Head to head · Agent harnesses · October 2026 research run

Devin vs T3 Code

Devin scores 57.3 (C) on agent readiness against T3 Code's 51.9 (D), and leads in 4 of 7 scored categories. T3 Code leads on reliability, payments & pricing and maintenance & community. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 harnesses comparisons

Which one, for what

Devin C

Best for A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.

Ahead on

  • Schema & documentation, 80 against 55
  • Security & auth, 72 against 35
  • Transparency & trust, 75 against 51

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

www.devinstatus.com lists two outages on 13 August and the web app down for about two hours on 24 September 2026

T3 Code D

Best for Developers who want one app, including on their phone, to drive several coding agents they already pay for.

Ahead on

  • Reliability, 43 against 35
  • Payments & pricing, 60 against 20
  • Maintenance & community, 75 against 63

Also in its favour

  • No key needed to call it
  • Open source

Watch for

Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom

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 T3 Code +40

Devin 20

Published rubric. No payment protocol (0). Plan prices are public, $20, $200 and $40 a seat with an $80 team minimum, but usage past the quota is billed at an unpublished rate (10). A Free plan exists. The pricing page lists cloud agents from Pro upward, and we couldn't confirm API use on Free or whether a card is needed (10). A person signs up in a browser and provisions the service user in settings (0).

T3 Code 60

Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60.

Security & auth Devin +37

Devin 72

Hosted reading. Service-user keys with roles and named permissions per endpoint, revocable, with rotation endpoints in beta for Enterprise and expiring personal tokens. Custom roles are an Enterprise option, and Teams has Admin and Member only (25). Security profiles restrict network, MCP servers, git and the Devin MCP to read-only, and read-only API permissions exist. They are opt-in, and session creation accepts bypass_approval (16). AI Guardrails screen user messages and pull request comments for prompt injection, on Enterprise only, and they don't cover web pages or repository content Devin reads (8). Audit logs through the API need an enterprise-level permission. Session events and insights are available on all plans (10). SOC 2 Type II and ISO/IEC 27001:2022, a disclosure address at security@cognition.ai, no security.txt, and the trust centre answers No to having a bug bounty (13).

T3 Code 35

Harness reading. Product usage events go by default to ingest.t3.codes and PostHog, with hashed identifiers for your T3 Connect, OpenAI and Claude accounts, and relay traces to Axiom, which can include machine names and error text. Off with T3CODE_TELEMETRY_ENABLED=false or a managed policy. Disclosed in docs/user/telemetry.md, not the README (10 of 30). Permission modes and managed policies (12 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 10 + 12 + 5 + 5 + 3 = 35.

Schema & documentation Devin +25

Devin 80

API reading. Public OpenAPI 3.1 spec for v3 with 182 paths and 274 operations on 4 November 2026, and separate v1 and v2 specs (25). llms.txt with 393 lines and a Markdown twin of every page (10). Each endpoint page names its required permission, but 63 of 274 operations have no description and the MCP tool descriptions are one line each (10). Enums on fields such as devin_mode, origin and category, with most strings unconstrained and nullable (9). curl examples in the quick starts, and 401, 403, 404, 409, 422 and 429 declared on all 274 operations, without a catalogue of error_code values (11). Versioned paths (v1, v2, v3, v3beta1) and an API release notes page dated by month, newest November 2026 (15).

T3 Code 55

Harness reading. User docs in the repository (managed policy, handoffs, providers, telemetry), AGENTS.md for contributors, a server other clients connect to (55).

Transparency & trust Devin +24

Devin 75

Editorial half. Closed source with clear terms from Cognition AI, Inc. (15). Terms (30 June 2026), privacy policy, security page and data processing agreement agree with each other. Customer data may be used for model training by default on self-serve plans, with an opt-out on paid plans that also turns on zero data retention at model providers, and Enterprise data isn't trained on without written consent. Retention is stated as the length of the customer relationship, with no periods (18). The API versioning policy on the release notes page says breaking changes are announced at least 7 days in advance and a deprecated endpoint stays available through a deprecation period. Dated notices followed it for the schedules endpoints (announced 10 September, creation refused from 24 September 2026), and others cover the v2 clone endpoint and Playbooks moving to Skills (23 October). v1 and v2 are marked legacy with no end date (20). Sub-processors listed with purpose and country, and 15 days' notice of additions, per the 8 October check (18).

