Head to head · Agent harnesses · October 2026 research run

boxes.dev vs Letta

Letta scores 63.5 (B) on agent readiness against boxes.dev's 53.2 (D), and leads in 5 of 7 scored categories. boxes.dev leads on security & auth and transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Best memory layers for AI agents · All 383 memory 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 35
  • Transparency & trust, 60 against 55

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, incident history or SLA found

Letta B

Best for Long-lived coding agents and assistants that keep memory and identity across sessions and machines.

Ahead on

  • Reliability, 58 against 32
  • Schema & documentation, 70 against 57
  • Agent ergonomics, 67 against 60
  • Payments & pricing, 90 against 50
  • Maintenance & community, 85 against 48

Also in its favour

  • Runs on your own machine
  • Open source

Watch for

The default permission mode is unrestricted, the renamed bypassPermissions, so tool calls aren't confirmed unless the user picks another mode

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 Letta +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.

Letta 90

No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Maintenance & community Letta +37

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.

Letta 85

v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.

Security & auth boxes.dev +34

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.

Letta 35

Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is unrestricted; standard, acceptEdits and strict are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.

Reliability Letta +26

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.

Letta 58

Local-software lines, read for the harness. @letta-ai/letta-code on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.

Schema & documentation Letta +13

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.

Letta 70

Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an applies_to block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.

Agent ergonomics Letta +7

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.

Letta 67

Harness reading. Toolsets switch with /model, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). letta -p --output-format json for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.

Score by category

CategoryWeightboxes.devLettaEdge
Reliability16%3258Letta +26
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5770Letta +13
Agent ergonomics13%6067Letta +7
Security & auth14%6935boxes.dev +34
Payments & pricing10%5090Letta +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4885Letta +37
Transparency & trust7%6055boxes.dev +5
Negative events≤1500
TotalD 53.2/100B 63.5/100

Facts side by side

Factboxes.devLetta
KindMCP serverAgent harness
VendorBoxes, Inc.Letta
Hosted endpointhttps://api.boxes.dev/mcpno (local only)
TransportsStreamable HTTP, HTTPstdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the @boxes-dev/cli package is marked UNLICENSEDApache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-172026-11-06
Terms last updated2026-10-20no date given
Privacy policy last updated2026-10-21no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
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
Popularitynone3.8k stars, 86k npm/wk, 2.2k PyPI/wk

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.

Letta

Letta's open-source harness gives agents git-tracked memory blocks, skills, subagents and headless JSON runs, with a $0 plan and public per-agent API prices. It starts in the unrestricted permission mode, defaults to Letta Cloud, sends usage telemetry unless LETTA_CODE_TELEM=0 is set, and the V1 API server the comparisons describe is retired.

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

Letta

  1. Start headless runs with an explicit permission mode such as standard or strict; the default auto-approves tools
  2. Pass --backend local for work that must stay on the machine, since Letta Cloud is the default
  3. Set LETTA_CODE_TELEM=0 in unattended runs if usage events must not be sent
  4. Use letta -p --output-format json for scripted runs and parse the JSON, not the terminal output
  5. Don't plan on the retired V1 REST server or .af AgentFile import; both are gone

Questions

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

Letta scores 63.5 (B) on agent readiness against boxes.dev's 53.2 (D), and leads in 5 of 7 scored categories. boxes.dev leads on security & auth and transparency & trust.

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

boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. Letta runs on your own machine, with no hosted endpoint listed.

Are boxes.dev and Letta open source?

No open-source release is listed for boxes.dev. Letta is open source (Apache-2.0).

Other comparisons with boxes.dev or Letta

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.