Head to head · Agent harnesses · October 2026 research run
Jules vs Sculptor
Sculptor scores 53.1 (D) on agent readiness against Jules's 45.1 (E), and leads in 4 of 7 scored categories. Jules leads on schema & documentation and agent ergonomics. Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
Jules E
Best for Nobody starting new work, since Jules turns read-only after 11 November 2026 and ends on 31 December 2026.
Ahead on
- Schema & documentation, 76 against 45
- Agent ergonomics, 64 against 50
Also in its favour
- Runs on your own machine
Watch for
Jules turns read-only after 11 November 2026 and winds down on 31 December 2026, per the changelog of 29 October
Sculptor D
Best for Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.
Ahead on
- Reliability, 43 against 13
- Payments & pricing, 60 against 30
- Maintenance & community, 75 against 18
- Transparency & trust, 57 against 51
Also in its favour
- No key needed to call it
- Open source
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.
Maintenance & community Sculptor +57
Jules 18
Closed service. The newest API or product change is the changelog entry of 9 March 2026, 241 days before 5 November (0). The changelog's 29 October 2026 entry announces the wind-down and an export route through the CLI, which is a notice, not an API change. No package releases, commits or tags in the 90 days, and the jules-sdk repository's last commit is 18 March 2026 (0). A public changelog and a Discord channel. The 18 October issue and pull request counts came from shields.io badges and are struck (8 of 15, a partial held). The official TypeScript SDK and MCP packages last published 0.2.0 on 9 March 2026, per the 18 October registry reading, and no official MCP registry entry could be read (5). The SDK has a CI workflow on pull requests whose results couldn't be read, and two runtime dependencies. The CLI wrapper downloads a closed binary on install and declares no licence (5). 0 + 0 + 8 + 5 + 5 = 18.
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.
Schema & documentation Jules +31
Jules 76
API reading. A public Google discovery document for v1alpha, revision 20261015, with 13 methods and 33 typed schemas, per the 18 October check. It sits on the API's own host and wasn't requested again (25). docs/llms.txt and a Markdown twin of every docs page (10). Discovery descriptions are one line per method, the field tables on the jules.google reference pages render empty, and the MCP tool descriptions say when to use each tool but two name tools that don't exist (jules_sync, jules_select) (8). Enums for automationMode and state, fields marked Required, Optional, Output only or Input only, and pageSize bounded 1 to 100 (11). curl examples on every endpoint page and an error table with the JSON body, without a catalogue of reasons (12). A versioned path and a dated public changelog, but archive and unarchive are in the discovery document without docs or a changelog entry (10). 25 + 10 + 8 + 11 + 12 + 10 = 76.
Sculptor 45
Harness reading. A README, specs and agent docs in the repository; no API reference (45).
Reliability Sculptor +30
Jules 13
Hosted reading. No status page for Jules was found (0). With no page there is no incident history to read (5, the score for no readable history). The plans page, re-read on 5 November, publishes task quotas with numbers, 15, 100 and 300 tasks a rolling 24 hours and 3, 15 and 60 concurrent, and list pageSize is capped at 100, but no request rate figures were found (8 of 15). 429 is listed as a status and the auth page says a quota error may mean rate limits, with no Retry-After or backoff guidance, and session creation has no request ID (0). No SLA found (0). The API is v1alpha and labelled experimental, and the changelog of 29 October 2026 says Jules turns read-only after 11 November (0). 0 + 5 + 8 + 0 + 0 + 0 = 13.
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.
Payments & pricing Sculptor +30
Jules 30
Published rubric. No payment protocol (0). Plans and their Jules limits are public without a login, and Jules sits inside the Google AI plans. The prices render per locale and weren't read, and there's no per-task price (10). A free plan of 15 tasks a day with a Google account, and no card step in the sign-up docs, until new tasks stop after 11 November 2026 (20). A person signs in, accepts the privacy notice, installs the GitHub app and creates the key in the web app (0). 0 + 10 + 20 + 0 = 30.
Sculptor 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.
