poplarity/dsh-science-workbench
dsh-science-workbench is a tool for DeepSeek Harness. A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots. 9 bio_* tools + workbench UI + publication-grade figure skills.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-scoped reproducibility plugin for agent-driven science; install if you need traceable, replayable analysis cells.
README documents a clear architecture (host/client dual-face plugin, per-cell subprocess isolation, SHA-256 hashing, git auto-commit) but no test suite, CI config, or lint setup is mentioned, so rigor is only partially evidenced.
No download-and-execute patterns, secrets, or excessive permissions are visible in the README; however, the plugin runs arbitrary agent-authored Python in subprocesses and auto-commits to git, and no sandboxing or permission model is described, so a neutral score is given.
Addresses a genuine and common pain point in agent-driven computational work — provenance, replayability, and figure iteration — with nine concrete tools, a three-panel workbench UI, and bundled publication-figure skills.
Last updated 2026-08-26, not archived, published to npm with a version badge, and the README reflects recent features (searchable project picker, mark-as-final, native directory picker), indicating active development.
README is thorough and bilingual, covering install via dsh plugin, a quick-start flow, a tool table, the reproducibility model, and screenshots; the only gap is that the install command field is unknown and the README excerpt is truncated mid-code-block.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
VALIDATION LADDER
FAQ
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots. 9 bio_* tools + workbench UI + publication-grade f
dsh-science-workbench has 7 stars and 0 forks on GitHub, last updated 2026-08-26.
dsh-science-workbench is distributed under the MIT license.
dsh-science-workbench is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:reproducible-research。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.