48 results
Agent-loop change review for the DeepSeek Harness web GUI: after every agent loop it snapshots the workspace, detects file/code changes, and offers one-click revert plus a right-sidebar diff review panel. 官方双面 dsh 插件（host + client），零依赖。
K12 capability substrate for DeepSeek Harness: 143 objectively-decidable capability anchors and 6,091 list items extracted from China's MOE 2022 curriculum standards, with local-only learner profiles
Voice practice mode for the DSH web app: bilingual (中文 / English) conversation output plus read-aloud (TTS) and speech input (STT). Adds a 语音交流 dialog-mode toggle to the composer.
DSH 自进化长期记忆插件:回合后 LLM 自动提取记忆、每步召回注入、语义重排检索、冲突合并、learned-* 技能沉淀,附记忆库管理面板。记忆文件默认存于 harness 根目录($DSH_HOME,未设时 ~/.dsh)下的 imemory/ 子目录,可用 config.memDir 覆盖。
Turn DeepSeek Harness conversations into user-curated quiz questions.
ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.
Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.
Interactive Learning mode and native learning activities for DeepSeek Harness
中文 DSH 本地知识复习插件：零配置资料库、证据优先问答、Markdown 摘要与二次分类。
DeepSeek Harness bundle that registers the learn skill pack on ctx.skills.
A DeepSeek Harness (dsh) plugin that greets the user at the start of every session with varied wording, learns their name on first use, and greets them personally afterward.
Native adaptive intelligence layer for DeepSeek Harness: memory, skills, /learn, background review, and curator — no Hermes or Python dependency.
一个助力包括我在内的萌新进行项目式学习的dsh preset
ML 管线工作流：数据→训练→评估→部署→监控的 MLOps 工程。受 wshobson/agents（38k★ MIT）启发。
A small DeepSeek Harness tool plugin for learning the Cordis extension model
DeepSeek Harness plugin for progressive, source-grounded deep research, writing, and learning: steerable checkpoints and citations verified against retrieved sources
把技能当可训练参数：像训练神经网络一样训练 agent 技能（epochs/batchsize/learning rate/验证门禁，但不碰模型权重）——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt（MIT）启发。
Practice bundle for learning DeepSeek Harness plugin development
RALPH cognitive-loop plugin for DeepSeek Harness: Reflect → Assess → Learn → Plan → Handle autonomous code-generation and error-repair state machine with a hard cycle cap and event-sourced observability.
Cross-session self-learning memory for DeepSeek Harness, ported from XT-AGENT packages/memory. BM25 relevance injection + background extraction (sanitize/dedupe/merge) + lifecycle archive + memory_read/memory_search/memory_write tools.
Search arXiv for ML/DL/RL papers and check claims against real abstracts.
Turn any markdown, local folder, or GitHub learning repo into a guided course inside DeepSeek Harness: gated skill-tree progression, BKT mastery tracking, SM-2 spaced repetition.
A proof-carrying correction loop for DSH: explicit adoption, scoped recall, and reconstructable delivery.
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness