A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.
Repository Index
142,273 visible repositories in the index
841–864 of 1,816 · Most stars
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
- chromadb
- information-retrieval
- openai
- python
Reusable prompts for a structured, evidence-first bug bounty hunting workflow
- application-security
- bug-bounty
- bug-bounty-hunting
- cybersecurity
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
Native vLLM serving for Jev decision models
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
- ai-for-science
- agentic-ai
- ai4science
Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK
- ai-agent
- aliyun
- bug-bounty
- claude-agent-sdk
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
- gpt
- knowledge-graph
- large-language-models
- llama2
An easy-to-use Python framework to generate adversarial jailbreak prompts.
- large-language-model
- llm-security
- llm-safety-benchmark
- jailbreak
Rust multiprovider generative AI client (Ollama, OpenAi, Anthropic, Gemini, DeepSeek, ZAI, OpenRouter, FireworksAI, xAI/Grok, Groq,, ...)
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
- wer
- automatic-speech-recognition
- python3
- speech-to-text
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)
All-in-one native macOS AI chat application for virtually any AI provider
AI-native open-source alternative to Vercel + Sentry + PostHog + Pingdom + Resend + E2B. 440+ CLI operations with drop-in skills for Claude Code, Codex & OpenCode — deployments, analytics, session replay, error tracking, OpenTelemetry, email, sandboxes & AI gateway in one self-hosted Rust binary.
FacTool: Factuality Detection in Generative AI
- generative-ai
- fact-checking
- large-language-models
- python
AI tutor powered by Theory-of-Mind reasoning
- ai
- education
- literacy
- machine-learning
An LLM-based Web Navigating Agent (KDD'24)
Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ONNX, GGUF, vLLM and SGLang; fine-tuning code included.
- decision-model
- jev
- system-one
- typed-decisions
Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, and charts.
- excel
- mcp-server
- claude-ai
- excel-automation
面向 Gemini 的 Local-First AI 工作流 WebUI,集成多模态聊天、Canvas、文件处理、实时搜索、代码执行与高级推理。
- gemini
- gemini-api
- react
NEO Series: Native Vision-Language Models from First Principles
- agi
- encoder-free-vlm
- large-language-models
- multimodal
A Desktop Application for Managing Multiple OpenAI Codex CLI Accounts
Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.