Ranked by Attention Score: stars gained over the last 7 complete days
101–200 of 468 by Attention Score · Oct 30, 2026 – Nov 5, 2026 (UTC)
TranslatedDeepSeek Harness integrated armor-breaking security analysis plugin: aggregating all domains of Android · Web · Native · Protocol · Malware · AI-Security (9 bundles + 1 preset)
LLM Council works together to answer your hardest questions
Translated🎭 277 plug-and-play AI expert roles — supporting 20 tools such as Claude Code/Cursor/Copilot, covering 20 departments including engineering/design/marketing/finance. Includes 64 original agents for the Chinese market (Xiaohongshu/Douyin/WeChat/Feishu/DingTalk/Qt host computer software/mechanical design). Paired with the orchestrator agency-orchestrator, a single sentence lets multiple experts collaborate automatically as a DAG.
TranslatedOpen-source manuscript of 《深入理解 AI Infra：量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
TranslatedA multi-account gateway that turns Tencent WorkBuddy accounts into an OpenAI-compatible API, while automatically completing all tasks in the task center. Includes a web management panel (account pool visualization / points tasks / hot configuration updates). An enhanced fork based on Sliverkiss/workbuddy2api
TranslatedAn enhanced tool for CodexApp, striving to make Codex better to use and more comfortable. It strives to make Codex and other AI Agents easier and more comfortable to use.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Next Generation Agentic Proxy for AI Agents and MCP servers
TranslatedDeepSeek Harness prompt jailbreak plugin: removes the model's response restrictions through system prompts, with deep adaptation to multiple modes on Web and desktop, as well as tool calling
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.
TranslatedProfessional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
A local inference engine for Apple silicon, built around the model.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
GLM 5.3 abliterated or uncensored API access with RouterHub. Browse 35 jailbreak prompt links, compare GLM models, and find SDK examples, coding-tool setup, pricing, and evaluation guides.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
TranslatedProduction-grade platform for building agentic IM bots - Agent, knowledge base orchestration, plugin system / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信 (Qiye Weixin, "Enterprise WeChat"), 企微智能机器人 (Qiwei Zhineng Jiqiren, "Enterprise WeChat smart bot"), 公众号 (Gongzhonghao, "official account")) / 飞书 (Feishu, "flying book") / 钉钉 (Dingding, "nail nail") / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow
Open Source AI Platform - AI Chat with advanced features that works with every LLM
TranslatedAI Cross-Border E-commerce Operations Agent Toolkit · Breaks operations SOPs down into 7 reusable AI Agent workflows, including prompts, templates, and real-world cases
"RAG-Anything: All-in-One RAG Framework"
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
The repository host gives no description.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
TranslatedBig Blue Fish desktop pet with local LLM. A Windows AI desktop pet with a built-in 4B local large model. It uses a whale-girl persona that combines weather, tech news and the current application to keep you gentle company through text bubbles. Supports one-click installation and pausing inference when off power.
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
Translatedvm2api: converts subscriptions into an API using a fully realistic virtual machine emulation approach
Ontology-Augmented Generation for AI agents.
SGLang is a high-performance serving framework for large language models and multimodal models.
TranslatedAccount management center for new-api / sub2api relay stations: balance, API Key, usage, rate multipliers, model price comparison | https://nvcenter.cc
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
🧱 Experimental library for building inference engines
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
The LLM Evaluation Framework
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
TranslatedCopy-ready prompts & 54 cases of Opus 5.5 code-rendered videos. Claude Opus 5.5 generates videos with code: cases from across the web and prompts you can copy directly.
TranslatedStartup screen and startup animation plugin for DeepSeek Harness
ChatGPT DAN, Jailbreaks prompt
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Official Inference Code of EAGLE-4
TranslatedBullFlow — Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. The entire knowledge base pipeline runs on local open-source models, with no paid models needed; AI Agent creates image-text posts / images / videos, with one-click publishing to 17 platforms including Douyin, Xiaohongshu, WeChat Official Accounts, LinkedIn, and YouTube. Commercial-grade, multi-tenant, billing & admin built in. MIT
Set up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux. Private, and works offline.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
Translated🧬 钝核 (Bluntcore, "blunt core") | Human-AI Intimacy Lab · Bluntcore Intimacy Lab | Human-AI romance, adult AI, Prompt, Memory, Agent, model bed tests, and experiment logs. https://x.com/QloveDudu
the LLM vulnerability scanner
Translatedchat-keeper focuses on providing a Claude mirror site. It offers an experience that is a 1:1 recreation of the official website, and it can be accessed directly from within China.
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra.
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
TranslatedA multi-account gateway that turns Tencent WorkBuddy accounts into an OpenAI-compatible API, while automatically completing all tasks in the task center, with a web admin panel (account pool visualization / points tasks / hot config reload). An enhanced fork based on Sliverkiss/workbuddy2api
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
TranslatedConnect all the model quotas you can get for free into the same DSH pool: automatic multi-account fault tolerance for WorkBuddy, QR-code login for 13 providers, aggregation of free quotas from 76 providers, a usage dashboard, model routing, a local OpenAI gateway, and automated points collection.
TranslatedAn Agent tavern based on DSH. A tavern-style text game Agent. Compatible with the SillyTavern ecosystem; character cards can be imported directly and played. Faster, more stable, more lively. Works with all models. Can also be played on mobile phones.
AI Observability & Evaluation
The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
DSPy: The framework for programming—not prompting—language models
Nano vLLM
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
TranslatedNovember 2026 | Simplest on the web | ChatGPT/Codex top-up / top-up-by-proxy guide | Plus 135, Pro100 650, Pro 200 1140 yuan, Alipay/WeChat Pay, arrives in 1 minute, official subscription, bills can be checked | Includes Grok/Gemini/Claude top-up / top-up-by-proxy | ChatGPT Plus top-up / ChatGPT Pro top-up tutorial | GPT Plus proxy top-up, GPT Pro proxy top-up, Codex proxy top-up subscription tutorial | ChatGPT top-up / GPT proxy top-up / Codex top-up guide / GPT subscription / Codex subscription / Codex proxy top-up / OpenAI subscription tutorial
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Convert PDF to markdown + JSON quickly with high accuracy
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.
LlamaIndex is the document processing platform for AI
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
TranslatedA community-maintained fan-creation resource library for the Whale Girl (鲸鱼娘), collecting character reference images, generation prompts, community works, and related projects, giving creators convenient and easy-to-use references and inspiration. This is an unofficial community project and does not represent the official position of DeepSeek.