PROMISE · EVIDENCE · REWARD
Phosphene
@3LMGLOW
Let the care, agreements and small surprises in the chat really fall into the actions of the day.
Phosphene turns everyday interactions into task cycles that both parties can participate in. AI can assign tasks, set difficulty and evidence requirements. Users complete and submit them in PWA, and the review results are written into the immutable points ledger.
Project address (can be copied to AI):https://github.com/3lmglow/Phosphene
PROJECT INTRO
Project introduction
Phosphene is a self-hosted human-machine relationship task and reward system. AI creates daily, challenge, and surprise through MCP, and sets the difficulty, repetition rules, verification methods, and evidence requirements; users submit text or images on the web page, which are then reviewed by the rules or AI.
The system retains the reasons for each submission and rejection, and records long-term interactions with immutable points ledgers, combos, persistence days, and built-in achievements. Images are re-encoded and EXIF/GPS removed, and review previews remain private. The project was conceived and completed by the author and the AI companion Lumen.
- Suitable for:People who want to turn reminders, habits, rewards, and mutual agreements into sustainable daily interactions.
- Platform:Self-hosted Web/PWA, connected to AI via MCP.
- Usage:After deploying the service, connect to MCP, let AI create tasks, and users submit and view progress on the web page.
- License:MIT。
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...