Stars
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Papers about red teaming LLMs and Multimodal models.
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…
Don't Simply Trust MCP Server Code, Validate and Scan
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Cellmate is a sandboxing framework for BUAs that enforces strict boundaries on their behavior, ensuring safety even in the worst-case execution scenario.
A live stream development of RL tunning for LLM agents
Constrain, log and scan your MCP connections for security vulnerabilities.
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with co…
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
The Security Toolkit for LLM Interactions
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
A collection of full time roles in SWE, Quant, and PM for new grads.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
Large-scale LLM inference engine
How can we build a true AI agent? Like Claude Code.
GPU-accelerated vector query processing system that supports large vector datasets beyond GPU memory.
🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️
MCP-SecurityTools 是一个专注于收录和更新网络安全领域 MCP 的开源项目，旨在汇总、整理和优化各类与 MCP 相关的安全工具、技术及实战经验。
Build memory-native AI agents with Memory OS — an open-source framework for long-term memory, retrieval, and adaptive learning in large language models. Agent Memory | Memory System | Memory Manage…
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
[ICLR 2025] Dissecting adversarial robustness of multimodal language model agents