Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

Lively Working-line extension for pi CLI and DSH

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

💡DSH 的 Prompt提示词工具箱：常用prompt保存后点击即可注入到对话框——省时省力，/prompt 自动提示已有Prompt。 💡The Prompt toolbox for DSH: save frequently-used prompts and inject them into the dialog with one click — saving time and effort, with /prompt auto-suggesting your existing prompts.

🖥️ Agent-project workbench for DeepSeek Harness — sidebar app drawer + dockable split workspace + a live control room watching every project.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress

Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

Fork of @deepseek-ai/dsh-agent-instructions that delivers the workspace instruction baseline as system-prompt sections, keeping the upstream mid-session reminder path.

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log

Heartbeat plugin for DeepSeek Harness: scheduled autonomous reflection loop with user profile, material pool, pace gate, and gated proactive expression.

Editor-facing ACP server for Zed and other ACP clients, composed from published DeepSeek Harness plugins. Community-maintained; not affiliated with DeepSeek.

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets

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

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

A meticulously curated list of useful plugins, extensions, tools and development resources built for DSH, covering productivity enhancement, functional expansion, debugging utilities and custom development modules.

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

dsh-purge Community · DeepSeek Harness 社区维护版：宿主兼容、状态诊断、提示词管理、更新与本机备份回滚。基于小杨 / YuJunZhiXue 的 dsh-purge。

DeepSeek Harness 破甲 (mirror of YuJunZhiXue/dsh-purge) — 上游即将删库，此为本仓库全量镜像：含全部分支/73 个 tag/完整提交历史。原作者署名与二开要求见 README 署名章节。

dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

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

dsh-purge 社区适配版：上游已停更，这里让它继续跑在 DeepSeek Harness 0.2.1-rc.2 上（基于 1.1.72）