Sign in

Head to head · Agent harnesses · October 2026 research run

Sculptor vs T3 Code

Sculptor scores 53.1 (D) on agent readiness against T3 Code's 51.9 (D), and leads in 2 of 7 scored categories. T3 Code leads on schema & documentation and agent ergonomics. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 harnesses comparisons

SculptorImbue, Inc. · Agent harness D53.1/100#960 of 1486 T3 CodeT3 Tools Inc. · Agent harness D51.9/100#1002 of 1486

Which one, for what

Sculptor D

Best for Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.

Ahead on

  • Security & auth, 57 against 35
  • Transparency & trust, 57 against 51

Watch for

Labelled an experimental research preview that may change drastically

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

  • Schema & documentation, 55 against 45
  • Agent ergonomics, 60 against 50

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.

Security & auth Sculptor +22

Sculptor 57

Harness reading. Product analytics, error reporting and session recording default to off in the user config, and the app asks for a telemetry level and privacy consent at first run; PostHog runs on the front end only for now (25 of 30). Each workspace is an isolated copy of the code (14 of 20). No prompt-injection guidance (5). No audit log (5). SECURITY.md (8). 25 + 14 + 5 + 5 + 8 = 57.

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 T3 Code +10

Sculptor 45

Harness reading. A README, specs and agent docs in the repository; no API reference (45).

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).

Agent ergonomics T3 Code +10

Sculptor 50

Harness reading. Workspaces as isolated copies, review and merge back, and built-in skills (50).

T3 Code 60

Harness reading. Remote control from phone or browser, portable handoffs between providers and managed policies for teams (60).

Transparency & trust Sculptor +6

Sculptor 57

MIT (30). Consent-based telemetry documented in the repository (18 of 30). The README warns of drastic changes during the research preview, with no deprecation policy (5). Opt-in telemetry (20). 30 + 18 + 5 + 20 = 73.

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.

Score by category

CategoryWeight this runSculptorT3 CodeEdge
Reliability16%204343even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24555T3 Code +10
Agent ergonomics13%16.25060T3 Code +10
Security & auth14%17.55735Sculptor +22
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87575even
Transparency & trust7%8.85751Sculptor +6
Negative events≤1500
TotalD 53.1/100D 51.9/100

Facts side by side

FactSculptorT3 Code
KindAgent harnessAgent harness
VendorImbue, Inc.T3 Tools Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-11-06
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked

Verdicts

Sculptor

Imbue's open-source app for parallel coding agents in isolated workspaces, with telemetry off until you choose otherwise. It's an experimental research preview that warns of bugs and drastic changes, Mac and Linux only, with no changelog.

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

Sculptor

  1. Download from the README's links, connect a repository and create a workspace before prompting
  2. Review the diff before merging a workspace back to main

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, Sculptor or T3 Code?

Sculptor scores 53.1 (D) on agent readiness against T3 Code's 51.9 (D), and leads in 2 of 7 scored categories. T3 Code leads on schema & documentation and agent ergonomics.

Are Sculptor and T3 Code open source?

Yes. Sculptor is open source (MIT). T3 Code is open source (MIT).

Other comparisons with Sculptor 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.

Get an auditSee a sample report