@chenjie1129/dsh-reliability-governor-plugin
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
510 results
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
Agent JIT: a compiler/runtime that offloads deterministic execution paths from LLM agent loops.
DeepSeek Harness plugin that bridges to external AI models (Codex, Claude, GPT, ...) for second-opinion code review, adversarial review, and task delegation.
User Message Minimap: a navigation rail for long DeepSeek Harness conversations
Tick-rail conversation navigator for the DeepSeek Harness web UI — a slim rail with one tick per message you sent, a peak-falloff hover effect, message previews, and click-to-jump.
AI 多角色协作开发框架:文件即通信 + 教训库 + 决策日志 + 一致性审计 + 复盘持续优化(REVIEW)。注册 ai_collab_init 工具。
Native DeepSeek Harness LLM adapter for Claude Code / Antigravity CLI subscriptions, plus local Ollama — Claude, Gemini and a free local model in the model picker, no API key
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
Workflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.
DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.
DeepSeek Harness plugin: Windows desktop notifications + sound when an agent turn finishes or the harness is waiting for you.
DeepSeek Harness 极简余额监视器:常驻余额徽章、每分钟自动刷新、高峰/空闲时段倒计时、余额分级配色。A minimal balance monitor for DeepSeek Harness.
Hand finished derivations and code to an independent reviewer subagent and feed the verdict back to the main model. 把设计推导与代码成品交给独立审查子代理,并把结论回注给主模型。
What can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
DSH Web GUI prompt-based conversation minimap: a vertical navigation rail on the left of long conversations, each anchor = one user prompt; hover shows the prompt preview, click jumps to that message.
科学技能包:100+ 科学数据库查询(PubChem/UniProt/ClinicalTrials/FRED…)、文献综述与证据有界假设生成、实验方案设计、同行评审回复、基金写作、方法验证(ICH/USP/CLSI)、论文级图表。受 K-Dense-AI/scientific-agent-skills(33.9k★ MIT)启发。
AI 系统的数据层:把 18 种来源(文档站/GitHub/PDF/视频/Notebook/Wiki…)转成结构化知识资产,导出到 22 种目标(Claude/Gemini/OpenAI/RAG 管道/编码助手);AI 驱动项目扫描生成配置。受 yusufkaraaslan/Skill_Seekers(14k★ MIT)启发。
DSH web plugin: show the DeepSeek API key's remaining balance, estimate usable tokens per model (peak/off-peak pricing + measured cache-hit ratio), and chart the real cost of every turn.
Multi-provider image generation and editing tools for DeepSeek Harness
让文本模型(如 DeepSeek)在 DSH 里直接收发图片:图片落盘工作区、模型可见面自动替换为 mmx(MiniMax VLM)识别结果,用户侧照常显示缩略图。
Deterministic before/after ordering for Cordis waterfall hooks, contributed across independent plugins
Skill station for DeepSeek Harness: a sidebar hub that scans Claude/Codex/Cursor/Gemini skill libraries, imports skills with one click, manages global and project skills, and installs skill folders by drag-and-drop. · DSH 技能站:侧边栏技能中枢,扫描各家 agent 技能库一键导入,管理全局与项目技能,拖拽文件夹即装。
Dify agent and knowledge-base capability for the DeepSeek Harness — the ctx.dify Service Definition, an HTTP Service Provider, and the model-facing dify_chat and dify_retrieve tools