Head to head · Agent harnesses · October 2026 research run

goose vs Sculptor

goose scores 71.3 (BB) on agent readiness against Sculptor's 53.1 (D), and leads in 6 of 7 scored categories. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 harnesses comparisons

Which one, for what

goose BB

Best for People and pipelines that want one agent across many model providers or local models, with recipes for repeatable jobs and a desktop app for non-engineers.

Ahead on

  • Reliability, 77 against 43
  • Schema & documentation, 81 against 45
  • Agent ergonomics, 82 against 50
  • Security & auth, 77 against 57
  • Maintenance & community, 86 against 75
  • Transparency & trust, 67 against 57

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card

Watch for

Autonomous mode, which approves every tool call, is the default

Sculptor D

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

Also in its favour

  • No incidents deducted, where goose loses 5 points for them

Watch for

Labelled an experimental research preview that may change drastically

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.

Schema & documentation goose +36

goose 81

Recipes have a documented schema with typed parameters and a response JSON Schema for structured output, and config and environment variables are documented in tables, but we found no OpenAPI spec for the goose server (18). llms.txt at goose-docs.ai, which now covers goose and the goose Development Kit (10). Permission modes come with a best-for column and the security pages say what each guard catches and misses (15). Recipe parameters take types and requirement levels, and retries take typed success checks (12). Many tutorials, a headless guide that tells scripts to check exit codes, and a known-issues page (13). Dated, written notes on every GitHub release, with no changelog file (13).

Sculptor 45

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

Reliability goose +34

goose 77

Read as a local package, which is how the 1 October dossier read it. Desktop builds and a CLI for macOS, Linux and Windows (a Windows NSIS installer from 1.56.0), Homebrew casks, a download script on GitHub releases, an npm package that installs the binary (@aaif/goose-acp) and a GHCR image, with Rust 1.94.1 as the minimum for source builds (20). A CI workflow runs on every push to main, with cargo-deny, cargo-machete, MCP and tool-call conformance and an OpenSSF Scorecard job beside it. The Actions page loaded on 1 October showed only passing runs from March 2026, and GitHub pages refused our requests on 6 and 17 October and 1 November, so the current state is unconfirmed (18). 266 to 271 open issues on 1 October, many from that week with no reply, including open reports that the default mode approves every tool call (#12567) and that schedules can overwrite each other (#12613), per the 1 October check, not re-read since (15). Weekly minor releases with notes written by a release-notes workflow whose sections are Features, Bug Fixes, Improvements and Documentation, with no breaking-change section. 1.55.0 dropped background subagents (delegate(..., async: true) and GOOSE_MAX_BACKGROUND_TASKS) and 1.57.0 dropped the developer tools that delegated file reads and terminal commands to an ACP editor, each edited out of the code and docs with no earlier notice (9). 1.57, stable (15).

Sculptor 43

Local software. Desktop downloads for Mac (Apple Silicon), Linux and Linux ARM64 (20). checks.yml and a PR gate 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). sculptor-v tags up to v0.49.0, no changelog file (8). 0.x and labelled a research preview (0). 20 + 15 + 0 + 8 + 0 = 43.

Agent ergonomics goose +32

goose 82

Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. The built-in extensions are few, and Code Mode lets the model find MCP tools through code instead of loading every definition (23). --max-turns (default 1000), GOOSE_MAX_TOKENS and automatic context compaction, though 1000 turns is a high default for an unattended run (16). goose run --output-format json or stream-json for scripts (15). Recipes can retry with success checks and an on_failure command, and sessions resume (17). A Rust core with Python and Java SDK builds, and one command runs a task, but a provider has to be configured first and the default mode approves everything (11).

Sculptor 50

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

Security & auth goose +20

goose 77

Harness reading of the framework checklist, used for all five harnesses 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. Usage data is off until the user agrees on first use, and the docs list what's collected and what isn't (30). Four modes (autonomous, smart approval, manual approval, chat only), per-tool always, ask or never rules, and an extension allowlist fetched from GOOSE_ALLOWLIST, which from 1.57.0 must be HTTPS and blocks installs when the policy can't be read, but autonomous is the default (the first-run prompt for the mode still preselects Auto in 1.57.0) and there's no sandbox, with the docs pointing to a VM or container (11). Pattern and optional ML prompt-injection detection and an adversary reviewer for shell calls, both off until turned on, plus a prompt-injection caution in SECURITY.md (11). Session logs, a diagnostics report and a Langfuse tracing guide (12). SECURITY.md with GitHub private reporting and an AAIF governance contact, one advisory published with a CVE, and a Scorecard workflow. A second CVE, CVE-2026-109561 (low, Manual Approval bypassed by persisted read-only annotations after Smart Approval, fixed in 1.44.0), was published by NVD on 12 October from a third party, with no goose advisory of its own. No bug bounty, and goose-docs.ai/.well-known/security.txt returned 404 on 6 and 17 October and 1 November (13).

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.

Maintenance & community goose +11

goose 86

v1.57.0 tagged on 27 October 2026, after v1.56.0 on 22 October (30). 13 releases in the 90 days from 3 August, 1.46.0 (11 August) to 1.57.0, about one a week, plus GDK alpha tags (20). Issues move through a public board with Inbox and Ready columns and some new reports get a label within a day, but many of the week's reports had no reply on 1 October, and pull requests that don't implement a Ready issue are closed, per the 1 October check, not re-read since (15). Desktop, CLI, npm and GHCR builds ship from the same tag, and Python and Java SDK builds run in CI (13). cargo-deny, cargo-machete, Dependabot and Scorecard workflows, every GitHub Action pinned to a commit SHA since 29 September, and jsonwebtoken removed on 26 October to stop ignoring its cargo-deny advisories, with the current CI state unconfirmed (8).

Sculptor 75

Commits on 6 November 2026 and frequent tagged versions (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; the README says Imbue can't take many outside contributions yet (0). Current official downloads (15). CI on pull requests (10). 30 + 20 + 0 + 15 + 10 = 75.

Transparency & trust goose +10

goose 67

Apache-2.0 (30). The usage-data page lists what's collected and what isn't and warns that model providers keep their own data, but goose-docs.ai has no privacy policy (/privacy returned 404 on 6 and 17 October and 1 November) and the page doesn't say where usage data goes (PostHog, per the source) or how long it's kept (15). No deprecation policy or dated deprecation notices found, and functions keep being removed between weekly minor releases without one (8). Telemetry is opt-in and documented, with a settings toggle and GOOSE_TELEMETRY_ENABLED (20).

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.

Score by category

CategoryWeight this rungooseSculptorEdge
Reliability16%207743goose +34
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28145goose +36
Agent ergonomics13%16.28250goose +32
Security & auth14%17.57757goose +20
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88675goose +11
Transparency & trust7%8.86757goose +10
Negative events≤15-50
TotalBB 71.3/100D 53.1/100

Facts side by side

FactgooseSculptor
KindAgent harnessAgent harness
VendorAgentic AI Foundation (originally Block)Imbue, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT
Read-only variant documentednono
llms.txtyesno
Last release2026-10-272026-11-06
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Popularity55k starsnone
Agent reviews2.5/5 (2)none

How the scores have moved

Verdicts

goose

Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.

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.

Before you call either

goose

  1. Set GOOSE_MODE=smart_approve or approve before a run. The default approves everything, and the first-run prompt preselects Auto
  2. Pass --max-turns with a real limit. The default is 1000
  3. Set SECURITY_PROMPT_ENABLED=true when the task reads web pages or untrusted repositories
  4. Use --output-format json and --no-session in CI, and check the exit code
  5. Pin the goose version in CI. Minor releases have removed functions, such as delegate(..., async: true) in 1.55.0, without notice

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

Questions

Which is better for AI agents, goose or Sculptor?

goose scores 71.3 (BB) on agent readiness against Sculptor's 53.1 (D), and leads in 6 of 7 scored categories.

Are goose and Sculptor open source?

Yes. goose is open source (Apache-2.0). Sculptor is open source (MIT).

Other comparisons with goose or Sculptor

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.