DeepSeek Harness 的软工作流插件:在画布上设计流程,编译成计划提示词,由模型按计划执行;运行状态由模型自己记,没有执行引擎
- deepseek-harness
- deepseek-harness-plugin
- dsh
- dsh-plugin
89,572 visible repositories in the index
193–210 of 210 · Most stars
DeepSeek Harness 的软工作流插件:在画布上设计流程,编译成计划提示词,由模型按计划执行;运行状态由模型自己记,没有执行引擎
A ChatGPT, Gemini, Claude, and Ollama(offline) plug-in for Embarcadero RAD Studio IDE XE5 to 12.1
Translateddsh jailbreak - DeepSeek Assistant jailbreak plugin (DSH jailbreak / jailbreak / jailbreak prompts): request boundary injection, so the model no longer starts with "I can't" right away. Combined ASR across 20 categories 45.0%, coverage 19/20, benign capability Δ=0.0pt (24/24 graded); 0 host patches, off by default, off passes through verbatim, every rewrite is recorded in a manifest and promptSha256 for auditing. Former name dsh-jalibreak
A DeepSeek Harness (dsh) plugin — turns dsh web into a SillyTavern-style roleplay frontend: character cards, prompt presets, lorebooks, personas, BM25 long-term memory, world-state deltas, and rollback-able floor operations, all on the dsh agent runtime.
A ~45 MB MaaS platform: one cluster across public and private clouds, on any mix of accelerators.
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.
Local multi-AI desktop workspace with official website panels, shared prompts and group collaboration.
Clover, a 35B diffusion large language model.
MindAct: Community-Driven AI Agent for Claude, Obsidian, and RAG Knowledge Graphs
GLM 5.3 Abliterated or Uncensored AI model — 35 jailbreak prompts, model guide and API. One 7API key also covers Claude, GPT, Gemini, Grok, DeepSeek and Kimi.
Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant
TranslatedA mobile web app where the hamster Mugi (むぎ) practices Japanese conversation with you one-on-one. Core idea: the LLM outputs structured replies using a JSON Schema, with the Japanese lines and the Chinese tips in separate fields, and the frontend uses partial JSON parsing to display the reply as it streams in; prompt caching and voice caching are maintained even during long chats. Kanji readings are annotated by the LLM, and any that it misses are filled in by kuromoji on the server side. Corrections are automatically saved into a tips notebook, so you can practice speaking until you have mastered them. For voice, you can choose local VOICEVOX or cloud Google/Azure, and the keys stay only on the local server. Developed in collaboration with Claude Code (Opus 5.5); originally for personal use, it was released as open source with a brand-new git history that contains no personal data or third-party assets. Records of each decision are in docs/decisions/.
[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
AION-2-Cheat: Complete Standalone Setup for Aion 2 AI Prompt Engineering
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
Translated🗺️ Research Data Map — AI-driven global research visualization platform | Research Data Map with 250M+ papers
Turn any Java, Kotlin or Python project into an AI-ready context file in one command.