dsh-policy-drift-proof
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
163 results
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.
Drive9 workspace and durable evidence components for DeepSeek Harness
Evidence that CLI, MCP and GUI bindings reach the same DeepSeek Harness action core
Content-addressed timeline, canon and character-knowledge evidence for DeepSeek Harness
Evidence-grounded bilingual research tools and workflows for DeepSeek Harness.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Content-addressed audit indexes across independent DeepSeek Harness evidence producers
Reproducible multi-source release evidence for DeepSeek Harness
Evidence-first token cost ledger and budget checks for DeepSeek Harness
A reusable DeepSeek Harness bundle for evidence-driven memory, orchestration, benchmark operations, repository audits, and plugin release workflows.
Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
OMV Audit Desk: an evidence-first vulnerability audit workbench for DeepSeek Harness
General APEX preset with a Minimal Pro anchor, role-bounded PTC implementation, verified handoffs, and evidence convergence
Local-first task outcome ledger & acceptance plugin for DeepSeek Harness (DSH): evidence-backed verification of task completion, zero extra model cost, user-owned sidecar data. 任务结果账本与验收插件:机械证据验收、默认零额外 token、数据本地持有。
记忆搬家:把 Claude / ChatGPT / Claude Code 的历史记忆搬进 DeepSeek Harness —— 带逐字证据,逐条批准 | Move your Claude & ChatGPT memory into DeepSeek Harness (DSH), with verbatim evidence and one-by-one approval
DSH plugin for DeepSeek Harness: 25 model tools across PubMed, Europe PMC, OpenAlex, PubTator3 & Semantic Scholar — cross-source unified search, article metadata, full text, citations, MeSH & ID tools, citation counts & recommendations — plus a personal literature knowledge graph with an AI-powered PubTator3 concept layer (normalized entities, curated relations, evidence-backed edges). Core PubMed capabilities originate from @cyanheads/pubmed-mcp-server; the knowledge-graph, concept and unified-search layers are original extensions.
Socratic clarify-first deep research plugin for DeepSeek Harness: adaptive multi-round research with evidence-closed cited reports, cross-verification, and citation auditing.
Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.
Evidence-first long-term project memory for DeepSeek Harness
DeepSeek Harness plugin for evidence-backed repository analysis and reviewable, bounded change proposals.
DSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.