Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
- ai
- ai-interpretability
- ai-safety
- aisafety
85,081 visible repositories in the index
2,137–2,160 of 2,616 · Most stars
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
Battle-tested agent skills for Product Builders. Part of the Product Builder OS by Superhero.tech: Super Brain for context, skills for action, built from 32+ years of combined product experience and pressure-tested with 1,800 builders.
File Scanning Framework
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
Let's make a SQL parser so we can provide a familiar interface to non-sql datastores!
A curated list of AI-assisted reverse engineering: decompilation, recompilation and native ports, with how each project verifies correctness
A small course on CTF (wargames) for beginners [in Russian]
Our lightning-fast inference engine.
Efficient sample rate conversion in python
One-link downloader for the Mac (videos, documents, images, articles, web pages), with optional automatic YouTube monitoring that translates and subtitles new videos.
Drivers for InvenSense inertial measurement units MPU9250, MPU9150, MPU6050
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
AI security review CLI: SAST, secret scanning, SCA, threat modeling and architecture review with Claude Code, Copilot, Codex, Gemini, Cursor or an API key. SARIF output for CI.
We took PersistenceSniper, merged it with Python, and misspelled it on purpose. Meet PyrsistenceSniper.
A modular Python application to collect intelligence for malicious hosts.
A simple, secure CLI tool designed to manage secrets (for humans and agents)
THE MOST POWERFUL OFFENSIVE AI AGENT FOR PENTESTING , OSINT , AND ETHICAL HACKING
TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.
A TextMate and Sublime Text Bundle for the Elixir programming language
Automated Tactics Techniques & Procedures
Universal python API to captcha solving services
Equipe de agentes de IA (CrewAI + AWS Bedrock/Claude) que lê a descrição de uma vaga e a base profissional da pessoa e gera currículos personalizados em PDF/LaTeX, em PT ou EN, sem inventar informações e preservando toda a trajetória de carreira.
Create adversarial attacks against machine learning Windows malware detectors
Suitable for Android APK reverse engineering analysis