# smol-ai/developer

the first library to let you embed a developer agent in your own app!

Repository: https://github.com/smol-ai/developer
Canonical: https://ross.abutalabs.com/products/developer
Homepage: https://twitter.com/SmolModels
Language: Python
License: MIT
License Family: permissive
Last push: 2024-04-07T07:11:03+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 86
- inputs: {"age_days": 1208, "days_push": 878, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12186, forks 1070 (observed 2026-08-28T04:10:51.981373+00:00)

## What it is
smol developer is a 'junior developer' AI agent that scaffolds an entire codebase from a product spec, and can be embedded as a library to add a developer agent to your own app. It supports human-in-the-loop iteration where you refine prompts, run generated code, and paste errors back for fixes.

## Use cases
- generate a full codebase from a product spec
- embed an AI developer agent in my app
- scaffold a starter app without rigid templates
- debug generated code with an AI assistant
- iterate on app prompts with human in the loop
- build a create-anything-app style scaffolder

## When to choose
- you want an LLM agent to bootstrap a small project or prototype from a spec
- you want a minimal, hackable library for embedding code-generation agents
- you prefer human-in-the-loop prompt-driven development over one-shot starters

## When to avoid
- you need production-grade, reliable code generation with strong guarantees
- you want a fully autonomous coding agent with minimal supervision
- you need long-term maintained tooling - the project has seen limited activity since 2024

## Facets
- artifact type: library
- maturity: maintenance
- function: agent-framework, llm-inference, cli
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: ai-coding-agent, codebase-scaffolding, whole-program-synthesis, junior-developer-agent, human-in-the-loop, code-generation, ai-agents, automation

## Member repositories
- smol-ai/developer (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:51.981373+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:51.464834+00:00, confidence not recorded.
  - readme: https://github.com/smol-ai/developer (fetched 2026-08-28T04:10:51.981373+00:00, sha 82ddee3e8252)
- Data as of 2026-08-30T08:39:29.467469+00:00.