@xiaozhugez/dsh-project-memory
Project-scoped AI memory: records pitfalls and user habits per project, injects them into future conversations
229 results
Project-scoped AI memory: records pitfalls and user habits per project, injects them into future conversations
DeepSeek Harness (DSH) WebGIS Plugin: Map reading, map manipulation, and 3D world comprehension.
A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify-commit-push-review-close sequence.
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.
DSH 大会话性能插件:零拷贝 fork + fast initFor + 投影分片预热 + fork 缓存回填 + 分片 materialize + 冷会话 LRU 裁剪 + heap 检测(DeepSeek Harness / DSH)
项目文档体系初始化 skill(DeepSeek Harness 插件包 / Reasonix 技能):提问驱动落实文档规范 + 固化 AI 协作工作流,以「存量完善」为核心场景,跨平台可用(DSH / Reasonix / Claude Code / Codex)。
Better Harness evidence lanes — session, project readiness, and agent assets — as one DeepSeek Harness bundle of three routable skills.
Overleaf tab for dsh-better-sidebar: account login via direct-CDP browsers (third-party Chromium supported), project list/switch, workspace mirrors under <workspace>/overleaf/, git/API sync, and file preview through the sidebar workbench
Discover Codex and Claude project directories and register them as shared DeepSeek Harness workspaces.
DeepSeek Harness dual-ledger cross-session memory: auto-extracted long-term facts (MEMORY.md) plus a living project progress ledger (PROGRESS.md), recalled into every new session.
Minimal prompt x full PTC tools for DeepSeek Harness - aligned with the Project2 we/let's trajectory (Minimal 99/96).
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: the agent publishes a project plan (steps) and a project framework (architecture graph); the browser renders the steps in a right-hand panel and the framework as a downloadable diagram in the center view.
dsh-docker — typed, guarded container control for DSH: structured docker/compose tools, project-aware targeting, an approval gate for destructive ops, service-health context, and a replayable status-table renderer
Persistent GitHub access plugin for DeepSeek Harness: visual settings, credential-backed API calls, and file/project upload tools.
Evidence-first long-term project memory for DeepSeek Harness
Delete sessions of a DeepSeek Harness profile from the UI: header danger button + session-row menu item with a risk-consent dialog; host endpoint + tool delete the log, projection cache and workspace accounting. Works in web and the desktop client alike.
Claude Code-style `paths:` rule injection for DeepSeek Harness (DSH): inject rules from ~/.dsh/rules, <project>/.dsh/rules and <project>/.claude/rules into the model context.
Trace DAG visualizer for the dsh web GUI: a conversation view tab that projects the official trajectory snapshot into a ReactFlow trace graph with dagre / d3-force layouts, hover highlighting, and a slide-out detail panel.
DSH 项目管理插件:在 DSH Web 设置页管理开发项目——添加/删除项目、一键启动/停止/重启、文件变更热重载自动重启、实时日志查看与持久化。
Drop-in replacement for the Codex subagent provider that projects the app-server stream into a harness child session, so Codex runs render as ordinary subagents in the Web UI
Out-of-tree dsh plugin: '@' project file/directory suggestions and plain-text references in the chat composer.
Agent.md viewer/editor tab in the conversation view ring: browse and edit the current project's agent.md from the Chat/Trajectory tab bar.
User-approved Goal, Milestone, and Turn checkpoints for solo long-running DeepSeek Harness projects.