47,133 repositories indexed
193–216 of 224 · Most stars
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.
TranslatedDSH Reading Bridge: automatically hands the words in a conversation to the DeepSeek web page to read aloud, with the sound coming out of your own computer
TranslatedDSH plugin: makes her speak up on her own when no one is talking to her (rolls a die locally, and if the roll hits, DSH takes a turn of its own)
TranslatedAI manages QQ groups: reviews and approves requests, sends files to groups, and communicates with the AI in other web sessions! Atmosphere crew: stickers are saved automatically, the AI decides by itself when to speak up, and multiple presets and personas take turns keeping people company in chat! Remote work: permission approvals and question cards are forwarded to QQ. Custom interactive buttons: the AI helps you easily build text games, and the AI writes the card logic for you. Token-saving design: the AI is only woken up after a group chat message is scored for value, and context is compressed automatically.
TranslatedA DeepSeek Harness skill that turns Chinese copy, art-style prompts, and sound into coherent code animations (Remotion / Canvas / HTML). Includes search of a 341-style art library, semantic storyboarding, shot transitions, character performance, four music and sound-effect plans, and review and revision.
Cross-platform desktop LLM client for OpenAI ChatGPT, DeepSeek R1, Anthropic Claude and more, with a focus on privacy and security.
TranslatedA native DeepSeek Harness plugin for Oil UI, with support for automatically switching to a locally installed Oil UI Pro
Translated海鸥工坊 (Haiou Workshop, "Seagull Workshop") | An AI professional workbench for reverse engineering, authorized penetration testing, and security R&D. It has a built-in rea reverse engineering workflow, combines Codex, Claude Code, and DeepSeek Harness, and integrates a professional skill library, REA analysis capabilities, and an on-demand toolchain to assist with binary analysis, Web/API security assessment, code auditing, CTF, digital forensics, and mobile and protocol analysis. It covers work stages such as task breakdown, script writing, tool analysis, evidence organization, remediation suggestions, and technical reports, letting AI take a deep part in professional analysis and development practice.
TranslatedA relay API jailbreak project written in Rust, supporting the Responses / Chat Completions / Anthropic Messages APIs, and supporting most mainstream models such as ChatGPT/Claude/Grok/Gemini/Deepseek/Glm/Kimi
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.
TranslatedDeepSeek Harness startup animation plugin (derivative work edition): dark cyberpunk-style boot animation, with an emblem badge, cyber electronic-style character artwork, and an access password feature
Agent skills that make DeepSeek models plan, verify and ship like frontier models. npx skills add aicodeking/deepseek-stack
Pass the baton from Claude Code or Codex to a local DeepSeek Harness. An MCP server that hands off tasks and brings the result back.
Translated🐋 Complete guide in Russian: how to install and run DeepSeek locally (V4, R1) on PC, Mac and server — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, agents, fine-tuning, best tips and tricks
TranslatedLink to QQ: two-way connection between the AI companion in DSH and QQ — whatever it says is automatically sent to QQ, and whatever you say in QQ is automatically forwarded into DSH (via OneBot 11 HTTP; both NapCat and SnowLuma work)
TranslatedPhone-like KOReader home: curated AI news, AI translation and Q&A on selections, WeRead shortcut
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.
TranslatedDesktop automation for DeepSeek Harness: giving an entire Windows machine eyes and hands. It can do anything a person can do, including but not limited to CAD, WPS, browser operations, and sending WeChat messages. Safe, fast, reliable, smart, and user-friendly.
Translated大肥鱼 (Big Fat Fish) / GPT娘 (GPT Girl) sticker knowledge kit for DeepSeek Harness (dsh), MCP and any chat bot · 大肥鱼 sticker knowledge base
OpenRouter alternative for uncensored AI LLM access — independent RouterHub gives developers one OpenAI- and Anthropic-compatible key for 37 frontier and open-weight models, including GPT, Claude, Grok, DeepSeek and GLM, with published per-token pricing and abliterated or uncensored entries where available.
TranslatedDeepSeek Blue Big Fat Fish Elimination Plan: a Chrome / Edge / Firefox browser extension that identifies and cleans up bot accounts (大肥鱼, Dafeiyu, "big fat fish") driven by the DeepSeek large model and AI agents in Bilibili comment sections. Offline rules + precise judgment by the DeepSeek API, AI comment detection, profile page identification, and one-click clearing by 鲸鱼娘 (Jingyuniang, "whale girl"). DeepSeek AI bot detector for Bilibili comments.
TranslatedA circuit-breaker and reconnector for dsh, aimed at network/large model API fluctuations during long tasks, preventing tasks from stalling; it switches between different channels and models to keep completing the task. Supports web and CLI.
TranslatedLet AI understand the video in which you @ it on Bilibili, and automatically reply with a comment containing clickable timestamps. A DSH / AI Agent skill.
GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok.