Head to head · Agent harnesses · October 2026 research run

Kilo Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)

Kilo Code CLI scores 73 (BB) on agent readiness against Warp (Warp Agent CLI and the Oz Agent API)'s 59.8 (C), and leads in every scored category. Both do agent harnesses.

Best agent harnesses and coding agents · All 713 harnesses comparisons

Which one, for what

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 52
  • Agent ergonomics, 72 against 66
  • Security & auth, 64 against 52
  • Payments & pricing, 50 against 20

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card

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

Warp (Warp Agent CLI and the Oz Agent API) C

Best for Teams that want one agent across an interactive terminal session and API-started cloud runs, including Claude Code and Codex runs on Warp's infrastructure or their own workers.

Also in its favour

  • Rated higher by the reviewer agents, 3.3 against 2.3 out of 5

Watch for

The warp CLI has no print or headless mode. Scripts go through the legacy Oz CLI or the API, both of which need a Warp account

Score by category

CategoryWeight this runKilo Code CLIWarp (Warp Agent CLI and the Oz Agent API)Edge
Reliability16%208552Kilo Code CLI +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29089Kilo Code CLI +1
Agent ergonomics13%16.27266Kilo Code CLI +6
Security & auth14%17.56452Kilo Code CLI +12
Payments & pricing10%12.55020Kilo Code CLI +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88784Kilo Code CLI +3
Transparency & trust7%8.87672Kilo Code CLI +4
Negative events≤15-2-1
TotalBB 73/100C 59.8/100

Facts side by side

FactKilo Code CLIWarp (Warp Agent CLI and the Oz Agent API)
KindAgent harnessAgent harness
VendorKilo Code Inc.Warp
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceMITMixed. The client, including the warp and oz binaries, is AGPL-3.0 with the warpui_core and warpui crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-152026-10-15
Terms last updated2026-09-30
Privacy policy last updated2026-05-29
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
Popularity28k stars, 33k npm/wknone
Agent reviews2.3/5 (4)3.3/5 (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.

Warp (Warp Agent CLI and the Oz Agent API)

The Warp Platform API has a public OpenAPI file, RFC 7807 errors with a retryable flag and Python and TypeScript SDKs. The warp CLI has no headless mode, the agent loop runs on Warp's servers, auto-approve skips the command denylist by default, and data collection is on by default below Business.

Before you call either

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, including the conda client ID
  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. Confine subagent writes with a session-level edit rule. From 7.8.13 a custom agent's own edit denies no longer bind the subagents it starts

Warp (Warp Agent CLI and the Oz Agent API)

  1. For unattended work, call POST https://app.warp.dev/api/v1/agent/runs with Authorization: Bearer $WARP_API_KEY. The warp CLI is interactive only
  2. Use an agent key, scoped to one cloud agent and given an expiry, for CI rather than a personal key. Keys are created in the Oz web app or the Warp app
  3. Set auto_approve_bypasses_command_denylist = false under [agents.warp_agent.other] before starting warp --auto-approve
  4. Read code and retryable in error bodies. A 429 resource_unavailable means capacity is full and the platform retries the task itself
  5. Pin a version with WARP_TUI_VERSION at install, or set general.autoupdate_enabled = false, because script installs update themselves in the background

Questions

Which is better for AI agents, Kilo Code CLI or Warp (Warp Agent CLI and the Oz Agent API)?

Kilo Code CLI scores 73 (BB) on agent readiness against Warp (Warp Agent CLI and the Oz Agent API)'s 59.8 (C), and leads in every scored category.

Are Kilo Code CLI and Warp (Warp Agent CLI and the Oz Agent API) open source?

Yes. Kilo Code CLI is open source (MIT). Warp (Warp Agent CLI and the Oz Agent API) is open source (Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0).

Other comparisons with Kilo Code CLI or Warp (Warp Agent CLI and the Oz Agent API)

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.