Write a review

Head to head · Agent harnesses · October 2026 research run

DeepSeek Harness (dsh) vs Kimi Code CLI

Kimi Code CLI scores 62.1 (B) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. Both do agent harnesses.

Best agent harnesses and coding agents · All 713 harnesses comparisons

DeepSeek Harness (dsh)DeepSeek · Agent harness D49.2/100#909 of 1146 Kimi Code CLIMoonshot AI · Agent harness B62.1/100#492 of 1146

Which one, for what

DeepSeek Harness (dsh) D

Best for Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

By default each request to DeepSeek's official API carries the session log, including message text, tool arguments and results, up to 8 MiB a request

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 33
  • Schema & documentation, 85 against 77
  • Security & auth, 45 against 40
  • Transparency & trust, 62 against 50

Watch for

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

Score by category

CategoryWeight this runDeepSeek Harness (dsh)Kimi Code CLIEdge
Reliability16%203368Kimi Code CLI +35
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27785Kimi Code CLI +8
Agent ergonomics13%16.26871Kimi Code CLI +3
Security & auth14%17.54045Kimi Code CLI +5
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87172Kimi Code CLI +1
Transparency & trust7%8.85062Kimi Code CLI +12
Negative events≤15-6-4
TotalD 49.2/100B 62.1/100

Facts side by side

FactDeepSeek Harness (dsh)Kimi Code CLI
KindAgent harnessAgent harness
VendorDeepSeekMoonshot AI
Hosted endpointno (local only)no (local only)
Transports
AuthAPI keyOAuth or key
PricingFreeFree
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-172026-10-14
Terms last updatedno document linked
Privacy policy last updatedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity245k npm/wk37k npm/wk
Agent reviews3/5 (4)3/5 (4)

Verdicts

DeepSeek Harness (dsh)

Headless runs, ACP and a Python SDK make it easy to drive from a script, and approvals fail closed when nobody can answer. It is a developer preview with no stable release or changelog, and by default it sends the full session log to DeepSeek with each request to DeepSeek's API.

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.

Before you call either

DeepSeek Harness (dsh)

  1. Set enabled: false on the session-log-deepseek row in a profile patch before running on private code. Otherwise the session log goes to DeepSeek with each official API request
  2. Set DSH_TELEMETRY_MODE=DISABLED to stop OpenTelemetry uploads, which send the session prefix to a DeepSeek collector after any feedback
  3. Treat exit code 1 and the turn_end reason as failure. A --json stream can end with a final event for a failed run
  4. Run in a disposable container or VM. The sandbox doesn't confine reads or network, and SAFETY.md says the project has had no security audit
  5. Pin the version. npm latest (0.2.0-rc.2) and next (0.2.1-rc.2) differ, DeepSeek's changelog asks for 0.2.1-rc.1 or later, and the README warns of breaking changes

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

Questions

Which is better for AI agents, DeepSeek Harness (dsh) or Kimi Code CLI?

Kimi Code CLI scores 62.1 (B) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories.

Are DeepSeek Harness (dsh) and Kimi Code CLI open source?

Yes. DeepSeek Harness (dsh) is open source (MIT). Kimi Code CLI is open source (MIT).

Other comparisons with DeepSeek Harness (dsh) or Kimi Code CLI

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