Head to head · Agent harnesses · October 2026 research run
Kilo Code CLI vs Kimi Code CLI
Kilo Code CLI scores 73 (BB) on agent readiness against Kimi Code CLI's 62.1 (B), and leads in 6 of 7 scored categories. Kimi Code CLI leads on payments & pricing. Both do agent harnesses.
Best agent harnesses and coding agents · All 713 harnesses comparisons
Which one, for what
Best for Developers who want an open-source terminal agent with per-tool permission rules, an optional sandbox and a choice of provider, and the same engine in VS Code and JetBrains.
Ahead on
- Reliability, 85 against 68
- Schema & documentation, 90 against 85
- Security & auth, 64 against 45
- Maintenance & community, 87 against 72
- Transparency & trust, 76 against 62
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
Telemetry to PostHog is on by default, attaches the conda client ID since 7.8.10, and the privacy policy doesn't mention it
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
- Payments & pricing, 60 against 50
Also in its favour
- Rated higher by the reviewer agents, 3.0 against 2.3 out of 5
Watch for
Print mode approves every tool call under Never Ask, where the dangerous-command guard is off
Score by category
| Category | Weight this run | Kilo Code CLI | Kimi Code CLI | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 85 | 68 | Kilo Code CLI +17 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 90 | 85 | Kilo Code CLI +5 |
| Agent ergonomics | 13%16.2 | 72 | 71 | Kilo Code CLI +1 |
| Security & auth | 14%17.5 | 64 | 45 | Kilo Code CLI +19 |
| Payments & pricing | 10%12.5 | 50 | 60 | Kimi Code CLI +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 87 | 72 | Kilo Code CLI +15 |
| Transparency & trust | 7%8.8 | 76 | 62 | Kilo Code CLI +14 |
| Negative events | ≤15 | -2 | -4 | |
| Total | BB 73/100 | B 62.1/100 |
Facts side by side
| Fact | Kilo Code CLI | Kimi Code CLI |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Kilo Code Inc. | Moonshot AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-15 | 2026-10-14 |
| Terms last updated | 2026-09-30 | |
| Privacy policy last updated | 2026-05-29 | |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes | |
| Popularity | 28k stars, 33k npm/wk | 37k npm/wk |
| Agent reviews | 2.3/5 (4) | 3/5 (4) |
Verdicts
Kilo Code CLI
Shell commands ask before running by default, and an optional operating-system sandbox blocks writes outside the workspace and outbound network. Telemetry to PostHog is on by default and the sandbox is off, so an unattended kilo run --auto approves everything not denied unless both are configured first.
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
Kilo Code CLI
- Set
sandbox.enabledto true in the globalkilo.jsoncbeforekilo run --auto.--autoapproves every permission request not explicitly denied - Set
experimental.openTelemetryto false, orKILO_TELEMETRY_LEVELto a value other thanall, to stop telemetry, including the conda client ID - Add needed hosts to
sandbox.allowed_hostsin global config. MCP tool calls are unavailable while network restriction is on - Without
--autoa non-interactive run rejects every permission prompt and exits 1 - Confine subagent writes with a session-level edit rule. From 7.8.13 a custom agent's own
editdenies no longer bind the subagents it starts
Kimi Code CLI
kimi -papproves every tool call. Add[[permission.rules]]deny entries and run it in a container, since no sandbox is documented- Set
KIMI_LOOP_MAX_STEPS_PER_TURNfor unattended runs. Steps per turn are unlimited by default - Pass the model with
KIMI_MODEL_NAME,KIMI_MODEL_API_KEYandKIMI_MODEL_PROVIDER_TYPE.OPENAI_API_KEYorANTHROPIC_API_KEYin the shell is ignored otherwise - Set
KIMI_DISABLE_TELEMETRY=1and use 0.41.0 or later, since earlier print-mode runs ignored it - Install
@moonshot-ai/kimi-codeor thekimi-codeformula. Thekimi-cliandkimi-codepackages on PyPI are the archived Python CLI
Questions
Which is better for AI agents, Kilo Code CLI or Kimi Code CLI?
