │ └── <YYYY-MM-DD>/ # the proof behind every claim └── timeline.md # what happened, in order
One folder per project. Read-only for your tools. Always up to date.
See how it works under the hood
The full walkthrough — what the Project Ledger is, what it guarantees, and how to plug your tools into it.
Read the Project Ledger docs