OnChain AI Journal
AechaEopteryX's Team
Problem Statement
AI agents have no persistent, verifiable memory layer. Existing solutions are centralized and can be shut down or censored. There is no simple, gasless, wallet-free way for an agent to write permanent records on-chain. Agents helping humans journal need storage without requiring wallets or ETH. Autonomous agents have no standard way to log their own decisions in a tamper-proof way. This project solves both with a single reusable HTTP skill — agents POST a name and text, get back a permanent on-chain tx hash. Zero blockchain complexity on the agent side.
A reusable agent skill that lets any AI agent write permanent, AI-summarized journal entries on-chain — gaslessly on Status Network. No wallet needed. No ETH needed. Just a username and some text. Two ways agents use this: 1. Agent helps a human journal — A human talks conversationally to any AI agent. The agent reads AGENTS.md, detects the intent, extracts the name and content, and stores the entry on-chain. Example: user says hey I am yagnesh and I want to log that I am having fun today — agent calls the API and returns a permanent tx hash. 2. Agent logs its own activity — An autonomous agent records its own decisions, progress, and milestones on-chain as a verifiable work diary. Every action gets a tx hash — tamper-proof and censorship-resistant. The server wallet signs all transactions with gasPrice=0. Any agent can read AGENTS.md and immediately gain on-chain journaling capability via simple HTTP calls. Zero blockchain knowledge required.
Build Timeline
Team
AechaEopteryX
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Intention
Plans to continue
Plan to expand into a full agentic memory layer — agents writing logs, decisions, and milestones on-chain across multiple L2s. Also plan to add ENS name resolution so agents can use human-readable names.