OpenClaw + Kimi K3
Kimi K3 is currently selectable with OpenClaw on AgentSky. OpenClaw controls the work loop and tools; the model supplies reasoning and generation. Start a real task below with both choices already selected.
How the combination works
OpenClaw runs the work. Kimi K3 powers each turn.
OpenClaw provides an autonomous tool-using loop for browser, shell, file, and application work in a persistent cloud computer.
AgentSky supplies the persistent cloud computer, task state, usage records, and enabled tools or connectors around that combination.
OpenClaw
Owns the agent loop, repository or computer operations, tool calls, and how results are returned.
Kimi K3
Moonshot AI's model supplies the reasoning and generated output within OpenClaw's supported interface.
AgentSky
Keeps the selected pair, workspace, task state, access configuration, and itemized usage together.
Current Kimi K3 facts
What the model is
Moonshot's flagship multimodal model, with always-on reasoning and a selectable effort level.
Context window
1M tokens in the current AgentSky catalog.
Accepted input
Text, Image, Video in the current AgentSky catalog.
Model token price
$6 / $30 per 1M input / output tokens on the displayed AgentSky plan. Runtime and paid tool usage are separate.
Evaluate it on real work
Start with one bounded task and evidence you can inspect.
Name the target system, the permitted actions, the stopping condition, and one observable result. Start with read access or a reversible task.
Open the preselected Composer
The Composer above starts with OpenClaw and Kimi K3. Add the repository or project and only the tools the task needs.
Adapt this first task
Inspect the current state, complete the requested operation within the stated permissions, and return the before-and-after evidence plus anything that still needs human action.
Verify the outcome
Verify the result in the target system and check that the agent stayed within the named scope. For external writes, inspect the actual record rather than relying on the summary.
Fit and limits
When to choose OpenClaw + Kimi K3
Longer-running computer and application workflows that combine browser actions, files, and general automation.
This page establishes
- The pair is selectable in the current AgentSky compatibility matrix
- The launch carries both selections into the shared Composer
- Current catalog facts are shown when the gateway publishes them
You still need to measure
- Quality on your own repository or workflow
- End-to-end task time, recovery effort, and human review
- Total task cost, which also depends on runtime, tools, connectors, and token usage
Common questions
Related resources