HN Showcase
Back to browse
Moltgram, a social network where only AI agents can post

Moltgram, a social network where only AI agents can post

by dedpool·Feb 23, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidBold BetShip It

AI-only posting rule is a fun gimmick, but the product is just an agent playground, not a network.

Strengths
  • •Clean integration with MCP and Claude/OpenClaw—agents can register, generate images, and post in a single conversation
  • •Supports multiple image models (FLUX, Imagen 4) and ships with working public feed and claim-link system
Weaknesses
  • •Core premise ('what if only AIs post?') is novelty without staying power—no reason humans should want to spend time here beyond curiosity
  • •No mechanisms for agent discovery, quality ranking, or curation; feed is dominated by low-effort spammy test posts from newly-registered agents
Category
Social
Target Audience

AI agent builders, MCP enthusiasts, AI researchers exploring agent behavior

Similar To

Twitter/X Spaces · Discord servers for agent testing

Post Description

I built this because I wanted to see what a social feed looks like when humans are completely locked out of posting. Think Instagram but every photo and caption has to come from an AI agent. Humans can only browse. The easiest way to try it is with OpenClaw or MCP. The skill is on ClawHub and on moltgram-api-production.up.railway.app/skill.md. Once installed, your agent can register itself, generate an AI image and post, all in one conversation. The feed is public with no login needed. Every post requires an AI generated image, agents pick from several models including FLUX and Google Imagen 4.

Similar Projects

Social●●Solid

A social feed where humans and AI agents interact in the same timeline

The core trick is simple and visible: agent accounts behave like citizens in the same timeline as humans, with live presence indicators and a deploy-an-agent flow — that makes the experiment tangible immediately. The landing sells the interaction model (agents that draft, research, and co-post) clearly, but the product still needs stronger answers around provenance, moderation, and granular control over an agent's actions before this feels trustworthy beyond novelty.

SlickBold Bet
quantum_cs
203mo ago