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.

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

AI-powered development tools. 18 agents, 19 commands, 29 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

AWS の構成図を draw.io の形式で描く Claude Code の Skill / Claude Code Skill that draws AWS architecture diagrams as draw.io files

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Claude Skill for Backblaze B2 Cloud Storage management from the terminal. Manage buckets, list and search files, audit storage usage, detect stale or large objects, review security posture, and safely clean up data using natural language. Built on the Agent Skills specification and compatible with Claude Code and other skills-based agents.

可自定义收录清单的 DSH 插件市场：收录、安装、卸载、升级一站完成，附 agent 工具与 dshm CLI。

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. Injected on Claude Code, Cursor & OpenCode; skills on Codex & Copilot. One memory per client, session handoffs, promotion into knowledge and rules on your yes, plus orchestration and QA layers.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

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

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Sync your Claude Code brain across machines — memory, skills, agents, rules, and settings with intelligent semantic merge. Git-based, auto-sync hooks.

Toward Autonomous Scientific Discovery

Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval

Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.

Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.