Back to catalog

GITHUB TOPIC

reproducibility

8projects include this topic

The "reproducibility" topic on GitHub groups 8 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-science-workbench with 7 GitHub stars. dsh-science-workbench — A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

Files & dataPlugin

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.

Structure check pending
agentbioinformaticsdeepseek-harnessdsh-plugin
Development toolsPlugin

dsh-benchmark

dongsheng123132

Deterministic revision-pinned benchmarks and regression evidence for DeepSeek Harness

Structure check pending
ai-agentbenchmarkdeepseek-harnessdsh
Learning & researchPlugin

DeepSeek Harness tools for reproducing the ml-quant-trading protocol v1 benchmark.

Structure check pending
benchmarkdeepseek-harnessdsh-pluginmlquant
InterfacePlugin

DSH plugin: Jupyter-style living notebook — a turn-replayable dataflow DAG with git commit provenance nodes, sub-agent handoff edges, persistent ledger, hover-to-rerun and LLM explanations

Structure check pending
agent-observabilitydagdata-lineagedataflow
Files & dataPlugin

Evidence-first frontier AI radar and reproducibility gate for DeepSeek Harness

Structure check pending
ai-agentsai-researcharxivdeepseek-harness
Agents & sessionsPlugin

Post-run contract verifier and persistent SDK canary for DeepSeek Harness subagents.

Structure check pending
agent-evaluationcanarycontract-testingdeepseek
DSH PluginsPlugin

Open research into better DeepSeek Harness plugins and configurations through reproducible, budget-aware experiments and community contributions.

Structure check pending
agent-harnessbenchmarksdeepseekdeepseek-harness
Development toolsPlugin

dsh-plugin-abtest

Morriaty-The-Murderer

Reproducible paired A/B experiments for DeepSeek Harness plugins, with isolated runners, auditable evidence, and deterministic promotion gates.

Structure check pending
ab-testingagent-evaluationai-agentsbenchmarking