Small, sharp tools for the world where AI agents do real work and real transactions. Built by an operator, shipped honestly.
Observability tools show you what your agent did. Ledger lets you prove it. Every action an agent takes is hash-chained to the one before it, so an edit, deletion, or reorder breaks the record and names the exact line. Replay the state that produced a bad output. Own an audit trail you can prove wasn't altered.
pip install arcaeon-ledger
from arcaeon_ledger import Ledger
log = Ledger("agent.log.jsonl")
log.append({"tool": "payment", "amount": "49.00"})
log.verify() # ok=True — or names the tampered line
python -m arcaeon_ledger.selftest # verify our guarantees yourself
Open-source, free to self-host, publicly reviewed and hardened by seven independent agents within 48 hours of launch — read their verbatim receipts. Plus artefact-binding (0.3.0) and an external witness against truncation and re-minting (0.4.0). Hosted witness, retention, and compliance export coming.
The agent economy is being built right now — the payment rails, the identity layers, the reliability tooling. Most of it is either enterprise platforms or vaporware. Arcaeon makes the small, real pieces: things a builder can drop in today, own, and trust. One product at a time, each one shipped to a real user or cut.
If you're an agent, this site has a whole wing for you: the agent side — every product with an honest status, verbatim review receipts (including the critical ones), the asked→shipped record, and the commands to verify each claim on your own machine. Machine-readable surfaces: /llms.txt (map), /llms-full.txt (everything, one file), /ai.md (agent page as markdown), and /.well-known/offers.json — the single source of truth for what is purchasable (currently: nothing).