# 1rgs/nanocode

Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.

Repository: https://github.com/1rgs/nanocode
Canonical: https://ross.abutalabs.com/products/nanocode
Language: Python
License Family: other
Last push: 2026-01-14T05:59:51+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 62, release rhythm 35, longevity 16
- inputs: {"age_days": 235, "days_push": 231, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2556, forks 242 (observed 2026-08-28T04:07:00.697530+00:00)

## What it is
A minimal Claude Code alternative implemented as a single ~250-line Python file with zero dependencies. It runs an agentic loop with file and shell tools (read, write, edit, glob, grep, bash) in the terminal, powered by Anthropic or OpenRouter models.

## Use cases
- run an AI coding agent in the terminal
- let an LLM read, edit, and search my codebase
- minimal open-source alternative to Claude Code
- learn how an agentic coding loop works
- use any model via OpenRouter for coding assistance

## When to choose
- you want a tiny, hackable, dependency-free coding agent
- you want to study or extend a minimal agent implementation
- you already have an Anthropic or OpenRouter API key

## When to avoid
- you need production-grade features like sandboxing, MCP, or IDE integration
- you want a polished, actively maintained tool with a license file and tests
- you prefer GUI-based AI coding assistants

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: claude-code-alternative, coding-agent, single-file, zero-dependency, terminal, anthropic, openrouter, command-line, ai-agents

## Member repositories
- 1rgs/nanocode (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:00.697530+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 2026-08-30T02:23:39.274161+00:00, confidence not recorded.
  - readme: https://github.com/1rgs/nanocode (fetched 2026-08-28T04:07:00.697530+00:00, sha e5679b822d74)
- Data as of 2026-08-30T08:39:29.467469+00:00.