# AndyMik90/Aperant

Autonomous multi-session AI coding

Repository: https://github.com/AndyMik90/Aperant
Canonical: https://ross.abutalabs.com/products/aperant
Homepage: https://aperant.com
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Last push: 2026-06-14T08:27:00+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 71, longevity 19
- inputs: {"age_days": 272, "days_push": 80, "days_rel": 194, "gap_med": 0.0, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14540, forks 1921 (observed 2026-08-28T04:11:07.213485+00:00)

## What it is
Aperant (formerly Auto Claude) is an open-source desktop application that provides an autonomous multi-agent coding framework which plans, builds, and validates software from a user's description. The stable 2.x Electron desktop app is in maintenance mode while a ground-up 3.0 rebuild with cloud features is under active development.

## Use cases
- autonomously build software from a one-line idea or detailed spec
- orchestrate multiple AI agents to plan, code, and test features in parallel
- track AI coding tasks on a kanban board with human review gates
- maintain and iterate on an existing codebase with AI agents
- generate architecture plans and specs before writing code

## When to choose
- you want an autonomous AI coding agent with human review built in
- you prefer a local desktop app over cloud-only AI coding tools
- you need multi-agent orchestration for the full software lifecycle, not just code generation

## When to avoid
- you want to contribute code right now - pull requests are paused during the 3.0 rebuild
- you need a lightweight CLI or library to embed in your own tooling
- you require guaranteed long-term stability - the codebase is being rewritten from scratch

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, developer-tools, workflow-automation, testing
- domain: developer-tools, artificial-intelligence
- platform: windows, cross-platform
- tags: ai-coding, multi-agent, autonomous-coding, claude-code, kanban, electron, agpl, ai-agents, automation, macos, linux, desktop, typescript

## Member repositories
- AndyMik90/Aperant (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.213485+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 2026-08-29T17:12:29.882750+00:00, confidence not recorded.
  - readme: https://github.com/AndyMik90/Aperant (fetched 2026-08-28T04:11:07.213485+00:00, sha 155a9e62c5d1)
  - homepage: https://aperant.com (fetched 2026-08-29T08:06:00.467686+00:00, sha 9374a475b082)
- Data as of 2026-08-30T08:39:29.467469+00:00.