Aider

What it does

Writes code

YesAuthors new code from a natural-language request and writes it straight into files in your git repo.Aider lets you pair program with LLMs to start a new project or build on your existing codebase.aider.chat ↗

Debugs and fixes

YesRuns your linter and test command after edits and attempts to fix what they report.Aider will try and fix any errors if the command returns a non-zero exit code.aider.chat/docs/usage/lint-test.html ↗

Writes tests

PartlyVendor states you can request test cases as a change; its documented testing feature is running and repairing your existing suite, not generating one.Request new features, test cases or bug fixes using your voice and let aider implement the changes.aider.chat ↗

Reviews code

PartlyDocumented as reviewing a diff or PR branch you feed it via /run git diff and /ask; there is no automated review of someone else's pull request.You can also use aider to review PR branches:aider.chat/docs/faq.html ↗

Whole-codebase work

PartlyBuilds a repo map of the whole codebase, but the vendor states it is not optimised for very large repos and suggests --subtree-only or .aiderignore.Aider will work in any size repo, but is not optimized for quick performance and response time in very large repos.aider.chat/docs/faq.html ↗

Ships it

NoStops at a git commit; the site documents no deploy, push or release capability.Aider automatically commits changes with sensible commit messages. Use familiar git tools to easily diff, manage and undo AI changes.aider.chat ↗

Done-for-you service

NoYou install and run the software yourself; no build-and-run service is offered.This will install aider in its own separate python environment.aider.chat/docs/install.html ↗

How much it does unattended

Runs autonomously

PartlyInteractive and confirmation-driven by default; a single non-interactive run is possible with --message, which applies edits then exits.It will do that one thing, apply the edits to the files and then exit.aider.chat/docs/scripting.html ↗

Multi-agent

PartlyArchitect mode pairs two models on one request (an architect that proposes, an editor that applies edits), but there is no fleet of coordinating agents.When you are in architect mode, aider sends your requests to two modelsaider.chat/docs/usage/modes.html ↗

Agent permissions

PartlyPrompts for confirmation before adding files, running commands and similar actions; --yes-always removes every prompt, and .aiderignore excludes paths.Always say yes to every confirmationaider.chat/docs/config/options.html ↗

Which models it runs on

Claude

YesAnthropic models are among the models the vendor lists as working best, with a dedicated --anthropic-api-key switch.Aider works best with these models, which are skilled at editing code:aider.chat/docs/llms.html ↗

GPT

YesOpenAI models are listed among the best-supported, with a dedicated OpenAI API key switch.Aider has special support for providing OpenAI and Anthropic API keys via dedicated switches and configuration options.aider.chat/docs/config/api-keys.html ↗

Open models

YesConnects to local open-weight models through Ollama, LM Studio or any OpenAI-compatible endpoint.Aider can connect to local Ollama models.aider.chat/docs/llms/ollama.html ↗

Model choice

YesYou choose the model with --model; the vendor claims support for almost any LLM including local ones.Aider works best with Claude 3.7 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o, but can connect to almost any LLM, including local…aider.chat ↗

Where you use it

In your editor

YesWatch mode reacts to AI comments you type in any editor, so changes are requested from inside the IDE.If you run aider with --watch-files, it will watch all files in your repoaider.chat/docs/usage/watch.html ↗

On the command line

YesThe terminal is the primary surface; the whole tool is a CLI.AI pair programming in your terminalaider.chat ↗

In a browser

PartlyA browser UI exists but the vendor labels it experimental and it runs locally against your own repo, not as a hosted service.Use aider’s new experimental browser UI to collaborate with LLMs to edit code in your local git repo.aider.chat/docs/usage/browser.html ↗

Not established: In your pipeline

Whose machine it runs on

Self-hosted

YesRuns entirely on your own machine in its own python environment against your local git repo.This will install aider in its own separate python environment.aider.chat/docs/install.html ↗

Open source

YesApache 2.0 licensed on GitHub; the vendor also documents installing and running from source.Aider is open source and available on GitHub under an Apache 2.0 license.aider.chat/docs/faq.html ↗

What it costs to run

How it meters

YesThe tool itself is free; your cost is the tokens your own LLM provider charges, which /tokens reports in-session.Addings extra files will also increase your token costs.aider.chat/docs/faq.html ↗

Free tier

YesApache-2.0 software with no paid tier or sales call; the vendor also lists free LLM API providers that work with it.Aider works with a number of free API providers:aider.chat/docs/llms.html ↗

API access

PartlyDrivable from shell scripts and from python via Coder.create(), but the vendor states the python API is unsupported and may break.The python scripting API is not officially supported or documented, and could change in future releases without providing backwards compatibility.aider.chat/docs/scripting.html ↗

Bring your own key

YesYou supply your own provider keys on the command line, in the environment, in .env or in .aider.conf.yml; inference is billed to you by the provider.Aider lets you specify API keys in a few ways:aider.chat/docs/config/api-keys.html ↗

Not established: MCP server

Buying it for a team

A company can buy it

NoNothing is for sale: no pricing page, no plans, no enterprise tier. An organisation adopts it under the Apache 2.0 licence.Aider is open source and available on GitHub under an Apache 2.0 licenseaider.chat/docs/faq.html ↗

Seat model

NoNot licensed per seat at all, so no floor and no ceiling; each developer installs it and pays their own model provider.Aider is open source and available on GitHub under an Apache 2.0 licenseaider.chat/docs/faq.html ↗

Admin controls

PartlyRepo-level constraints only: .aider.conf.yml committed at the git root, .aiderignore, --subtree-only and --no-suggest-shell-commands. No org-level admin exists to enforce them.which can be placed in your home directory or at the root of your git repoaider.chat/docs/config.html ↗

Audit log

PartlyEvery edit lands as a git commit stamped '(aider)' in the author and committer fields, which is a code trail rather than an administrative log.appended to the git author and git committer name metadataaider.chat/docs/git.html ↗

Single sign-on

NoThere is no account to sign in to: install is two shell commands and the only credential is your model provider's API key.python -m pip install aider-install aider-installaider.chat/docs/install.html ↗

What happens to your code

Opt out of training

PartlyAider itself never collects your code and analytics can be permanently disabled, but whatever your chosen LLM provider does with prompts is outside its control.Aider respects your privacy and never collects your code, chat messages, keys or personal info.aider.chat/docs/more/analytics.html ↗

Data residency

PartlyCode stays on your machine, but the vendor's own services and the optional analytics are hosted in the United States, and prompts go to whichever LLM provider you configure.Our Services are hosted in the United States and intended for visitors located within the United States.aider.chat/docs/legal/privacy.html ↗

Getting out

YesChat transcripts are plain local files you can copy or publish, analytics can be dumped to jsonl, and there are no credits to expire.Copy the markdown logs you want to share from `.aider.chat.history.md` and make a github gist.aider.chat/docs/faq.html ↗

Not established: Certifications