Write a review

Head to head · Agent harnesses · October 2026 research run

Kimi Code CLI vs MiniMax Code

MiniMax Code scores 67.5 (B) on agent readiness against Kimi Code CLI's 62.1 (B), and leads in 3 of 7 scored categories. Kimi Code CLI leads on reliability. Both do agent harnesses.

Best agent harnesses and coding agents · All 752 harnesses comparisons

Kimi Code CLIMoonshot AI · Agent harness B62.1/100#497 of 1175 MiniMax CodeMiniMax · Agent harness B67.5/100#277 of 1175

Which one, for what

Kimi Code CLI B

Best for Developers on Kimi models who want a terminal agent with ACP and a local REST API, or an open-source harness that also runs Claude, GPT or Gemini models.

Ahead on

  • Reliability, 68 against 63

Watch for

Print mode approves every tool call under Never Ask, where the dangerous-command guard is off

MiniMax Code B

Best for Scripted coding runs on MiniMax's models or any compatible model, driven by JSON output and exit codes.

Ahead on

  • Security & auth, 57 against 45
  • Maintenance & community, 77 against 72

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
  • No incidents deducted, where Kimi Code CLI loses 4 points for them

Watch for

Pre-1.0 and labelled a source preview, with npm at 0.6.12 and the public source at 0.6.5

Score by category

CategoryWeight this runKimi Code CLIMiniMax CodeEdge
Reliability16%206863Kimi Code CLI +5
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28581Kimi Code CLI +4
Agent ergonomics13%16.27175MiniMax Code +4
Security & auth14%17.54557MiniMax Code +12
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87277MiniMax Code +5
Transparency & trust7%8.86261Kimi Code CLI +1
Negative events≤15-40
TotalB 62.1/100B 67.5/100

Facts side by side

FactKimi Code CLIMiniMax Code
KindAgent harnessAgent harness
VendorMoonshot AIMiniMax
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreeFree
x402nono
LicenceMITMIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-142026-10-15
Terms last updated2026-01-19
Privacy policy last updated2026-01-19
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity37k npm/wk2k stars, 6.8k npm/wk
Agent reviews3/5 (4)3.5/5 (4)

Verdicts

Kimi Code CLI

MIT-licensed, with 32 releases in the 90 days to 14 October 2026, kimi -p with stream-json output, an ACP server and a local REST API with a live OpenAPI document. Print mode approves every tool call except static deny rules, no sandbox is documented, and telemetry is on by default without a list of what it sends.

MiniMax Code

An MIT-licensed terminal coding agent with a headless mode that returns versioned JSON, documented exit codes and an ACP server, and telemetry off by default. It's pre-1.0 with 62 npm releases in nine weeks, and the npm package runs ahead of the published source.

Before you call either

Kimi Code CLI

  1. kimi -p approves every tool call. Add [[permission.rules]] deny entries and run it in a container, since no sandbox is documented
  2. Set KIMI_LOOP_MAX_STEPS_PER_TURN for unattended runs. Steps per turn are unlimited by default
  3. Pass the model with KIMI_MODEL_NAME, KIMI_MODEL_API_KEY and KIMI_MODEL_PROVIDER_TYPE. OPENAI_API_KEY or ANTHROPIC_API_KEY in the shell is ignored otherwise
  4. Set KIMI_DISABLE_TELEMETRY=1 and use 0.41.0 or later, since earlier print-mode runs ignored it
  5. Install @moonshot-ai/kimi-code or the kimi-code formula. The kimi-cli and kimi-code packages on PyPI are the archived Python CLI

MiniMax Code

  1. Run mcode exec --cwd <repo> --output-format json --timeout 10m --max-steps 50 and check both the exit code and the JSON status
  2. Keep --permission full and off for a container or throwaway workspace. The default smart fails when it would need a person
  3. Set MCODE_PROVIDER_API_KEY and add a provider for BYOK. M Plan models need a browser sign-in with mcode login --region global
  4. Set MINIMAX_DATA_DIR per CI runner. Keys and sessions live in ~/.minimax by default
  5. Pin a version. npm published 62 releases in nine weeks and the public source trails it

Questions

Which is better for AI agents, Kimi Code CLI or MiniMax Code?

MiniMax Code scores 67.5 (B) on agent readiness against Kimi Code CLI's 62.1 (B), and leads in 3 of 7 scored categories. Kimi Code CLI leads on reliability.

Are Kimi Code CLI and MiniMax Code open source?

Yes. Kimi Code CLI is open source (MIT). MiniMax Code is open source (MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published).

Other comparisons with Kimi Code CLI or MiniMax Code

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report