T3 Code 51

MIT (30). docs/user/telemetry.md lists what is sent and what isn't, but includes hashed third-party account identifiers and the README doesn't mention it (15 of 30). No deprecation policy (5). Disclosed with an opt-out, on by default (12 of 20). 30 + 15 + 5 + 12 = 62.

Maintenance & community T3 Code +12

Devin 63

Closed service. Newest release note dated 2 November 2026 (30). Thirty dated release notes between 7 August and 2 November 2026, and API notes for August, September, October and November (20). Public release notes and a support address, with no public tracker or forum found (10). No official SDK for the Devin API found (a Python SDK in the federal docs covers analytics and ACU limits for air-gapped Desktop), and the Devin MCP server didn't appear in the official MCP registry per the 8 October check (0). No public CI or packages to assess, with the docs and three OpenAPI specs kept current (3).

T3 Code 75

Commits and nightly tags on 6 November 2026 (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 official apps and install script (15). CI on push (10). 30 + 20 + 0 + 15 + 10 = 75.

Reliability T3 Code +8

Devin 35

Hosted reading. Status page at www.devinstatus.com (Atlassian Statuspage) with 14 components, among them Cloud Agent and Cloud Web Client, read from the page itself on 4 November 2026 (20). Its history feed for the 90 days from 6 August 2026 lists Devin unavailable on 13 August (20 minutes), Devin Cloud unavailable on 13 August (2 hours 40 minutes) and the web app down on 24 September (about 2 hours), with minor session and Ask Devin incidents on 10 and 11 August, 3 and 17 September and 26 October. Both 13 August entries report the service unavailable. The 24 September entry names only the web app, not the API or the MCP server, so it is read as partial, as dashboard outages are on other listings. Two majors (5). Two scheduled maintenance entries (7 and 17 August) are read as maintenance. 429 is a documented response, but no rate limit figures were found (0). No Retry-After or backoff guidance found, and v3 session creation has no idempotency key (0). The platform terms give no guarantee of availability, and enterprise terms weren't read (0). The v3 API is the current, recommended surface, with 27 of 274 operations under /v3beta1 (10).

T3 Code 43

Local software. An install script and desktop and mobile apps from the vendor (20). ci.yml and windows-tests.yml 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). Stable tags v0.1.5 to v0.1.7 with many nightlies, no changelog file (8). Version 0.1.7 (0). 20 + 15 + 0 + 8 + 0 = 43.

Score by category

CategoryWeight this runDevinT3 CodeEdge
Reliability16%203543T3 Code +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28055Devin +25
Agent ergonomics13%16.26260Devin +2
Security & auth14%17.57235Devin +37
Payments & pricing10%12.52060T3 Code +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86375T3 Code +12
Transparency & trust7%8.87551Devin +24
Negative events≤1500
TotalC 57.3/100D 51.9/100

Facts side by side

FactDevinT3 Code
KindAgent harnessAgent harness
VendorCognition AI, Inc.T3 Tools Inc.
Hosted endpointhttps://mcp.devin.ai/mcpno (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceProprietary service under Cognition's Platform Terms of ServiceMIT
Tools exposed13none
Read-only variant documentedyesno
llms.txtyesno
Last release2026-11-022026-11-06
Terms last updated2026-06-30no document linked
Privacy policy last updated2026-03-09no document linked
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waiveryesnot read yet

How the scores have moved

Verdicts

Devin

The v3 API is well specified, with a public OpenAPI 3.1 file covering 274 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records two outages on 13 August and a two-hour web app outage on 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.

T3 Code

A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.

Before you call either

Devin

  1. Use a cog_ service-user key with the Member role. Legacy apk_ keys fail against v3 and the MCP server with 401 or 403
  2. Set max_acu_limit on every session you create. Usage is metered by the work done and has no published unit rate
  3. Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again
  4. Enterprise keys and personal access tokens must send X-Org-Id to the MCP server. Organisation-scoped keys resolve it automatically
  5. Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026

T3 Code

  1. Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent
  2. Install and log in to at least one provider CLI first, such as codex login or claude auth login
  3. Use a managed policy to fix settings across a team

Questions

Which is better for AI agents, Devin or T3 Code?

Devin scores 57.3 (C) on agent readiness against T3 Code's 51.9 (D), and leads in 4 of 7 scored categories. T3 Code leads on reliability, payments & pricing and maintenance & community.

Are Devin and T3 Code open source?

No open-source release is listed for Devin. T3 Code is open source (MIT).

Other comparisons with Devin or T3 Code

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.