Head to head · Agent harnesses · October 2026 research run

boxes.dev vs mini-swe-agent

mini-swe-agent scores 62.7 (B) 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 maintenance & community. 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 58
  • Maintenance & community, 48 against 32

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, incident history or SLA found

mini-swe-agent B

Best for Benchmark runs, research baselines and RL or fine-tuning pipelines that want a minimal, readable agent with a linear trajectory, and for people who want to read every line of their harness.

Ahead on

  • Reliability, 65 against 32
  • Agent ergonomics, 69 against 60
  • Payments & pricing, 90 against 50

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

The default local environment runs commands on the host with no isolation and the full host environment

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 mini-swe-agent +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.

mini-swe-agent 90

Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). No card or account for the software, and it runs against a local model (20). An agent can install it from PyPI and run a task with no sign-up, given a model endpoint (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Reliability mini-swe-agent +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.

mini-swe-agent 65

Read as a local package, graded on 2.4.6, the release pip install mini-swe-agent installs, and still the newest tag on 4 November 2026. One official PyPI package with Python 3.10 or newer stated (20). A pytest workflow runs on every push to main with Podman, bubblewrap and Apptainer installed, 41 test files and Codecov coverage, but GitHub's pages refused this run, so whether main passes is unconfirmed (15). Issue counts and types couldn't be read (the 18 October counts came from shields.io, a third-party copy, and are struck). The git remote shows outside bug fixes merged through 22 July, such as #915, #896 and #886, and nothing merged into main since apart from a pre-commit update on 17 August, while 77 of the 85 pull requests numbered after #917 still carry open merge refs (10). Versions follow semver and v2's breaking changes came with a migration guide, but there's no changelog file and tags carry only a version bump (8). 2.4.6, past 1.0, though the PyPI classifier still says 3 - Alpha (12).

Maintenance & community boxes.dev +16

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.

mini-swe-agent 32

2.4.6 on PyPI on 2026-07-23, 104 days before this check, and still the newest tag (10). No release in the 90 days to 4 November (0). Main hasn't moved since 3 September (three commits since 23 July, one from pre-commit-ci). Outside fixes were merged within days through July, but no pull request has been merged since #917 (17 August), 77 of the 85 pull requests numbered after it still carry open merge refs on the git remote, and maintainer reply times couldn't be read; the 18 October shields.io counts are struck (5). The Python library ships in the same package as the CLI and is current (10). Dependabot and pre-commit-ci run, and CI workflows exist with their current state unconfirmed (7).

Security & auth boxes.dev +11

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.

mini-swe-agent 58

Harness reading of the framework checklist, used for every harness in this batch. 30 for 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. No telemetry in mini's own source, and prompts go only to the configured provider. LiteLLM's own network behaviour wasn't checked (28). The CLI asks before each command by default, with regex whitelists and -y to skip, but the Python DefaultAgent never asks, the default local environment has no isolation and passes the full host environment to every command, and the experimental bubblewrap sandbox leaks host variables and shares the network (CVE-2026-108592). Docker forwards no host variables unless listed (8). No prompt-injection guidance found (2). A full trajectory of every command and output saved as JSON after each step, and a trajectory inspector (13). A security policy (docs/SECURITY.md) naming four maintainers to contact by email, with no response time, which meets the disclosure-policy reading at 7 as for cowagent and tokenrip. No bounty or advisory page, and CVE-2026-108592 (VulnCheck, 10 October) still has no fix in any release or on main. Compromised LiteLLM 1.82.7 and 1.82.8 are excluded in the dependency pins since 24 March 2026 (#794) (7).

Agent ergonomics mini-swe-agent +9

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.

mini-swe-agent 69

Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. One bash tool and a short system prompt, with output over 10,000 characters cut to its first and last 5,000, but no compaction of a long history (22). Step, cost and wall-time limits, global call and cost limits by environment variable, and a 30-second timeout per command (18). The trajectory JSON records Submitted, LimitsExceeded, TimeExceeded or RepeatedFormatError, but stdout is human-readable only and these aren't process exit codes (12). Model calls retry ten times with exponential backoff, and the trajectory is saved after every step, but there's no resume and no undo (8). Python bindings only. An unattended mini run needs -y, --exit-immediately and MSWEA_CONFIGURED, the last found only in the source (9). No MCP client, ACP or server mode.

Score by category

CategoryWeightboxes.devmini-swe-agentEdge
Reliability16%3265mini-swe-agent +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5758mini-swe-agent +1
Agent ergonomics13%6069mini-swe-agent +9
Security & auth14%6958boxes.dev +11
Payments & pricing10%5090mini-swe-agent +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4832boxes.dev +16
Transparency & trust7%6056boxes.dev +4
Negative events≤1500
TotalD 53.2/100B 62.7/100

Facts side by side

Factboxes.devmini-swe-agent
KindMCP serverAgent harness
VendorBoxes, Inc.SWE-bench team (Princeton and Stanford)
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 release2026-11-172026-07-23
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
Popularitynone8.6k stars, 4.4M PyPI/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.

mini-swe-agent

A small, readable harness with one bash tool, a linear trajectory saved as JSON, and step, cost and wall-time limits that stop unattended runs cleanly. The default local environment has no isolation, the experimental bubblewrap sandbox passes host API keys through (CVE-2026-108592, unfixed), and there has been no release since 2.4.6 on 23 July 2026.

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

mini-swe-agent

  1. Run with -y --exit-immediately for unattended use. Without --exit-immediately it waits for input when the agent finishes
  2. Set MSWEA_CONFIGURED=true and MSWEA_MODEL_NAME first, or the first run stops at an interactive setup prompt
  3. Read info.exit_status in the -o trajectory file. A run that hits its limits still exits normally
  4. For untrusted repositories use -c mini.yaml -c environment.environment_class=docker -c environment.image=<image>. The local and bubblewrap environments both expose host variables
  5. Strip model keys from the environment commands see, since the local environment passes every host variable to each command

Questions

Which is better for AI agents, boxes.dev or mini-swe-agent?

mini-swe-agent scores 62.7 (B) 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 maintenance & community.

Can an agent call boxes.dev and mini-swe-agent without installing anything?

boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. No hosted endpoint is listed for mini-swe-agent.

Are boxes.dev and mini-swe-agent open source?

No open-source release is listed for boxes.dev. mini-swe-agent is open source (MIT).

Other comparisons with boxes.dev or mini-swe-agent

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.