# DeepSeek Harness (dsh) vs Sculptor (slim)

> Sculptor scores 53.1 (D) to DeepSeek Harness's 48.5 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor.md (~6,200 tokens) · this version ~2,230 tokens · JSON https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor.json · canonical https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Sculptor scores 53.1 (D) on agent readiness against DeepSeek Harness (dsh)'s 48.5 (D), and leads in 4 of 7 scored categories. DeepSeek Harness (dsh) leads on schema & documentation and agent ergonomics. Both do agent harnesses.

- DeepSeek Harness (dsh): D 48.5, rank #1123 of 1510 · https://www.anchorterminal.com/tools/deepseek-harness.min.md
- Sculptor: D 53.1, rank #966 of 1510 · https://www.anchorterminal.com/tools/sculptor.min.md
- DeepSeek Harness (dsh), good for Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK. Ahead on Schema & documentation, 77 against 45; Agent ergonomics, 68 against 50. Also Free to start without a card.
- Sculptor, good for Developers who want parallel coding agents in isolated workspaces and are fine with a research preview. Ahead on Reliability, 43 against 38; Security & auth, 57 against 40. Also No key needed to call it; No incidents deducted, where DeepSeek Harness (dsh) loses 8 points for them.

| Category | DeepSeek Harness (dsh) | Sculptor |
| --- | --- | --- |
| Reliability (16%) | 38 | 43 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 77 | 45 |
| Agent ergonomics (13%) | 68 | 50 |
| Security & auth (14%) | 40 | 57 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 71 | 75 |
| Transparency & trust (7%) | 53 | 57 |

| Fact (where they differ) | DeepSeek Harness (dsh) | Sculptor |
| --- | --- | --- |
| Vendor | DeepSeek | Imbue, Inc. |
| Auth | API key | None |
| llms.txt | yes | no |
| Last release | 2026-10-17 | 2026-11-06 |
| Popularity | 245k npm/wk | none |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Schema & documentation, DeepSeek Harness (dsh) +32: DeepSeek Harness (dsh) 77 (Framework reading. `--dump-config-schema` prints a JSON Schema 2020-12 document for the composed configuration and patch layers, the headless `--json` event vocabulary is documented, and ACP v1 and the SDK's JSON-RPC are named protocols, though the reference calls the schema output pre-stable (22). llms.txt on the docs site, with a raw Markdown address for every page (10). Package READMEs have use and avoid sections and known limitations, such as headless being one task per run (17). Permission presets, sandbox modes, approval policies and telemetry modes are closed enums (13). Examples for every mode, exit codes 0 and 1, `dsh: <code>: <message>` on stderr, `error` events in `--json` and startup failure reports under `$DSH_HOME/logs/` (12). Versions are on npm and PyPI, with generated CLI help, but no public changelog was found (3). Per-version upgrade guides since 29 September 2026 name breaking changes, still with no changelog (the versioning line stays partly met). 22 + 10 + 17 + 13 + 12 + 3 = 77.); Sculptor 45 (Harness reading. A README, specs and agent docs in the repository; no API reference (45).)
- Agent ergonomics, DeepSeek Harness (dsh) +18: DeepSeek Harness (dsh) 68 (Harness reading, scored on what a pipeline driving it has to supply. Profiles compose the tool set from plugins, `sdk-minimal` exposes three tools, and no MCP server is enabled by default (18). Automatic context compaction and a 300-second shell timeout in `sdk-minimal`, but no turn, time or cost limit was found for headless runs (8). Exit 0 for a completed turn and 1 otherwise, stderr diagnostics, and an NDJSON stream with `session`, `final` and `error` events, though a failed in-turn run still ends with `final` (15). `--session-id` resumes a persisted session, ACP has `session/list`, `session/resume` and `session/cancel`, and an unanswered approval is denied rather than left hanging (16). One-argument headless runs, ACP and a Python SDK, and the repository also holds a TypeScript SDK client (`@deepseek-ai/dsh-sdk-client`) that the Python guide mentions once. Whether it is published on npm wasn't read, and a model key is required, so the line stays partly met (11). 18 + 8 + 15 + 16 + 11 = 68.); Sculptor 50 (Harness reading. Workspaces as isolated copies, review and merge back, and built-in skills (50).)
- Security & auth, Sculptor +17: DeepSeek Harness (dsh) 40 (Harness reading of the framework checklist, 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. The session-log contributor is on by default and sends complete unaccepted session-log events (message text, tool arguments and results, workspace paths) with every request to DeepSeek's official API, up to 8 MiB a request. Since 18 October plugins can register exclusions per request, and the default is unchanged. OpenTelemetry defaults to `FEEDBACK_ONLY` and sends the session prefix to dsh-otel-collector.deepseeksvc.com after any feedback or rating. Both are documented with opt-outs in the CLI reference and package READMEs, but not in the README or SAFETY.md. Keys stay local (8). `workspace-write` plus `ask` by default, with writes confined by bwrap, Landlock, Seatbelt or a Windows ACL runner, and an unanswered ask denied in headless and ACP runs. Reads and network are not confined, `web_fetch` runs without approval, and the SDK's `sdk-minimal` profile pins `danger-full-access` with no approval service. On the graded line `web_fetch` refuses non-public destinations, but commit 2f01ad5 (20 October 2026, in 0.2.2-alpha.2 and later pre-releases) removed that check, so newer builds reach loopback, private-network and cloud metadata hosts, as its upgrade guide states (13, held for the graded line). SAFETY.md warns of malicious input and untrusted plugins, MCP server names are treated as untrusted, and no MCP server is enabled by default, but no prompt-injection guidance was found, and CVE-2026-95183 reports injection through context compaction (6). Local JSONL session logs record approval decisions as audit events (12). No SECURITY.md or security policy file in a clone of 4 November, no security.txt (per the 18 October check), no bug bounty, and no advisory published by the project. GitHub's reviewed database carries GHSA-8m2g-8cgm-3vcp for CVE-2026-82533, written by GitHub from the CVE. SAFETY.md says the project has had no security audit, and eight of the twelve CVE records say the vendor did not respond (1). 8 + 13 + 6 + 12 + 1 = 40.); 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.)
- Reliability, Sculptor +5: DeepSeek Harness (dsh) 38 (Local-package reading, graded on npm `latest`, which the README's `npx @deepseek-ai/dsh` installs (0.2.0-rc.2 per the 18 October check; npm not re-read on 4 November). Official npm package with Node 22.19+ and 24+ stated, and a Python wheel for Python 3.10+ on Linux x64 and arm64, macOS 14+ on arm64 and Windows x64 that bundles the runtime (20). Public CI. ci.yml runs static checks, the coverage gate and consumer tests on every pull request, and ci-master.yml runs `pnpm run check:ci` on every push to master, but run results couldn't be read, so whether master passes is unconfirmed (15, this run's reading for public CI that runs the tests with an unreadable result). CONTRIBUTING.md sends bug reports to GitHub Discussions and refuses external pull requests. Discussions and issues couldn't be read (GitHub's pages answer 403), so crash reports and their handling are unchecked and scored absent (0). Alpha, next and latest dist-tags separate channels. Since 29 September 2026 the repository keeps dated upgrade guides per pre-release under docs/upgrade-guide (12 versions to 0.2.2-alpha.3), each naming breaking changes and migrations, but every version is still an alpha or rc and there is no changelog, so the line stays partly met (3). Developer preview, no 1.0 or stable release (0). 20 + 15 + 0 + 3 + 0 = 38.); 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.)