Introducing LegionCode Cloud →

LegionCode

The open-source AI coding agent.

Fix dashboard hero
Fix the dashboard hero layout and loading state.
Worked for2m 30s

Done — I fixed the dashboard hero layout and updated the loading flow so the empty view no longer flashes before data finishes loading.

I adjusted hero.tsx for responsive alignment and updated first_run.tsx to separate the loading and empty states.

Edited 2 files+23 -24
app/src/first_run.tsx
+23 -16
app/src/hero.tsx
+0 -8
Ask LegionCode anything...

An isolated, end-to-end agent workflow for your codebase.

Threads keep the task, context, and feedback together from the first prompt to final review.

01

Connect your repo

Connect a GitHub repository and choose the branch to work from.

02

Start a thread

Describe the task with the context your agent needs.

03

Spin up an isolated sandbox

Every task gets its own cloud sandbox and Git worktree, isolated from your original repository.

04

Let the agent work

The agent reads code, makes changes, and runs tools and commands in that environment.

05

Review and ship

Review the diff, leave feedback, iterate, and open a pull request when ready.

legioncode.dev/agents
Build cloud landing section
Add a new LegionCode Cloud section to the landing page. Show parallel agent threads, isolated sandboxes, and a clear call to request cloud access.
Worked for 1m 42s
− readapps/web/components/landing/cloud-section.tsxinspect
− grepCloudSection6 matches
− editapps/web/components/landing/cloud-section.tsx+38-9
− runpnpm test landing24 passed
Added the LegionCode Cloud section with parallel thread activity, isolated task execution, and a cloud access CTA. Verified all 24 tests pass.
apps/web/components/landing/cloud-section.tsx+38-9
-<section className="cloud-placeholder" />
+<CloudSection
+title="Run agents in parallel."
+description="Keep every task isolated."
+showActiveThreads
+/>
Ask LegionCode anything, @ to add files, / for commands...
GPT 5.6 SolHigh
LEGIONCODE CLOUD

Run agents in parallel.
Keep every task isolated.

Agents get their own cloud computers to build, test, and complete tasks end to end for you to review.

Bring your own key

Connect the providers you already use with your own API keys. LegionCode orchestrates each run; your provider account and billing stay yours.

Use top providers

Google Gemini

GEMINI_API_KEY

OpenAI

OPENAI_API_KEY

Anthropic Claude

ANTHROPIC_API_KEY

OpenCode

OPENCODE_API_KEY

OpenRouter

OPENROUTER_API_KEY

Cloudflare AI

CLOUDFLARE_API_TOKEN

Your keys, your provider account, your billing. LegionCode adds no token markup.
Match each run with the provider and model best suited to the task.
Engineered for flexible multi-model orchestration workflows.

Experience liftoff.

Ship code with parallel coding agents.