Agent ergonomics Jules +14
Jules 64
API and MCP reading, per the 18 October check. Responses can be sized with pageSize, the standard fields parameter and a create_time filter that fetches only new activities. The MCP server has 8 tools, and query_cache takes a token budget (20). Token pagination on every list and filters on sessions, activities and sources (16). Google's error JSON with status and an ErrorInfo reason, plus a documented status table (14). No idempotency key on session creation and no readOnlyHint or destructiveHint annotations on the MCP tools, with requirePlanApproval as the only gate before work starts (4). Only prompt is required and a session without a source runs repoless. One official SDK, in TypeScript, plus the MCP server and CLI (10). 20 + 16 + 14 + 4 + 10 = 64.
Sculptor 50
Harness reading. Workspaces as isolated copies, review and merge back, and built-in skills (50).
Transparency & trust Sculptor +6
Jules 51
Editorial half. Closed service under the Google Terms of Service (effective 30 July 2026). The SDK is Apache-2.0, but npm lists @google/jules-mcp as ISC while its README says Apache-2.0, and @google/jules declares no licence (12). The FAQ says private repositories aren't used for training. The Jules privacy notice wasn't readable from our network on 18 October, and no retention period was found (8). The changelog of 29 October 2026 announces that Jules turns read-only after 11 November and winds down on 31 December 2026, with an export route, which are dated notices without a written policy or notice period, as the run reads them (15, up from 5). No subprocessor or data location statement found (0). 12 + 8 + 15 + 0 = 35.
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
| Category | Weight this run | Jules | Sculptor | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 13 | 43 | Sculptor +30 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 76 | 45 | Jules +31 |
| Agent ergonomics | 13%16.2 | 64 | 50 | Jules +14 |
| Security & auth | 14%17.5 | 57 | 57 | even |
| Payments & pricing | 10%12.5 | 30 | 60 | Sculptor +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 18 | 75 | Sculptor +57 |
| Transparency & trust | 7%8.8 | 51 | 57 | Sculptor +6 |
| Negative events | ≤15 | 0 | 0 | |
| Total | E 45.1/100 | D 53.1/100 |
Facts side by side
| Fact | Jules | Sculptor |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Google LLC | Imbue, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed | MIT |
| Tools exposed | 8 | none |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-03-09 | 2026-11-06 |
| Terms last updated | 2026-07-30 | no document linked |
| Privacy policy last updated | 2026-10-01 | no document linked |
| Customer content may train models | yes | not read yet |
| Terms restrict automated access | yes | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | 2.8/5 (4) | none |
How the scores have moved
Sculptor
No score change since it was listed.
Verdicts
Jules
Google is winding Jules down. Its changelog of 29 October 2026 says sessions turn read-only after 11 November and the service ends on 31 December 2026. Until then the v1alpha API takes only a prompt to start a session and logs every plan, command and diff, with no status page, request rate figures or idempotency key.
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
Jules
- Don't start new work on Jules. Sessions turn read-only after 11 November 2026 and the service ends on 31 December 2026
- Export settings, memories and session history with the Jules Tools CLI before 31 December 2026, following the changelog's 29 October entry
- Set
requirePlanApproval: trueon sessions that touch shared branches, then call:approvePlanyourself. API sessions otherwise run their plan without review - Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another
- Poll activities with a
create_timefilter and cache them. Activities never change once written
Sculptor
- Download from the README's links, connect a repository and create a workspace before prompting
- Review the diff before merging a workspace back to main
Questions
Which is better for AI agents, Jules or Sculptor?
Sculptor scores 53.1 (D) on agent readiness against Jules's 45.1 (E), and leads in 4 of 7 scored categories. Jules leads on schema & documentation and agent ergonomics.
Are Jules and Sculptor open source?
No open-source release is listed for Jules. Sculptor is open source (MIT).
