NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Aider is AI pair programming in your terminal
Last release 7 months ago
12 Feb 2026
Ships unpredictably
gaps range from 8 days to 6 months
Nearly every release is documented
notes for 59 of the last 60 stable releases
18 versions withdrawn
withdrawn after publishing
3 years old
174 releases · first in 2023
One column per quarter.
Updated prompting to use more natural phrasing about files, the git repo, etc. Removed reliance on read-write/read-only terminology.
openrouter/anthropic/claude-3-opus, gpt-3.5-turbo--show-prompts debug switch.Added native support for Deepseek models using DEEPSEEK_API_KEY and deepseek/deepseek-chat, etc rather than as a generic OpenAI compatible API.
DEEPSEEK_API_KEY and deepseek/deepseek-chat, etc rather than as a generic OpenAI compatible API.Aider LLM code editing leaderboards that rank popular models according to their ability to edit code.
Nothing published for this version
Aider is now also AI pair programming in your browser! Use the --browser switch to launch an experimental browser based version of aider.
--browser switch to launch an experimental browser based version of aider./model <name> and search the list of available models with /models <query>.Adding missing google-generativeai dependency
google-generativeai dependencyAdded Gemini 1.5 Pro as a recommended free model.
--models <MODEL-NAME> to search the available models.--no-show-model-warnings to silence model warnings.Improved model warnings for unknown or unfamiliar models
Added better support for groq/llama3-70b-8192
Added support for directly connecting to Anthropic, Cohere, Gemini and many other LLM providers.
--weak-model <model-name> which allows you to specify which model to use for commit messages and chat history summarization.--4-turbo-vision--opus--sonnet--anthropic-api-key/add of images from anywhere in the filesystem.Added support for new gpt-4-turbo-2024-04-09 and gpt-4-turbo models.
gpt-4-turbo-2024-04-09 and gpt-4-turbo models.
gpt-4-0613 and worse than the gpt-4-preview-XXXX models. See recent Exercism benchmark results.gpt-4-preview-XXXX models. See recent refactor bencmark results.gpt-4-1106-preview as it performs best on both benchmarks, and significantly better on the refactoring/laziness benchmark.Improved repomap support for typescript, by @ryanfreckleton.
Fixed bug affecting parsing of git config in some environments.
Added -3 and -4 switches to use GPT 3.5 or GPT-4 (non-Turbo).
-3 and -4 switches to use GPT 3.5 or GPT-4 (non-Turbo).Issue a warning if user adds too much code to the chat.
.aiderignore
--openai-organization-id argument.Fixed bug with cost computations when --no-steam in effect
New /web command which scrapes the url, turns it into fairly clean markdown and adds it to the chat.
/web <url> command which scrapes the url, turns it into fairly clean markdown and adds it to the chat.gpt-3.5-turbo-0125.! alias for /run.Added support for --model gpt-4-0125-preview and OpenAI's alias --model gpt-4-turbo-preview. The --4turbo switch remains an alias for --model gpt-4-11
--model gpt-4-0125-preview and OpenAI's alias --model gpt-4-turbo-preview. The --4turbo switch remains an alias for --model gpt-4-1106-preview at this time./test command that runs a command and adds the output to the chat on non-zero exit status./quit as alias for /exit.--skip-check-update to skip checking for the update on launch.--openrouter as a shortcut for --openai-api-base https://openrouter.ai/api/v1OPENAI_API_BASE, OPENAI_API_TYPE, OPENAI_API_VERSION, OPENAI_API_DEPLOYMENT_ID.Improvements for unified diff editing format.
Bugfix for unified diff editing format.
Improvements to unified diff editing format.
--check-update arg to check if updates are available and exit with status code.Add images to the chat to automatically use GPT-4 Vision, by @joshuavial
Add images to the chat to automatically use GPT-4 Vision, by @joshuavial
Bugfixes:
/run command output, by @ctoth- Removed stray debug output.
Significantly reduced "lazy" coding from GPT-4 Turbo due to new unified diff edit format
gpt-4-1106-preview.--4-turbo command line switch as a shortcut for --model gpt-4-1106-preview.Upgraded to new openai python client v1.3.7.
