achimala/dream-loop
Agent skill for impressive 3D visuals using Blender + image gen + subagent critic
About the project
An agent skill that builds a game, app, or 3D scene in a loop: generate a target screenshot, build, have a separate critic agent compare and give feedback, repeat until satisfied.
Useful for
- Build a Three.js 3D demo matching a target art style via critic iterations
- Model a Blender scene through MCP, comparing output to a reference screenshot
- Run the target-generation and build loop to improve an existing scene's visuals
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 36 stars today.
- Interest is fading: the two-day pace is 25% of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 6 days old and already has 965 stars.
- Top new repositories this week: #6.
- Top new repositories this month: #87.
- About 8 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 965
- Stars in a day
- 36
- Forks
- 111
- Issues and pull requests
- 4
- Watchers
- 5
- Language
- JavaScript
- License
- MIT
- Created
- September 7, 2026
- Last push
- September 9, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026Top new repositories this week: #6; Top new repositories this month: #87
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.