Other comparisons with Jules or Sculptor
- Agent Zero vs Jules
- Agent Zero vs Sculptor
- Aider vs Jules
- Aider vs Sculptor
- Amp vs Jules
- Amp vs Sculptor
- Antigravity CLI vs Jules
- Antigravity CLI vs Sculptor
- Auggie CLI vs Jules
- Auggie CLI vs Sculptor
- AXLR vs Jules
- AXLR vs Sculptor
- Claude Code vs Jules
- Claude Code vs Sculptor
- Cline vs Jules
- Cline vs Sculptor
- Conductor vs Jules
- Conductor vs Sculptor
- Crush vs Jules
- Crush vs Sculptor
- Cursor CLI vs Jules
- Cursor CLI vs Sculptor
- DeepSeek Harness (dsh) vs Jules
- DeepSeek Harness (dsh) vs Sculptor
- dsh-superagent (DeepSeek) vs Jules
- dsh-superagent (DeepSeek) vs Sculptor
- Devin vs Jules
- Devin vs Sculptor
- Droid CLI vs Jules
- Droid CLI vs Sculptor
- Pi vs Jules
- Pi vs Sculptor
- Emdash vs Jules
- Emdash vs Sculptor
- Gemini CLI vs Jules
- Gemini CLI vs Sculptor
- GitHub Copilot CLI vs Jules
- GitHub Copilot CLI vs Sculptor
- goose vs Jules
- goose vs Sculptor
- Harness² vs Jules
- Harness² vs Sculptor
- HarnessRouter vs Jules
- HarnessRouter vs Sculptor
- Jules vs Junie CLI
- Jules vs Kilo Code CLI
- Jules vs Kimi Code CLI
- Jules vs Kiro CLI
- Jules vs Letta
- Jules vs mini-swe-agent
- Jules vs MiniMax Code
- Jules vs Mistral Vibe CLI
- Jules vs Muse Code
- Jules vs OpenAI Agents API
- Jules vs OpenAI Codex
- Jules vs OpenCode
- Jules vs OpenHands
- Jules vs OpenMausBot
- Jules vs Orca
- Jules vs Paseo
- Jules vs Prime Agent
- Jules vs Qoder CLI
- Jules vs Qwen Code
- Jules vs Mirror CLI
- Jules vs Rovo Dev CLI
- Jules vs T3 Code
- Jules vs Traycer
- Jules vs Unstoppable
- Jules vs Verdent
- Jules vs Vibe-Trading
- Jules vs Warp (Warp Agent CLI and the Oz Agent API)
- Junie CLI vs Sculptor
- Kilo Code CLI vs Sculptor
- Kimi Code CLI vs Sculptor
- Kiro CLI vs Sculptor
- Letta vs Sculptor
- mini-swe-agent vs Sculptor
- MiniMax Code vs Sculptor
- Mistral Vibe CLI vs Sculptor
- Muse Code vs Sculptor
- OpenAI Agents API vs Sculptor
- OpenAI Codex vs Sculptor
- OpenCode vs Sculptor
- OpenHands vs Sculptor
- Orca vs Sculptor
- Paseo vs Sculptor
- Prime Agent vs Sculptor
- Qoder CLI vs Sculptor
- Qwen Code vs Sculptor
- Mirror CLI vs Sculptor
- Rovo Dev CLI vs Sculptor
- Sculptor vs T3 Code
- Sculptor vs Traycer
- Sculptor vs Unstoppable
- Sculptor vs Verdent
- Sculptor vs Vibe-Trading
- Sculptor vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Jules
- Clawboo vs Sculptor
- CLI Manager vs Jules
- CLI Manager vs Sculptor
- Harness vs Jules
- Harness vs Sculptor
- Jules vs Paperclip
- Jules vs Parallax
- OpenMausBot vs Sculptor
- Paperclip vs Sculptor
- Parallax vs Sculptor
Machine-readable
- This page as Markdown
/compare/jules-vs-sculptor.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/jules.json·/api/v1/tools/sculptor.json - From a terminal
anchor compare jules sculptor(the CLI) - Over MCP
compare_tools {"a": "jules", "b": "sculptor"}at/mcp, no key