136 results
AI-driven partial wave analysis for DeepSeek Harness: physics-gated config editing, ctpwa fit execution, numeric evaluation, and goal-driven iterative convergence. Physics knowledge (PDG-2026) as pure functions; DSH integration as a thin pwa_* tool plugin.
Host-side Cordis control plugin for aeval: one-shot config injector (experiment variables, gateway-lease budgets, fork lineage, bundle descriptor), with a standalone status mode, a Web status chip, and a self-check command.
dsh 插件开发知识库：DeepSeek Harness 官方文档站完整 Markdown 镜像（中英双语 188 页）+ 182 篇仓库补充开发参考 + 主题导航与 373 文件全量搜索索引；以 dsh-plugin-dev-kb 技能让 agent 在插件开发任务中自动加载定位文档。纯数据插件，零运行时依赖。
Persistent 5-layer memory system for DeepSeek Harness (entry injection, relevance retrieval, agent tools, and LLM-backed auto-extraction).
AiFP Cognitive Memory — persistent memory MCP server for AI assistants. Chinese-first retrieval with causal chains, Hebbian associations and graph diffusion. 记忆感知系统
Neon Genesis Evangelion themed surfaces for the DeepSeek Harness Web GUI — three unit schemes (Unit-01/00/02), full-element palettes, mecha art in the sidebar, in-GUI switcher. Installable via `dsh plugin --profile web add <this-dir>`.
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
Local-first experiment and evaluation workbench for DeepSeek Harness.
Persistent memory for DeepSeek Harness: per-conversation notes, selective injection, project memory, semantic Vault search (bge-m3, free optional key) and automatic retrieval — agents stop forgetting.
DeepSeek Harness plugin — manage an LLM-Wiki knowledge base from the agent: wiki_search / wiki_read / wiki_stats / wiki_validate / wiki_fix / wiki_errorbook / wiki_ingest
RAGFlow knowledge-base retrieval capability for the DeepSeek Harness — the ctx.ragflow Service Definition, an HTTP Service Provider, and the model-facing ragflow_retrieve tool
Fifth DeepSeek Harness mode with configurable Codex, Claude Code, or DSH audits, user-approved remediation turns, progressive Cordis/skill elevation, safety pauses, and Web/TUI review controls.
Skill-trigger evaluation: an LLM judge recreates the DSH skill catalog and measures how reliably a skill description routes matching queries.
DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.
Reproducible local experiment matrices for DSH profiles
Local knowledge bases with explicit, source-backed retrieval for DeepSeek Harness Web.
Skill Radar for DeepSeek Harness (dsh): scan the current session's visible skills, score their relevance against the recent conversation, and recommend which skill to load. Model tool + optional interactive panel.
KnowLP-RAG: dual knowledge-graph retrieval for Markdown notes — DeepSeek Harness (dsh) bundle: MCP server + native Cordis plugin
Code reference & reuse-survey plugin for DeepSeek Harness (DSH): search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse. 开发前检索本地与开源可复用代码并询问用户的复用调查插件。
A workbench-quality docking system for DeepSeek Harness Web plugins
A responsive, tabbed Ghostty terminal for the DeepSeek Harness Web UI
DSH agent preset for rigorous strategy live-deployment testing/evaluation. Retest.
Semantic long-term memory for DeepSeek Harness: embedding-based retrieval over a persistent cross-session memory store, with model-facing tools, proactive per-question recall, automatic conversation summarization, and auto-selected embedding provider (apiKey present → API, otherwise local).