Get an audit

Head to head · Agent harnesses · October 2026 research run

Agent Zero vs Kilo Code CLI

Kilo Code CLI scores 75.4 (BB) on agent readiness against Agent Zero's 54.2 (C), and leads in 6 of 7 scored categories. Agent Zero leads on payments & pricing. Both do agent harnesses.

Best agent harnesses and coding agents · All 205 harnesses comparisons

Agent ZeroAgent Zero, s.r.o. · Agent harness C54.2/100#709 of 986 Kilo Code CLIKilo Code Inc. · Agent harness BB75.4/100#48 of 986

Which one, for what

Agent Zero C

Best for A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.

Ahead on

  • Payments & pricing, 60 against 50

Also in its favour

  • No key needed to call it

Watch for

No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow

Kilo Code CLI BB

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 57
  • Schema & documentation, 90 against 64
  • Agent ergonomics, 72 against 62
  • Security & auth, 66 against 54
  • Maintenance & community, 87 against 75
  • Transparency & trust, 76 against 55

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • No incidents deducted, where Agent Zero 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 runAgent ZeroKilo Code CLIEdge
Reliability16%205785Kilo Code CLI +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26490Kilo Code CLI +26
Agent ergonomics13%16.26272Kilo Code CLI +10
Security & auth14%17.55466Kilo Code CLI +12
Payments & pricing10%12.56050Agent Zero +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87587Kilo Code CLI +12
Transparency & trust7%8.85576Kilo Code CLI +21
Negative events≤15-60
TotalC 54.2/100BB 75.4/100

Facts side by side

FactAgent ZeroKilo Code CLI
KindAgent harnessAgent harness
VendorAgent Zero, s.r.o.Kilo Code Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-232026-10-07
Terms last updatedno document linked2026-09-30
Privacy policy last updatedno document linked2026-05-29
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
Popularity19k stars28k stars, 33k npm/wk

Verdicts

Agent Zero

Self-hosted under the MIT licence, with nine releases in the 90 days to 12 October 2026 and breaking changes listed in the release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and five CVEs from the past year have no published GitHub advisory.

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

Agent Zero

  1. Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none
  2. Fill allowed_users, allowed_numbers or sender_whitelist before enabling a channel. An empty list accepts every sender
  3. Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled
  4. Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal
  5. Call POST /api_message with the X-API-KEY header. The token changes when the UI login or password changes

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, Agent Zero or Kilo Code CLI?

Kilo Code CLI scores 75.4 (BB) on agent readiness against Agent Zero's 54.2 (C), and leads in 6 of 7 scored categories. Agent Zero leads on payments & pricing.

Are Agent Zero and Kilo Code CLI open source?

Yes. Agent Zero is open source (MIT). Kilo Code CLI is open source (MIT).

Other comparisons with Agent Zero or Kilo 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