KodaCode
Coming soon
Agents

Hand each job to the right agent.

One agent can’t be an expert at everything.

Build a team of specialists, each with its own instructions, tools and model: a reviewer that only reviews, a test writer that only writes tests, a researcher that never edits a file. The lead reads the task, picks the right specialist and hands the work over.

Every handoff in plain sight.

Watch the lead delegate as it happens: who is working on what, how much it took, and what came back. Open any specialist to see exactly what it did.

Built once, shared by the team.

Save an agent to the project and it lives in the repo, so everyone works with the same specialists. Keep personal ones global and use them everywhere.

Stop prompting one generalist. Start running a team.

SpecialistsReviewers, test writers, researchers
ConfiguredOwn instructions, tools and model
RoutedThe lead hands each job to the best fit
VisibleEvery handoff, shown as it happens
01Setting one up

Tell it when to hand work over.

An agent needs a name, a line saying when to use it, and instructions. The lead reads that line to decide when to pass work along, so it's worth writing well. Then pick its model and the tools it's allowed to use.

NameOne word, like security-reviewer. You and the lead call it @security-reviewer
Use when"Reviews a change for injection, auth and secret-handling bugs. Use after edits that touch input parsing or credentials."
InstructionsWhat it does, how it should work, and what to report back
ContextStart from the task alone, or pick up the conversation so far
ModelSame as the session, or its own from any provider you've connected
ToolsEverything the lead can use, or just a few things

Build your team.

macOSDesktop appComing soon
WindowsDesktop appComing soon
LinuxDesktop appComing soon