Improved prompting for both GPT-4 and GPT-4 Turbo.
gpt-4-1106-preview).gpt-4-0613). Performance leaps from 47%/64% up to 51%/71%.Support for OpenAI's new 11/06 models:
/add used on file matching .gitignore- Fixed repo-map support for C#.
- Fixed docker image.
Updated tree-sitter dependencies to streamline the pip install process
/add wildcards.Improved repository map using tree-sitter
/add wildcards.Added support for .aiderignore file, which instructs aider to ignore parts of the git repo.
.aiderignore file, which instructs aider to ignore parts of the git repo.--commit cmd line arg, which just commits all pending changes with a sensible commit message geneated by gpt-3.5./run and /git now accept full shell commands, like: /run (cd subdir; ls)--encoding cmd line switch.Easily run aider from a docker image
soundfile package not available./add and /drop handle absolute filenames and quoted filenames
Support for Claude2 and other LLMs via OpenRouter by @joshuavial
Only git commit dirty files that GPT tries to edit
--voice-language switch to constrain /voice to transcribe to a specific languagesounddevice, as it was slowing down aider startupVoice-to-code support, which allows you to code with your voice.
Added a progress bar when initially creating a repo map.
text when using --no-pretty.--no-streamAutomatically summarize chat history to avoid exhausting context window.
--no-stream/add and /drop always use paths relative to the git root
/git command to run git from inside aider chats..gitignore with .aider* to prevent users from accidentaly adding aider files to git.--no-pretty if aider detects it is running inside a VSCode terminal.Added /git command to run git from inside aider chats.
/git command to run git from inside aider chats..gitignore with .aider* to prevent users from accidentaly adding aider files to git.--no-pretty if aider detects it is running inside a VSCode terminal.Support for the OpenAI models in Azure
--show-repo-map--verbose outputAdded --dark-mode and --light-mode to select colors optimized for terminal background
--dark-mode and --light-mode to select colors optimized for terminal background--help output/add and /drop commands--encoding into ctags, require it to return utf-8--encoding switch to specify another encoding--code-theme switch to control the pygments styling of code blocks (by @kwmiebach)Disabled general availability of gpt-4 (it is rolling out, not 100% available yet)
/add and /drop commands--encoding into ctags, require it to return utf-8--encoding switch to specify another encoding--code-theme switch to control the pygments styling of code blocks (by @kwmiebach)Ask to create a git repo if none found, to better track GPT's code changes
/add and /drop commands--encoding into ctags, require it to return utf-8--encoding switch to specify another encoding--code-theme switch to control the pygments styling of code blocks (by @kwmiebach)Benchmark comparing code editing in GPT-3.5 and GPT-4
--encoding switch to specify another encoding--code-theme switch to control the pygments styling of code blocks (by @kwmiebach)Fixed a bug to allow aider to edit files that contain triple backtick fences.
New in v0.7.2:
Plus changes from earlier v0.7.x versions:
--message to give GPT that one instruction and then exit after it replies and any edits are performed.--no-stream to disable streaming GPT responses.
Fixed a bug in the display of streaming diffs in GPT-3.5 chats
New in v0.7.1:
Plus all the additions from v0.7.0:
--message to give GPT that one instruction and then exit after it replies and any edits are performed.--no-stream to disable streaming GPT responses.
Graceful handling of context window exhaustion, including helpful tips.
--message to give GPT that one instruction and then exit after it replies and any edits are performed.--no-stream to disable streaming GPT responses.
Nothing published for this version
Nothing published for this version
Support for gpt-3.5-turbo-16k, and all OpenAI chat models
gpt-3.5-turbo-16k, and all OpenAI chat models--openai-api-base to support API proxies, etc.Nothing published for this version
Added support for gpt-3.5-turbo and gpt-4-32k.
gpt-3.5-turbo and gpt-4-32k.--map-tokens to set a token budget for the repo map, along with a PageRank based algorithm for prioritizing which files and identifiers to include in the map./tokens to report on context window token usage./clear to clear the conversation history.Your coding agent can read these notes before it upgrades. Set up the MCP server →