Google's differential privacy libraries.

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

ResearchStudio: Our AI co-author, from research problem to final publication.

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

State-of-the-art native debugging tools

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Text-audio foundation model from Boson AI

Academic Research Skills for Claude Code: research → write → review → revise → finalize

A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

[NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Implementation of "PrivATE: Differentially Private Average Treatment Effect Estimation for Observational Data" (NDSS 2026)

Implementation of "VICTOR: Dataset Copyright Auditing in Video Recognition Systems" (NDSS 2026)

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Official implementation of "Graph Unlearning" (ACM CCS 2022)

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

Revizor - Hardware fuzzing for the age of speculation

New ways of breaking app-integrated LLMs

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Awesome Machine Unlearning (A Survey of Machine Unlearning)

Official implementation of "PrivGraph: Differentially Private Graph Data Publication by Exploiting Community Information" (USENIX Security 2023)

Official implementation of "FACE-AUDITOR: Data Auditing in Facial Recognition Systems" (USENIX Security 2023)