Aider

license

Apache-2.0(OSI)

source

public(GitHub)

core features withheld

no

Aider is Apache-2.0 with its full source public under Aider-AI/aider, and no managed or enterprise tier gates the core.

• https://github.com/Aider-AI/aider recorded 2026-08-13

  Apache-2.0 license on the repo, full CLI source public, 48.2k stars, 4.8k forks; no enterprise or commercial directory and no paid tier offered

• https://pypi.org/pypi/aider-chat/json recorded 2026-09-29

  PyPI metadata for aider-chat lists the classifier "License :: OSI Approved :: Apache Software License" for the package.

• https://raw.githubusercontent.com/Aider-AI/aider/main/LICENSE.txt recorded 2026-09-29

  The LICENSE file is the Apache License, with the text "Apache License" and "Version 2.0, January 2004" followed by "TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION".

• https://raw.githubusercontent.com/Aider-AI/aider/main/pyproject.toml recorded 2026-09-29

  The pyproject for the aider-chat package carries the classifier "License :: OSI Approved :: Apache Software License" and names the public repository as its Homepage.

• https://raw.githubusercontent.com/Aider-AI/aider/main/README.md recorded 2026-09-29

  The README describes Aider as a terminal tool and says "Aider lets you pair program with LLMs to start a new project or build on your existing codebase." Searched the body for enterprise, paid, premium and subscription: none.

PyPI downloads of aider-chat drive this reading, since that package is Aider's declared and primary distribution channel. The figure measures use of the product itself, not a proxy for it.

• https://github.com/Aider-AI/aider recorded 2026-08-13

  48.2k stars, 4.8k forks (corroborating, not the basis); the 'Used by' dependent count is rendered client-side and does not appear in the fetched page

• https://pypistats.org/api/packages/aider-chat/recent recorded 2026-08-13

  796,686 downloads in the trailing 30 days for aider-chat

Aider's two-model architect and editor pipeline handles multi-file changes from the terminal, but its SWE-bench Verified result in architect mode is well below the open agents that lead the category. Cline and OpenHands both score far higher on the same leaderboard.

• https://awesomeagents.ai/leaderboards/swe-bench-coding-agent-leaderboard/ recorded 2026-09-29

  The leaderboard lists "Aider (architect mode)" with "Claude Sonnet 4.5" and "31.4%" in the SWE-bench Verified column, described as "Two-model architect-editor pipeline".