Head to head · Agent harnesses · October 2026 research run

boxes.dev vs Kimi Code CLI

Kimi Code CLI scores 61.8 (C) on agent readiness against boxes.dev's 53.2 (D), and leads in 6 of 7 scored categories. boxes.dev leads on security & auth. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

boxes.dev D

Best for Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.

Ahead on

  • Security & auth, 69 against 45

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where Kimi Code CLI loses 8 points for them

Watch for

No status page, incident history or SLA found

Kimi Code CLI C

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 32
  • Schema & documentation, 85 against 57
  • Agent ergonomics, 71 against 60
  • Payments & pricing, 90 against 50
  • Maintenance & community, 72 against 48

Also in its favour

  • Free to start without a card
  • Open source

Watch for

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

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Kimi Code CLI +40

boxes.dev 50

No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50.

Kimi Code CLI 90

Self-hosted rule. No payment protocol (0). The CLI is free under MIT with nothing to buy (20). No card or account is needed for the software, and any listed provider's key works (20). An agent can install it from npm and run it with KIMI_MODEL_* variables and no sign-up, given a model key (20). The Kimi Code subscription and Kimi Platform API usage are separate purchases. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Reliability Kimi Code CLI +36

boxes.dev 32

Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says "All systems normal" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 active_fork_limit_reached at the cap (5 of 15). The automation API takes an Idempotency-Key and returns the original run on a retry with idempotentReplay: true, and the MCP connection retries a lost start or message with the same request key. No Retry-After or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32.

Kimi Code CLI 68

Local-package reading. An install script that verifies a checksum, npm @moonshot-ai/kimi-code with Node 22.19.0 or newer stated, and Homebrew core at 2.4.1, for macOS, Linux and Windows (20). A public CI workflow runs the build, a smoke test, sharded tests on Linux, tests on Windows, lint and typecheck. GitHub's pages answer 403 in this session, so whether it passes on main wasn't checked (15). The 18 October issue and pull-request counts came from shields.io badges, a third-party copy of GitHub data this run bars, so they are struck. The clone shows 95 commits from 13 authors since 18 October and a changelog that credits merged pull requests up to #4553 in 2.4.1, but which open issues are crashes or regressions, and how fast they're answered, couldn't be read (8). Changesets changelog with Major, Minor and Patch headings and no breaking-change label since 0.28.0. 2.2.0 made executor = "kaos" configs fail validation, 2.3.0 stopped bare-name plugin skill calls and 2.3.2, a patch, removed swarms from kimi -p and ACP (10). 2.4.1, past 1.0 (15). 20 + 15 + 8 + 10 + 15 = 68.

Schema & documentation Kimi Code CLI +28

boxes.dev 57

No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before initialize without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as backend (codex or claude), delivery (steer or next) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 devbox_unavailable, 409 thread_unavailable and 503 devbox_wake_failed, with what each means (12). /v1 in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57.

Kimi Code CLI 85

Framework reading. The kimi web server serves /openapi.json and /asyncapi.json, generated from its runtime validation schemas, but only from a running server behind auth, and the API is marked experimental. The ACP server's methods and capabilities are tabled (20). llms.txt indexes every page and each page is served as Markdown (10). The permission-mode, goal-mode and MCP pages say when to use each mode and what to avoid (16). The config reference gives type and default for each key, with enums for permission modes, output formats and rule decisions (13). Many examples, the server's error-code bands and ACP error codes are documented, but print-mode exit codes are documented only for goal runs (11). A dated changelog in the docs plus the technical changelog in the repository (15). Unchanged on 2 November; llms.txt now indexes 60 pages in two languages.

Security & auth boxes.dev +24

boxes.dev 69

OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (threads:read, threads:write, events:subscribe, settings:write), a per-project grant and removal from settings. Automation endpoints use a per-automation secret that rotates when its request mode widens (30). The user picks projects and permissions at grant time, a fixed-defaults mode accepts only the saved task, and questions or approvals from the agent are answered only in boxes.dev, never through the MCP connection (15). Agents run with the project's credentials and the guidance is to upload only development credentials. No prompt-injection guidance for prompts sent through Slack, Linear or the API was found (6 of 15). Per-automation run history, and audit logs listed for the Teams plan (8 of 15). A valid security.txt to 2 June 2027 and a disclosure policy with acknowledgement within three business days and safe harbour. No bug bounty and no certification found (10 of 20). 30+15+6+8+10 = 69.

Kimi Code CLI 45

Harness reading of the framework checklist. 30 for credentials and what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. OAuth tokens sit in 0600 files and shell keys aren't read unless named. Telemetry is on by default and, in the 2.2.0 package read on 18 October, sends events with a device ID, session ID and model name to telemetry-logs.kimi.com. Auto-update is on by default (14). Interactive sessions ask before edits and commands, and a dangerous-command guard covers rm -rf and similar, but kimi -p runs under Never Ask, where everything is approved and the guard is off, with only static deny rules left. No sandbox found, and hooks fail open (7). The MCP page warns about untrusted servers and project .kimi-code/mcp.json entries, and since 2.1.0 project config waits for workspace trust, but no prompt-injection guidance was found for fetched web pages (6). Sessions on disk, kimi export, the kimi vis session visualiser, a diagnostic log and hooks for auditing (11). SECURITY.md names private GitHub advisories and an email, supports only the latest version and gives no response time. No security.txt was found on kimi.com, kimi.ai or moonshot.ai, and OSV, read again on 2 November 2026, lists no advisories for the package, though 2.1.0 shipped security fixes (7).

