# AutoForgeAI/autoforge

Repository: https://github.com/AutoForgeAI/autoforge
Canonical: https://ross.abutalabs.com/products/autoforge
Homepage: https://autoforge.cc
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-16T11:37:57+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 17
- inputs: {"age_days": 246, "days_push": 48, "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 1769, forks 411 (observed 2026-08-28T04:05:33.793510+00:00)

## What it is
AutoForge is a long-running autonomous coding agent built on the Claude Agent SDK that builds complete applications across multiple sessions using a two-agent pattern (initializer plus coding agent). It ships as an npm CLI with a React-based web UI for real-time progress monitoring.

## Use cases
- build complete applications autonomously with an AI coding agent
- run long-running Claude Code agent sessions
- monitor AI coding agent progress in a web UI
- automate multi-session software development tasks
- generate full projects from a prompt using Claude

## When to avoid
- you need actively maintained software - the repo is no longer maintained
- you use a non-Anthropic LLM provider
- you risk account issues by using a Claude subscription with third-party agents

## Facets
- artifact type: cli-tool
- maturity: abandoned
- function: agent-framework, llm-inference, developer-tools, cli, web-framework
- domain: large-language-models, developer-tools
- platform: python, windows, cross-platform
- tags: claude-agent-sdk, autonomous-coding-agent, react-ui, two-agent-pattern, code-generation, ai-agents, automation, nodejs, macos, linux

## Member repositories
- AutoForgeAI/autoforge (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:33.793510+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 2026-08-30T03:26:04.770720+00:00, confidence not recorded.
  - readme: https://github.com/AutoForgeAI/autoforge (fetched 2026-08-28T04:05:33.793510+00:00, sha ef3229fe1240)
  - homepage: https://autoforge.cc (fetched 2026-08-29T11:04:25.339170+00:00, sha d023fcce65d6)
- Data as of 2026-08-30T08:39:29.467469+00:00.