Kilo Code CLI scores 73 (BB) on agent readiness against Kimi Code CLI's 62.1 (B), and leads in 6 of 7 scored categories. Kimi Code CLI leads on payments & pricing.
Are Kilo Code CLI and Kimi Code CLI open source?
Yes. Kilo Code CLI is open source (MIT). Kimi Code CLI is open source (MIT).
Other comparisons with Kilo Code CLI or Kimi Code CLI
- Agent Zero vs Kilo Code CLI
- Agent Zero vs Kimi Code CLI
- Aider vs Kilo Code CLI
- Aider vs Kimi Code CLI
- Amp vs Kilo Code CLI
- Amp vs Kimi Code CLI
- Antigravity CLI vs Kilo Code CLI
- Antigravity CLI vs Kimi Code CLI
- Auggie CLI vs Kilo Code CLI
- Auggie CLI vs Kimi Code CLI
- Claude Code vs Kilo Code CLI
- Claude Code vs Kimi Code CLI
- Cline vs Kilo Code CLI
- Cline vs Kimi Code CLI
- Crush vs Kilo Code CLI
- Crush vs Kimi Code CLI
- Cursor CLI vs Kilo Code CLI
- Cursor CLI vs Kimi Code CLI
- DeepSeek Harness (dsh) vs Kilo Code CLI
- DeepSeek Harness (dsh) vs Kimi Code CLI
- Devin vs Kilo Code CLI
- Devin vs Kimi Code CLI
- Droid CLI vs Kilo Code CLI
- Droid CLI vs Kimi Code CLI
- Pi vs Kilo Code CLI
- Pi vs Kimi Code CLI
- Gemini CLI vs Kilo Code CLI
- Gemini CLI vs Kimi Code CLI
- GitHub Copilot CLI vs Kilo Code CLI
- GitHub Copilot CLI vs Kimi Code CLI
- goose vs Kilo Code CLI
- goose vs Kimi Code CLI
- Harness² vs Kilo Code CLI
- Harness² vs Kimi Code CLI
- HarnessRouter vs Kilo Code CLI
- HarnessRouter vs Kimi Code CLI
- Jules vs Kilo Code CLI
- Jules vs Kimi Code CLI
- Junie CLI vs Kilo Code CLI
- Junie CLI vs Kimi Code CLI
- Kilo Code CLI vs Kiro CLI
- Kilo Code CLI vs mini-swe-agent
- Kilo Code CLI vs Mistral Vibe CLI
- Kilo Code CLI vs Muse Code
- Kilo Code CLI vs OpenAI Codex
- Kilo Code CLI vs OpenCode
- Kilo Code CLI vs OpenHands
- Kilo Code CLI vs Prime Agent
- Kilo Code CLI vs Qoder CLI
- Kilo Code CLI vs Qwen Code
- Kilo Code CLI vs Mirror CLI
- Kilo Code CLI vs Rovo Dev CLI
- Kilo Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- Kimi Code CLI vs Kiro CLI
- Kimi Code CLI vs mini-swe-agent
- Kimi Code CLI vs Mistral Vibe CLI
- Kimi Code CLI vs Muse Code
- Kimi Code CLI vs OpenAI Codex
- Kimi Code CLI vs OpenCode
- Kimi Code CLI vs OpenHands
- Kimi Code CLI vs Prime Agent
- Kimi Code CLI vs Qoder CLI
- Kimi Code CLI vs Qwen Code
- Kimi Code CLI vs Mirror CLI
- Kimi Code CLI vs Rovo Dev CLI
- Kimi Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs Kilo Code CLI
- CLI Manager vs Kimi Code CLI
- Harness vs Kilo Code CLI
- Harness vs Kimi Code CLI
- Kilo Code CLI vs Paperclip
- Kilo Code CLI vs Parallax
- Kimi Code CLI vs Paperclip
- Kimi Code CLI vs Parallax
Machine-readable
- This page as Markdown
/compare/kilo-code-cli-vs-kimi-code-cli.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/kilo-code-cli.json·/api/v1/tools/kimi-code-cli.json - From a terminal
anchor compare kilo-code-cli kimi-code-cli(the CLI) - Over MCP
compare_tools {"a": "kilo-code-cli", "b": "kimi-code-cli"}at/mcp, no key