The open-source AI-native IDE.
Powered by the state-of-the-art agentic framework on swebench-lite
Ever tried making large changes in a codebase using AI? If you are like me, you probably were very impressed – at first. The initial bliss quickly fades away when you realise the code will be very hard to maintain, or is flat out wrong.
A proactive agent
Aide proactively proposes fixes or asks to include files that may be missing in the context. Our agent can do so by iterating on linter errors and pulling in relevant context using LSP tools, like “Go to references”.
What if LLMs could make edits across multiple files without breaking the logic? After a month of hacking, we tested our framework against SWE-Bench Lite and (kinda shockingly) became the SOTA, resolving 43% of the issues.
Developercontrol
Go ahead, do AI-edits on top of your coding session. We keep slim, VS Code-native checkpoints (we don’t use git) to easily roll back to previous states, in case the agent made any mistake.
Brainstorm, then edit.
Or the other way around.
We try to make Aide feel like a real engineer to pair-program with. Chat about a problem by @’ting the file(s) and then jump into edits, or go from a smaller set of edits and discuss their side-effects.
Quick invoke
Taking inspiration from MacOS spotlight, we created a floating widget you can invoke with CMD + K. If you have a text selection active, you quickly prompt a change for it.
Galaxy brain. Local-first.
We ship a binary called sidecar which takes care of preparing and sending prompts to LLMs, as well as giving them access to editor features. You get full control over the prompts and responses (unless you choose our subscription, sharing some data with us).
Other features
Deep reasoning
Enforce and expose deep reasoning behind complex changes. Break down large tasks into smaller units of work that follow a logical flow.
Blazing-fast edits
With prompt caching and multi-location editing, you will be amazed by how little time occurs between pressing enter and reviewing the changes.
Context persistence
The editor listens to all events and changes made by both the developer and AI to keep a continuous context.
We want to hear from you
We know we have a way to go, and we want to make a product experienced developers will love.
Talk directly to the developers at team@codestory.ai or on Discord. Shape the future of the development of Aide with us.
Downloads
MacOS
.dmg
.zip
Windows
User Installer
System Installer
.zip
Linux
.tar