01
Context before code.
Explore your project with file search, symbol relationships, and relevant context for the task at hand.
CODEBASE UNDERSTANDING v0.1.2 is here / Built for Linux Big ideas.
Big ideas.
Meet better
code.
Your code, your AI, your next big thing. An editor that brings codebase context, native analysis, and hands-on building into one workspace.
Debian & Ubuntu · x86_64 · No account needed to download
Native C++ engine Workspace permissions
export function totalsByUser(users, orders) { // Index once. Look up in constant time. const totals = new Map( users.map(user => [user.id, 0]) ); for (const order of orders) { if (totals.has(order.userId)) { totals.set( order.userId, totals.get(order.userId) + order.amount ); } } return totals;}TERMINAL~/commerce
❯ rg -n "totalsByUser" src
src/services/orders.js:1
LAMIED AGENT
Read the context · locating related code
Context. Code. Checks. All in one place.
YOUR WORKFLOW. YOUR MODEL.
OpenAIAnthropicGoogle GeminiGroqNVIDIALocal models
Provider integrations, not endorsements. API access and usage depend on your provider.BUILT AROUND YOUR FLOW
Less context switching.
More forward motion.
From the first unfamiliar file to the next meaningful change. Keep the tools you need close to the code.
02
An extra pair of hands.
Ask for a focused change, follow the assistant's work, and inspect the result in your own workspace.
AI-ASSISTED BUILDING03
The output stays visible.
Run approved commands and see their logs alongside the task. Keep your checks close to your changes.
INTEGRATED TERMINAL01
Understand
Explore files, symbols, and the code around your task.
02
Build
Ask for a focused change and inspect the work as it happens.
03
Verify
Run your checks, read the logs, and review the result.
LOOK BEYOND THE DIFF
Good code does more
than just work.
Explore time and space complexity, and identify likely network hotspots. Use the findings to guide your next improvement—not as a substitute for profiling real workloads.
Explore code intelligence A better data structure EXAMPLE
Repeated scansO(u × o)For each user, scan all orders
Indexed accumulationO(u + o)Initialize users, then scan orders
A Map trades extra storage for fewer lookups.
Expected complexity with average O(1) Map access.
YOUR WORKSPACE
Local files
Review changes
Visible commands
AUTOMATION, WITH OVERSIGHT
Move quickly.
Stay in control.
See the commands, read their output, and review proposed changes. Choose whether to approve commands individually or remember permission for a trusted workspace.
Cloud AI and embedding providers may receive relevant code and prompts. Review your configuration before working with sensitive repositories.
Understand permissions & dataWhich platforms can I use today?
The verified release is a Linux amd64 Debian package for Debian and Ubuntu. AppImage, macOS, Windows, and ARM installers are not currently offered on this website.
Do I need an account or an API key?
No account is needed to download the installer. AI availability depends on your account, subscription, and provider configuration. A provider API key may be required, and provider usage can incur separate charges.
Can I use a local model?
You can configure a local model through an OpenAI-compatible endpoint. Review embedding settings too: a local chat model alone does not make remote embeddings, sign-in, or other network-dependent features work offline.
Does my code stay on my machine?
Native parsing and local complexity analysis run on your machine. Cloud AI and remote embedding configurations may send code, prompts, or tool output to configured providers or services. Review those settings before using sensitive repositories.
Will the assistant ask before running commands?
Commands require approval unless you have granted remembered command permission for that workspace. Only enable it for projects you trust. Commands run with your operating-system permissions, not in a guaranteed security sandbox.
YOUR NEXT PROJECT STARTS HERE
Make something
worth shipping.
Get Lamied for Linux. Bring your ideas and your favorite model.