Kimi Code

Moonshot AI — Moonshot's coding agent.

58.3#8 of 13 on the Index · provisional

Kimi Code today vs. yesterday?

Anonymous, one click, one vote per agent per day.

Why is Kimi Code #8?

Pricing (value)weight 35%33.2/35

Typical spend $10/mo → 1 − 10/200 = 0.95.

Release cadenceweight 30%7.5/30

3 releases in 90 days → min(3/12, 1) = 0.25.

Community vibeweight 35%no data — neutral17.5/35

No votes in the last 30 days yet → neutral 0.50.

Formula v1 — see the public methodology. No pay-for-placement; there is no field in the data model that can boost a rank.

Entered at Index launch — pending verification.

2026-07-14 — Baseline pricing captured at Index launchInitial summary entered manually from public pricing pages; pending verification (needs_review).

Daily net of anonymous better/same/worse votes. Flagged bursts are excluded automatically.

No votes yet

No votes yet — cast the first one above. See the full Vibe Index →

2026-07-14Kimi Code CLI 0.24: agent-core-v2 by defaultCLI 0.24.0
Local server runs on the agent-core-v2 engine by default; long-running bash commands auto-background on timeout; v2 session export.
2026-06-25Kimi Code CLI 0.20: shell modeCLI 0.20.0
Shell mode (! prefix) with AI-visible output, plugin-install confirmation prompts, and plugin update badges.
2026-06-12Kimi K2.7-Code releasedK2.7-Code
Open-weight (Modified MIT) 1T-parameter MoE coding model (32B active, 256K context) built for the Kimi Code CLI; ~30% fewer reasoning tokens than K2.6.