A tiny but powerful AI agent that scaffolds entire projects from a single prompt. Human-in-the-loop by default.
Smol Developer is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view smol-ai/developer --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Smol Developer is a compact AI agent that takes a project description and generates the entire scaffold — folder structure, files, package.json, configs, and tests. It shows you each file before writing and asks for approval, keeping you in control of the AI-generated output.
Smol Developer is a compact AI agent that takes a project description and generates the entire scaffold — folder structure, files, package.json, configs, and tests. It shows you each file before writing and asks for approval, keeping you in control of the AI-generated output.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 139 days ago.
12300 GitHub stars indicate community interest.
55 open issues signal maintenance load.
MIT license detected.
Project scaffolding
MVP generation
Learning by example
Shows files before writing, human approves each step
Generated code should be reviewed
12,300
Stars
1,500
Forks
55
Issues
MIT
License
Run large language models locally with a simple CLI. Supports Llama, Mistral, Gemma, and 100+ models with one command.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Anthropic's official CLI agent for coding. Claude-powered terminal agent that reads, writes, and refactors entire codebases.
A tiny but powerful AI agent that scaffolds entire projects from a single prompt. Human-in-the-loop by default.
Indie Hackers, Rapid Prototypers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Shows files before writing, human approves each step Generated code should be reviewed
Similar or complementary options to evaluate include Ollama, anthropic-skills, Claude Code.
May 31, 2026
2 security/trust notes recorded.
Setup difficulty is 2/5.