Head to head · Agent harnesses · October 2026 research run

boxes.dev vs Traycer

Traycer scores 58.9 (C) on agent readiness against boxes.dev's 53.2 (D), and leads in 4 of 7 scored categories. boxes.dev leads on security & auth and payments & pricing. 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 42
  • Payments & pricing, 50 against 45

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, incident history or SLA found

Traycer C

Best for Teams who want several coding agents working together with shared context and boards.

Ahead on

  • Reliability, 65 against 32
  • Schema & documentation, 65 against 57
  • Agent ergonomics, 65 against 60
  • Maintenance & community, 75 against 48

Also in its favour

  • No key needed to call it
  • Open source

Watch for

Privacy Mode is opt-in for individuals; with it off, prompts may be logged

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.

Reliability Traycer +33

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.

Traycer 65

Local software. Builds for macOS, Linux and Windows, and package-manager publishing workflows (20). test.yml, CodeQL, OpenSSF Scorecard and secret scanning run on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). CHANGELOG.md (15). Host 1.5.3 (15). 20 + 15 + 0 + 15 + 15 = 65.

Security & auth boxes.dev +27

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.

Traycer 42

Harness reading. Code is processed in memory and not used for training, but Privacy Mode is opt-in for individuals, prompts may be logged with it off, and Sentry and PostHog 'may be enabled in release builds' (10 of 30). No approval model described in the README (8 of 20). No prompt-injection guidance (5). No audit log found (5). SECURITY.md, CodeQL, Scorecard and secret scanning (14 of 20). 10 + 8 + 5 + 5 + 14 = 42.

Maintenance & community Traycer +27

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.

Traycer 75

Commits on 6 November 2026 and host 1.5.3 (30). More than three releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current apps and CLI packages (15). CI with tests (10). 30 + 20 + 0 + 15 + 10 = 75.

Schema & documentation Traycer +8

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.

Traycer 65

Harness reading. Mintlify docs, a protocol package and a CLI (65).

Agent ergonomics Traycer +5

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.

Traycer 65

Harness reading. Model switching within an agent, agent-to-agent loops, a CLI and cross-device sync (65).

Payments & pricing boxes.dev +5

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.

Traycer 45

Scored on the paid option, Traycer's own inference subscription, whose price wasn't read (0 of 20). No protocol (0). Bring-your-own-agent use is free (20). Accounts for sync and teams weren't checked, half (10). 0 + 0 + 20 + 10 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Score by category

CategoryWeightboxes.devTraycerEdge
Reliability16%3265Traycer +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5765Traycer +8
Agent ergonomics13%6065Traycer +5
Security & auth14%6942boxes.dev +27
Payments & pricing10%5045boxes.dev +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4875Traycer +27
Transparency & trust7%6060even
Negative events≤1500
TotalD 53.2/100C 58.9/100

Facts side by side

Factboxes.devTraycer
KindMCP serverAgent harness
VendorBoxes, Inc.Traycer AI
Hosted endpointhttps://api.boxes.dev/mcpno (local only)
TransportsStreamable HTTP, HTTP
AuthOAuth or keyNone
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.txtyesno
Last release2026-11-172026-11-06
Terms last updated2026-10-20no document linked
Privacy policy last updated2026-10-21no document linked
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet

How the scores have moved

boxes.dev

No score change since it was listed.

Traycer

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.

Traycer

An open-source app for running several coding agents together with shared context, agent-to-agent messaging and team boards, on every desktop OS. Privacy Mode is opt-in for individuals, and the README says Sentry and PostHog may be on in release builds.

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

Traycer

  1. Turn on Privacy Mode if you're an individual user and don't want prompts logged
  2. CLI agents you configure send requests straight to their provider; Traycer's own inference goes through Traycer

Questions

Which is better for AI agents, boxes.dev or Traycer?

Traycer scores 58.9 (C) on agent readiness against boxes.dev's 53.2 (D), and leads in 4 of 7 scored categories. boxes.dev leads on security & auth and payments & pricing.

Can an agent call boxes.dev and Traycer without installing anything?

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

Are boxes.dev and Traycer open source?

No open-source release is listed for boxes.dev. Traycer is open source (MIT).

Other comparisons with boxes.dev or Traycer

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.