管线管理内核（pipeline-kernel）：单向任务链的任务板/台账/注册表/巡检/播种/打包/自愈。v0.9.0：rc.8 削薄工程（依赖对齐 rc.8、DshAgentRuntime 窄收口、webServer inject、domain/changed 统一失效、契约测试、CI 全量门禁；业务语义与入口冻结）。

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

Lively Working-line extension for pi CLI and DSH

Pluggable DeepSeek-colored TUI for DeepSeek Harness

Trace Compare & Live Maze for DeepSeek Harness: visualize agent exploration (main path, detours, backtracks) from session logs or live sessions

把 DeepSeek Harness 变成手机 App：移动端界面重排（两级页面栈、会话列表主屏、composer 重排、手势、附件上传）+ 配对码认证网关 + PWA 安装 + 真 Web Push。Complete mobile plugin for DeepSeek Harness (DSH): app-shell mobile UI, pairing-code gateway for public-internet access behind your own reverse proxy, ins

Deep reading & summarization workflow for books/papers/videos/web — plugin parsers, MapReduce deep-read, JSON Schema output, Obsidian-ready (DSH)

把法律画出来 · Make the Law Visible —— 给法律人的诉讼可视化工具集：把凌乱的诉讼图重画成能进材料的图，或直接读案件材料画准一张时间轴。Claude Skill / DeepSeek Harness 通用。

🧠 The memory that dreams — self-evolving memory for DeepSeek Harness: your AI remembers across sessions, consolidates in its sleep, forgets what matters less, and grows smarter over time. Fully offline & private.

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

Claude-Code-style TUI bundle for DeepSeek Harness. 充分结合 DSH 的核心机制和高级特性与Codex CLI 、Claude Code 等主流交互机制，打造的 DSH-Code. （对齐DSH官方上游最新版本！持续更新中！支持DSH 特殊模式，插件系统，模型管理，子代理管理，切换模型特殊动画）

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — TWO agent presets in one install: vibe-math-v1 (classic pipeline: brainstorm → solver iteration → multi-verifier debate → Verified) and vibe-math-v2 (new probability

Swift Cycle governance skill adapter for DeepSeek Harness; user-invoked, version-pinned, and offline-verifiable.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate