KodaCode
Coming soon

An Agentic orchestrator that works for you

The agent orchestration platform with code intelligence and persistent memory built in, not bolted on, so every agent starts with the context it needs and every token drives real progress.

macOS · Windows · Linux ·
LeadSplits up the work and hands it out
AgentsSpecialists you set up, each on its own model
AutomateChecks that run on a schedule
GoalsPlans that keep going while you're away
01Less rediscovery

Every task shouldn’t start from scratch.

The code graph

Reveals how your project fits together: every file, every function, and what calls what.

Memory

Preserves the decisions, fixes, conventions, and hard-won lessons that would otherwise be lost between sessions.

Together, they cut unnecessary exploration, reduce repeated work, and help agents spend their context and compute where it matters most.

Less rediscovery. Less wasted context. More progress per token.

Others0 calls · 0 lines
KodaCode0 calls · nothing read
Others
0 lines in context
KodaCode
answers only
02Works without you

Four ways to hand off a task.

Work with the agent turn by turn, hand a task to a crew of cheaper models, let an automation watch on a schedule, or accept a plan, set an optional dollar budget and leave it running.

03Automations

Watch one get made.

This one checks a Kubernetes cluster named pharma every 15 minutes. A small model on your own machine reads its nodes and pods and decides whether the cluster is healthy. If it is, nothing happens. If it isn't, an agent starts, investigates and reports what it found. Six automations come built in, and you can add as many as you want.

How automations work →

04Knows your code
Code graphSee how your code connects, and who calls whatExplore → MemoryProblems, fixes and decisions, linked by whyExplore → EditorAsk about a selection, review edits in placeExplore → Code reviewFour reviewers on a change, the worst problems firstExplore →
05Stays in bounds
ChangesAsk before each edit, or let them apply and keep or discard each file afterwards · control
Outside the projectOn your machine, anything that reaches past the project asks you first
UndoEvery run is recorded before it starts. One click puts it back
Mid-runSteer the agent while it works, or queue what's next
Where it runsOn your machine, or inside Docker or Podman · isolation
Your keysAPI keys and sign-in tokens live in your system's keychain, never in a plain-text file or an environment variable
06Plugs into

Use the models you already pay for.

Bring the subscriptions and API keys you already have, and mix them, with a different model for each agent if you like. Add tools from MCP servers, and let agents search the web or follow skills you write.

Try it on your own code.

macOSDesktop appComing soon
WindowsDesktop appComing soon
LinuxDesktop appComing soon

$10 a month after a 14-day trial · Questions