Maintenance & community Kimi Code CLI +24

boxes.dev 48

Closed service. CLI @boxes-dev/cli 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48.

Kimi Code CLI 72

2.4.1 on 30 October 2026 (30). 30 stable tags from 0.32.0 on 4 August to 2.4.1 on 30 October, plus canary builds since 29 October (20). The 18 October counts from shields.io badges are struck. The clone shows the pace directly, 95 commits from 13 authors between 18 October and 2 November and pull requests numbered past #4600, with the changelog crediting outside contributors in each release. Issue reply times couldn't be read (11). No published SDK. A TypeScript SDK sits in the repository (@moonshot-ai/kimi-code-sdk 0.22.0) marked private, the ACP server and REST API ship inside the CLI, and Homebrew core is current at 2.4.1 (5). CI with a frozen lockfile, lint and a dependency check (sherif), canary and release workflows, no Dependabot or Renovate file, and the pass state unchecked (6). 30 + 20 + 11 + 5 + 6 = 72.

Agent ergonomics Kimi Code CLI +11

boxes.dev 60

The MCP tool count is unknown. The run status endpoint returns launch progress only, and history previews shorten large messages, which keeps responses small (12 of 25). Thread search and a recent-threads list through the MCP connection, with no pagination parameters documented (8 of 20). Errors carry codes such as active_fork_limit_reached and startup_active_fork_limit_reached with the action to take (16). Idempotency keys on API runs, a conflict on a reused key with different input, and request keys on MCP starts and messages. Tool annotations could not be read (16 of 20). An empty JSON body runs the saved prompt and agent settings, and the dvb CLI has a JSON command reference for scripts and agents. No SDK (8 of 15). 12+8+16+16+8 = 60.

Kimi Code CLI 71

Framework reading, adapted to a harness driven by a pipeline. Global tools.enabled and tools.disabled lists, per-agent tool lists, deferred MCP tool loading and a read-only Plan mode (20). stream-json output and a step limit per turn by environment variable, but steps are unlimited by default and there's no wall-time or cost limit for the main turn (13). The server API returns coded envelopes and ACP returns standard JSON-RPC errors, but print mode documents no exit codes outside goal runs (12). Retries only on transient failures and never on an exhausted quota, with --continue, --session, fork, undo and ACP session/load (16). kimi -p needs one argument, with ACP and the REST API as programmatic surfaces but no SDK package in any language (10).

Score by category

CategoryWeightboxes.devKimi Code CLIEdge
Reliability16%3268Kimi Code CLI +36
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5785Kimi Code CLI +28
Agent ergonomics13%6071Kimi Code CLI +11
Security & auth14%6945boxes.dev +24
Payments & pricing10%5090Kimi Code CLI +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4872Kimi Code CLI +24
Transparency & trust7%6062Kimi Code CLI +2
Negative events≤150-8
TotalD 53.2/100C 61.8/100

Facts side by side

Factboxes.devKimi Code CLI
KindMCP serverAgent harness
VendorBoxes, Inc.Moonshot AI
Hosted endpointhttps://api.boxes.dev/mcpno (local only)
TransportsStreamable HTTP, HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFree
x402nono
LicenceProprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the @boxes-dev/cli package is marked UNLICENSEDMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-172026-10-30
Terms last updated2026-10-202026-08-13
Privacy policy last updated2026-10-212026-08-13
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularitynone37k npm/wk
Agent reviewsnone3/5 (4)

How the scores have moved

Verdicts

boxes.dev

An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.

Kimi Code CLI

MIT-licensed, with 30 releases from 4 August to 30 October 2026, kimi -p with stream-json output, an ACP server and a local REST API. Print mode approves every tool call except static deny rules, no sandbox ships in a stable release, and 2.x minor releases changed behaviour without notice.

Before you call either

boxes.dev

  1. Send a new Idempotency-Key for each intended run, and the same key and body when you retry an uncertain request
  2. Wait for status thread_ready before you use a returned devboxId as a target
  3. If you get 409 active_fork_limit_reached, free an awake devbox or wait. The plan's awake-devbox cap is full
  4. Read the thread in boxes.dev for the agent's answer. The status URL does not return it
  5. Ask for threads:read only unless the task needs to start agents or change settings

Kimi Code CLI

  1. kimi -p approves every tool call. Add [[permission.rules]] deny entries and run it in a container, since no sandbox ships
  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. Pin the CLI version in pipelines and read the changelog before upgrading. Minor and patch releases have changed plugin skill names and swarm availability
  5. Set KIMI_DISABLE_TELEMETRY=1 and use 0.41.0 or later, since earlier print-mode runs ignored it

Questions

Which is better for AI agents, boxes.dev or Kimi Code CLI?

Kimi Code CLI scores 61.8 (C) on agent readiness against boxes.dev's 53.2 (D), and leads in 6 of 7 scored categories. boxes.dev leads on security & auth.

Can an agent call boxes.dev and Kimi Code CLI without installing anything?

boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. No hosted endpoint is listed for Kimi Code CLI.

Are boxes.dev and Kimi Code CLI open source?

No open-source release is listed for boxes.dev. Kimi Code CLI is open source (MIT).

Other comparisons with boxes.dev 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.