Get an audit

Head to head · Agent harness · October 2026 research run

Claude Code vs Kilo Code CLI

Kilo Code CLI scores 75.4 (BB) on agent readiness against Claude Code's 61.9 (C), and leads in 4 of 7 scored categories. Claude Code leads on agent ergonomics, security & auth and transparency & trust. Both do agent harness.

Claude CodeAnthropic · Agent harness C61.9/100#409 of 841 Kilo Code CLIKilo Code Inc. · Agent harness BB75.4/100#47 of 841

Which one, for what

Claude Code C

Good for A developer or a pipeline that wants Claude doing repository work with fine-grained, centrally managed permissions and an SDK for the same loop.

Ahead on

  • Agent ergonomics, 87 against 72
  • Security & auth, 80 against 66
  • Transparency & trust, 81 against 76

Watch for

The sandbox is off by default and native Windows has none

Kilo Code CLI BB

Good 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 50
  • Schema & documentation, 90 against 80
  • Payments & pricing, 50 against 20
  • Maintenance & community, 87 against 82

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • Open source
  • No incidents deducted, where Claude Code loses 6 points for them

Watch for

Telemetry to PostHog is on by default, and the privacy policy and PRIVACY.md don't mention it

Score by category

CategoryWeight this runClaude CodeKilo Code CLIEdge
Reliability16%205085Kilo Code CLI +35
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28090Kilo Code CLI +10
Agent ergonomics13%16.28772Claude Code +15
Security & auth14%17.58066Claude Code +14
Payments & pricing10%12.52050Kilo Code CLI +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88287Kilo Code CLI +5
Transparency & trust7%8.88176Claude Code +5
Negative events≤15-60
Total61.9 · C75.4 · BB

Facts side by side

FactClaude CodeKilo Code CLI
KindAgent harnessAgent harness
VendorAnthropicKilo Code Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
LicenceProprietary. LICENSE.md says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the sourceMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-012026-10-07
Terms last updatedno date given2026-09-30
Privacy policy last updatedno date given2026-05-29
Customer content may train modelsyes, with an opt-outnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesyes
Popularity141k stars28k stars, 33k npm/wk

Verdicts

Claude Code

Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.

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.

Before you call either

Claude Code

  1. Pass --permission-mode on every claude -p run. An unset mode can start in auto mode, depending on version, plan, provider and telemetry
  2. Turn on the sandbox with sandbox.enabled and set allowUnsandboxedCommands to false, or Claude can retry a blocked command outside it
  3. Set CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 on a Claude login to stop metrics and error reports in one go
  4. Set autoUpdatesChannel to stable or DISABLE_AUTOUPDATER=1 in CI. Native installs update themselves about once a day
  5. Cap pipeline runs with --max-turns and --max-budget-usd

Kilo Code CLI

  1. Set sandbox.enabled to true in the global kilo.jsonc before kilo run --auto. --auto approves every permission request not explicitly denied
  2. Set experimental.openTelemetry to false, or KILO_TELEMETRY_LEVEL to a value other than all, to stop telemetry
  3. Add needed hosts to sandbox.allowed_hosts in global config. MCP tool calls are unavailable while network restriction is on
  4. Without --auto a non-interactive run rejects every permission prompt and exits 1
  5. Put provider keys in global config or the environment. {env:VAR} in a project kilo.json is ignored

Questions

Which is better for AI agents, Claude Code or Kilo Code CLI?

Kilo Code CLI scores 75.4 (BB) on agent readiness against Claude Code's 61.9 (C), and leads in 4 of 7 scored categories. Claude Code leads on agent ergonomics, security & auth and transparency & trust.

Are Claude Code and Kilo Code CLI open source?

No open-source release is listed for Claude Code. Kilo Code CLI is open source (MIT).

Other comparisons with Claude Code or Kilo Code CLI

Disclosure

Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.

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