24 results
Claude Science-style research workbench for DeepSeek Harness: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), SSH remote-compute engine for long bioinformatics jobs on workstations/HPC (remote_* tools), and 11 science skills for genomics / pathogens / bioinformatics. Ships the tiered cross-provider model router via the companion dsh-model-tier bundle.
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots.
Content-addressed receipts for skills actually loaded by DeepSeek Harness
Content-addressed data and action lineage evidence for DeepSeek Harness
Cancelable auxiliary-model runtime for DeepSeek Harness with a provenance-preserving usage ledger outside official tokenUsage
Ask any line of code its backstory: what it does, and why it's here — grounded in git history and the agent's own session log. Ships a DeepSeek Harness plugin and a standalone MCP server.
Reproducible deterministic benchmark evidence for DSH tools and plugins
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
Reproducible multi-source release evidence for DeepSeek Harness
Read-only insight panel for a DeepSeek Harness profile: where every plugin, service, tool and model came from, which config layer inserted or disabled it, and what is running right now.
Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.
Content-addressed proof that a DeepSeek Harness profile declaration, pnpm lock and installed bundles agree
Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Native, per-workspace long-term memory for DeepSeek Harness: facts and profiles on DSH's own storage-domain, cross-session recall through session-query FTS, approval-gated writes, and cited provenance — no external server, no extra runtime dependency.
Cross-session long-term memory for DeepSeek Harness: dual-scope SQLite memory graph, hybrid retrieval, provenance audit, and a knowledge flywheel.
Content-addressed evidence for DSH configuration winners and shadowed sources
Privacy-minimal provenance receipts for DeepSeek Harness workspace instructions
A Jupyter-shaped, Git-backed research surface for DeepSeek Harness: session lineage, stable script attempts, visual evidence, provenance, safe previews, and explicitly confirmed reruns.
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
Local append-only evidence ledger for DeepSeek Harness
LLM Wiki workbench for dsh-better-sidebar: browse and lint a Karpathy-style interlinked markdown wiki, open pages with the native markdown viewer, clickable [[wikilinks]] and provenance/relative .md links, and backlinks. Ships the llm-wiki agent skill.
DeepAtlas provides local capability assurance for DSH: on-demand discovery, provenance-backed recommendations, pinned risk review, and controlled installation. DSH 本地能力保障：按需发现、证据推荐、固定版本审计与受控安装。
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score