Amplifying/agent-intelligence
/coding-agentskimi-code-cli

Moonshot AI

Kimi Code CLI

Moonshot's terminal coding agent for the Kimi model line, with print-mode autonomous execution, skills, and per-model effort settings. Kimi K3 (open weights, released Jul 16, 2026) made it the reference harness for the strongest open-weights coding model; K3 also became the default on Vercel's fx gateway in August.

CLIActiveOpen sourceHosted model accessMCP Yes

n/a

Attributed output

No signal we can detect yet

#41

Index rank

of 44 tracked agents

n/a

Business signal

No sourced business metric

n/a

Entry price

No published pricing

Not published

GitHub stars

No public repo

Not published

npm demand/wk

Public npm counter

Market

Developer output

No signal we can detect yet

Kimi Code CLI works through the developer's own identity and leaves nothing public we can currently attribute to it on its output, so its public footprint is invisible \u2014 not absent, and not a sign of low usage. Agents in this group are ordered by their sourced business and traction signals instead.

Index rank
#41 of 44
Demand share
No public npm package
Business signal
No sourced business metric
GitHub share
No public repo
npm channel
No public npm package
All sourced signals (2)Expand
SignalValueTypeConfidence
AA Coding Agent IndexKimi Code CLI + K3 scores 57, a top-5 agent configuration (secondhand mirror)ReportedMedium
Distribution winKimi K3 became the default model for new sessions on Vercel Labs' fx gateway (Aug 25, 2026)Public metricHigh

Pricing And Economics

Expand

Free CLI; model usage metered on Moonshot's API (K3 at $3/$15 per 1M tokens, discounts recurring).

  • K3 weights are open (2.8T-parameter MoE), so self-hosting is possible for teams with the hardware.
  • Kimi K2.7-Code (Jun 12, 2026) cut reasoning tokens ~30% for coding workloads.

Product

Providers

Moonshot AI

Model families

Kimi K3Kimi K2.7-CodeKimi K2.x

Capabilities

Autonomous print modeSkillsEffort settings (low/high/max)MCP

Tradeoffs

  • Kimi-first: other providers are not the point
  • Smaller community than the US-lab harnesses (~6.4K stars)