v0.1.7 · no license
Manage DeepSeek Harness locally: run multiple DSH versions in isolated containers, open the UI in an embedded WebView, import plugins/skills with one click, share extension bundles, and let a queued task system handle installs with live logs. Zero-dependency installer.
— · no license
The next-gen lightweight coding agent cli
— · MIT
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
— · MIT
Obsidian 零成本同步:iPhone ↔ Mac,GitHub 自动备份。本地优先 + 长期积累。|Local First. Zero-cost Obsidian sync across iPhone, Mac & GitHub. Let knowledge grow over time.
— · no license
ProMentor 是一个 AI Coding Agent Skill。装上它,你的 AI 编程助手立刻化身为导师——扫描项目架构、生成阶梯式 Chapter、带你手写核心逻辑、自动判题、AI Code Review。
— · MIT
3D code dependency graph generator with built-in LLM agent. Language-agnostic (Python, TypeScript, Rust, Go, Java, C/C++, C#, Ruby, Kotlin, Swift, PHP, Lua). Coupling depth analysis, constraint gating, real-time file watching. Tauri 2 + Three.js + Rust engine.跨语言代码依赖拓扑图生成器 · 14 门语言统一 IR · 3D 全息星图 · 内置 AI Agent 双向联动 · 四级耦合诊断 · 桌面应用 / CLI 双模
— · Apache-2.0
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
— · no license
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
— · no license
Atlas Cloud skills for Claude Code, Codex & Gemini CLI — generate images/videos and call 300+ AI models from your coding agent.
— · no license
meoo cli 是秒悟(Meoo)官方推出的命令行工具,让 Claude Code、Codex、Cursor、Qoder等本地 agent 在帮你写完前端代码后,能直接接管「数据库、用户登录、文件存储、部署上线」的所有云端工作——你只需要在终端跑一条命令,剩下的交给 AI。
v0.3.0 · MIT
Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.
v1.0.1 · MIT
Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.
v0.1.0 · no license
Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)
v0.8.8 · MIT
Remote-work assistant for DeepSeek Harness (DSH): connect SSH (key or password), pick a remote workspace, operate with rw_* tools, and SFTP-mirror it into a real local DSH workspace.
v0.1.29 · BSD-3-Clause
A caring memory companion for DSH — three-layer auto memory, proactive calendar reminders, warm AI greetings, per-turn auto-consolidation, and inheritance of memories from other AI tools.
v0.3.7 · Apache-2.0
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
v0.2.12 · MIT
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.
v3.1.1 · MIT
DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
v0.10.0 · MIT
Cross-instance message/event handoff plugins for DSH (interconnect service + tools)
v0.5.5 · Apache-2.0
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
v0.1.2 · MIT
Create and manage sandboxed JavaScript tools for DeepSeek Harness with a Monaco editor and model-driven tool lifecycle.
v0.6.2 · MIT
IMAP/SMTP email tools for DeepSeek Harness: list, read, search and send mail, with QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets.
v1.2.1 · MIT
Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap (bash+read), then full Standard tools after the first tool call or reply
v0.1.3 · MIT
Multi-agent team collaboration for DeepSeek Harness, with independent models, skills, MCP tools, contexts, and a shared workspace.