The AI-coding operations layer that makes "done" require evidence — persistent memory, evidence-gated completion checks, and clean handoffs for any AI agent (Claude Code, Codex, Cursor). State lives as plain files in your repo. CLI + MCP, 0 runtime depend

Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

Manage MCP servers (stdio / streamable-http) for dsh web; tools are reached only through four middleware tools. DSH MCP 管理器：Web 侧边栏「MCP」入口，面板按状态分级展示 MCP 服务器（运行中/连接中/已配置/失败），支持快速接入（stdio / streamable-http 表单）与粘贴 mcpServers JSON 导入。已连接服务器的工具一律经中间层工具（ws_mcp_

Two main-stage panels for the DSH web GUI: a multi-column kanban board with real execution through DSH sessions, schedules, session rules and auto-cruise automation, plus a task-list workbench whose rows are themselves cards on one canvas, with a navigati

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.

Use AI agents from the DSH session UI.

深鲸记忆：跨会话热记忆（每轮注入 MEMORY/USER + memory 工具读写）+ 记忆体检、瘦身归档、记忆包、诊断报告、文档只读。本地明文、零依赖、不上传数据。

DSH session completion notifier: appends a plugin system message to the session log on turn/end and pushes browser notifications (Web Notification + toast) with custom per-reason image/icon/alert-sound, plus a fully customizable official settings panel (p

会话管理菜单、归档管理、轮次级删除、重新生成、记忆管理、任务管理、话题导航。Conversation management menu, archive management, round-level deletion, regeneration, memory management, task management, topic navigation.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Claude Code scaffolding and first steps for complex brownfield projects

让 DSH 把做过的任务，变成下次用得上的经验。 候选不会自动采纳。自动整理会使用当前会话模型和额度，两个自动开关可分别控制。 欢迎提交 issues 和 PR。

Requires dsh >= 0.1.7 (session format 4); on dsh 0.1.5 use dsh-repeat-tool-breaker@0.7. Escalating repeat detection for dsh: a synchronous ctx.tools.guard gate that counts semantic fingerprints (exact/cmd/net/host/sink) over a per-agent sliding window, wa

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers, and project ideas from it.

Your team and your AI agents work from the same context: tasks, their full history and time as plain files in your git repository

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Vitest-native testing for Model Context Protocol (MCP) servers - matchers, snapshots, interaction doubles, and real external servers, on both SDK majors.

A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.