Models & MCPPlugin
dsh-purge
YuJunZhiXue
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 ⭐
Structure check pending
deepseekdeepseek-harnessdsh-plugindsh-plugins
Back to Marketplace
Models & MCPPlugin
dsh-Agentlink
hootandy321/dsh-Agentlink
dsh-Agentlink is a tool for DeepSeek Harness. Caller-side bridge from Codex and other agent frameworks to DeepSeek Harness, with observable sessions, follow-up, cancellation, and human-gated approvals.
- Stars
- 7
- Forks
- 2
- Issues
- 5
- Update
- 38 days
REVIEW SCORECARD
Review Scorecard
7.6/10Average
License compliance9.0
Engineering quality5.8
Content completeness7.0
Repository scale7.0
Maintenance activity8.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
7.8/10Consider
Solid, actively maintained Codex/Claude-to-DSH bridge with strong docs, but limited caller support and no published inst
Code quality8
README documents a CI badge, npm test, a doctor command, and explicit fail-closed lock handling, indicating real engineering rigor, though no test details are visible.
Security7
Setup backs up Codex TOML, uses approval_mode = "prompt", requires human-gated approvals and explicit --replace flags, and never starts DSH or alters sandbox settings, though the agent-driven install prompt asks an AI to clone and run scripts.
Utility8
It solves a concrete pain point by letting Codex or Claude Code delegate work to DeepSeek Harness with observable sessions, follow-up, cancellation, and approvals.
Maintenance8
Last updated 2026-08-25 with an active CI workflow and a KNOWN_ISSUES file, and the repo is not archived, indicating ongoing maintenance.
Documentation8
The README covers prerequisites, agent-driven and manual install paths, per-caller setup commands, and known issues, but the install command is listed as unknown and several callers remain planned rather than available.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
PROJECT READMEREADMEExpandCollapse
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is dsh-Agentlink used for?
Caller-side bridge from Codex and other agent frameworks to DeepSeek Harness, with observable sessions, follow-up, cancellation, and human-gated approvals.
How popular is dsh-Agentlink?
dsh-Agentlink has 7 stars and 2 forks on GitHub, last updated 2026-08-25.
What license does dsh-Agentlink use?
dsh-Agentlink is distributed under the MIT license.
Is dsh-Agentlink compatible with DeepSeek Harness?
dsh-Agentlink is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
Classification evidence
Project typePlugin
Feature categoryModels & MCP
Rule confidenceHigh
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:mcp。
Models & MCPPlugin
AI-Novel-Writer
EthanYoQ
AI novel writing software: organizes inspiration, characters, worldbuilding, outlines, chapter writing, review, and revision into a controllable workflow; offers Windows/macOS desktop versions and Ollama and DSH plugin previews.
Structure check pending
ai-writingcreative-writingdeepseek-harnessdsh-plugin
Models & MCPPlugin
agentrq
agentrq
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness.
Structure check pending
acp-clientacp-gatewayagentic-aiagentic-workflow
Models & MCPInfrastructure
sandbase-harness
sandbaseai
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.
Outside plugin validation
agent-frameworkagent-observabilityagent-pluginsagent-runtime
Models & MCPApplication
dsh-desktop
vibeinging
DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.
Outside plugin validation
agentic-workflowsai-agentai-workbenchdata-analysis
Models & MCPPlugin
memtrace-public
syncable-dev
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
Structure check pending
agent-memoryai-agentsbi-temporal-graphclaude-code