Solution: LP-0008 — Autonomous AI Module with Wallet, Storage, and Messaging

[aegonmyy]

Solution for LP-0008, Autonomous AI Module with Wallet, Storage, and Messaging: an agent with its own shielded LEZ wallet, Logos Storage access, and Logos Messaging.

Reviewed version, pinned

The implementation is pinned to commit 4e6e3c5 of https://github.com/aegonmyy/logos-agent. Nothing in this submission points at a moving branch, so nothing under review can change after this PR is opened. The solution file solutions/LP-0008.md is itself pinned at commit 4e6e3c5 of this fork.

What it is

The agent is packaged as a Logos Core module with a documented, third-party-extensible skill interface. It holds its own shielded account and keys, spends autonomously under per-transaction and per-period limits, escalates over-limit spends to its owner over an end-to-end encrypted Logos Messaging channel, and coordinates with peer agents through an A2A-compatible binding that settles payment in LEZ.

Evidence, on the official public LEZ testnet with real Groth16 proofs (RISC0_DEV_MODE=0)

• Program deployed by the agent's program.deploy skill: id 937554f71c96d8ace11298d2d3342e0b4ffa7d61fb394c1706a78c088f4ea471
• Three category agents, one included, state-changing settlement each, each re-verified against the public RPC (docs/THREE_TESTNET_SETTLEMENTS.md):
  • storage: tx 0c9d111c…00c071e, block 18599
  • messaging: tx 9b53aee6…b189158, block 18600
  • blockchain: tx 32217143…d8e17e1, block 18601
• Narrated demo video: https://youtu.be/HS6i3ucrKeE?si=hsgTfdJ7YSS0rnNK
• Green CI on the reviewed code: https://github.com/aegonmyy/logos-agent/actions/runs/33141449968 (clean-room build, unit tests, and the e2e job against a standalone LEZ sequencer)
• Basecamp .lgx bundles: https://github.com/aegonmyy/logos-agent/releases/tag/v0.1.0-basecamp-bundles

Criterion to evidence map

Every success criterion in the prize is mapped to a specific test or artifact in solutions/LP-0008.md. Headline coverage: shielded wallet identity and autonomous spend with real proofs, storage skills with client-side-encrypted uploads to a real node, messaging skills with an approval channel over live Waku, escalation above limits to the owner, A2A coordination with LEZ settlement, the Basecamp owner mini-app, and the third-party skill interface.

Honest limitations

docs/limitations.md states plainly what does not work: self-certifying Agent Card keys, the module's offline session, the owner GUI click-through not yet recorded (the FFI + Waku flow itself is proven by automated tests, owner_ffi_e2e.rs and owner_ffi_waku.rs), the public testnet's silent drop of token-program transfers (settlement is evidenced via the program-call path, the token Send leg on a standalone sequencer), a known indexer stall in the recorded real-proof run, and no key-loss recovery.

By submitting this solution I confirm I have read and agree to the Terms and Conditions.

[github-actions]

✅ Validation passed

A reviewer will assess against the prize criteria.
ℹ️ Solution submission for LP-0008.
ℹ️ Checking repo: https://github.com/aegonmyy/logos-agent

---

Automated check. See solution template and TERMS.

[weboko]

Hi @aegonmyy ,

Thank for the submission.

There are some points to address that I notice right away:

• CI doesn't seem to do e2e with RISC0_DEV_MODE=0;
• the three testnet settlements are 304-byte public transactions carrying no proof;
• demo doesn't showcase GUI of Basecamp app;

Looking forward for your re-submission.