Search Results for "safety" - Page 3
Sort By:
Showing 71 open source projects for "safety"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
Atheris
A Coverage-Guided, Native Python Fuzzer
...It hooks into Python’s interpreter to collect fine-grained coverage and uses that signal to evolve inputs, pushing programs into previously unexplored code paths. Because many Python libraries are thin wrappers over C/C++ code, Atheris is equally adept at surfacing memory safety issues in extension modules compiled with sanitizers. The tool integrates smoothly with Python’s packaging and unit-test ecosystems, so you can wrap existing tests as fuzz targets and keep results understandable. It supports structured input strategies and custom mutators, which is especially helpful for text and data formats common in Python workloads. ... -
2
The Alignment Handbook
Robust recipes to align language models with human and AI preferences
The Alignment Handbook is an open-source resource created to provide practical guidance for aligning large language models with human preferences and safety requirements. The project focuses on the post-training stage of model development, where models are refined after pre-training to behave more helpfully, safely, and reliably in real-world applications. It provides detailed training recipes that explain how to perform tasks such as supervised fine-tuning, preference modeling, and reinforcement learning from human feedback. ... -
3
PKU Beaver
Constrained Value Alignment via Safe Reinforcement Learning
PKU Beaver is an open-source research project focused on improving the safety alignment of large language models through reinforcement learning from human feedback under explicit safety constraints. The framework introduces techniques that separate helpfulness and harmlessness signals during training, allowing models to optimize for useful responses while minimizing harmful behavior. To support this process, the project provides datasets containing human-labeled examples that encode both performance preferences and safety constraints across multiple dimensions. ... -
4
ImageMerge
ImageMerge combines media, removes duplicates, and renames in order.
...Key features include advanced duplicate detection (checking file size, extension, and content hashing), flexible file handling options (copy, move, or copy-and-delete), and a safe temporary workspace staging system that ensures your files are processed reliably without risk of interruption. Built for speed, safety, and ease of use, ImageMerge gives you complete control over your media organization with a clean interface and robust backend. -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
Visphotgraph Software
Intelligent Precision for Vibration Detection
Visphotgraph is a compact, automated IoT-based seismograph that accurately detects and records ground vibrations in real time. With cloud connectivity and instant data updates, it provides quick insights and reliable alerts to researchers, institutions, industries, and safety teams. -
6
BimmerLink Log Analysis
BMW / MINI Bimmerlink Log Visualizer
...Disclaimer This is a small utility application designed to visualize Bimmerlink time-series logs. As such, it may contain inaccuracies or errors. It must not be used for real diagnostics, vehicle troubleshooting, or safety-critical decisions. For any official or accurate diagnosis, always rely on certified tools or professional automotive technicians. SHA256 hash of BimmerLogAnalyzer.exe: ae3c7cd66bf9f34736dc004a2ba4e92435e3736eac114b78ee02f0d14210d33a DETAIL; https://github.com/aaasci/bimmerlink_log_analysis -
7
OpenaiBot
Refractoring ChatBot+LLM, Gpt-3.5-turbo, ChatGPT Bot/Voice Assistant
If you don't have the instant messaging platform you need or you want to develop a new application, you are welcome to contribute to this repository. You can develop a new Controller by using Event.py. Compatibility with multiple LLMs and integration with GPT and third-party systems is handled by our llm-kira project on GitHub. It can accurately limit billing, with limits and ID binding. Supports asynchronous operations and can handle multiple requests simultaneously. Allows for private and... -
8
State of Open Source AI
Clarity in the current fast-paced mess of Open Source innovation
...Because the AI domain moves quickly, part of the aim is to make the content maintainable and updateable by the community. The structure includes chapters or sections about model formats, evaluation benchmarks, hardware/backends, MLOps systems, alignment and safety issues, and open datasets. The repository contains the text (in Markdown or similar), configuration for build or publishing (static site or e-book), and contributor guidelines. -
9
ParlAI
A framework for training and evaluating AI models
...It provides a unified interface—agents, teachers, and worlds—so the same model can be trained on multi-turn chit-chat, question answering, task-oriented dialogue, retrieval, or safety-focused datasets without changing core code. The library integrates tightly with PyTorch and supports both generative and retrieval-augmented models, along with utilities for multitask training and model selection. A large set of built-in tasks and dataset loaders (with consistent preprocessing and metrics) makes it easy to compare methods under shared conditions. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Ultroid
Telegram UserBot, Built in Python Using Telethon lib
Ultroid, a pluggable telegram userbot, made in python using Telethon! Ultroid has been written from scratch, making it more stable and less crashes. Ultroid warns you when you try to install/execute dangerous stuff (people nowadays make plugins to hack user accounts, Ultroid is safe). Unlike many others userbots that are being suspended by Heroku, Ultroid doesn't get suspended. Ultroid has been written from scratch, making it more stable and less of crashes. Error handling been done in the... -
11
Face Mask Detection
Face Mask Detection system based on computer vision and deep learning
...Amid the ongoing COVID-19 pandemic, there are no efficient face mask detection applications which are now in high demand for transportation means, densely populated areas, residential districts, large-scale manufacturers and other enterprises to ensure safety. The absence of large datasets of ‘with_mask’ images has made this task cumbersome and challenging. Our face mask detector doesn't use any morphed masked images dataset and the model is accurate. Owing to the use of MobileNetV2 architecture, it is computationally efficient, thus making it easier to deploy the model to embedded systems (Raspberry Pi, Google Coral, etc.). -
12
Spinning Up in Deep RL
Educational resource to help anyone learn deep reinforcement learning
...At OpenAI, we believe that deep learning generally, and deep reinforcement learning specifically, will play central roles in the development of powerful AI technology. To ensure that AI is safe, we have to come up with safety strategies and algorithms that are compatible with this paradigm. As a result, we encourage everyone who asks this question to study these fields. However, while there are many resources to help people quickly ramp up on deep learning, deep reinforcement learning is more challenging to break into. -
13
SCRAM
Probabilistic Risk Assessment Tool
SCRAM is a free and open source probabilistic risk analysis tool. The tool is under development to include fault tree, event tree, common cause, and other standard analyses. -
14
SafetySwitch
Un-attended shutdown of multiple SSH enabled devices.
Polar Bear Safety Switch is an Open Source suite that has been designed for reliable, un-attended shutdown of Juniper devices (M, EX and SRX series), Checkpoint appliances as well as multiple UNIX based SSH enabled devices. -
15
BlackRay is a high performance relational database, which combines regular database features with search engine like performance. Full transaction support, SQL and version controlled persisted snapshots characterize BlackRay.
-
16
ReliaFree is a Python and PyGTK based suite of tools to assist in Reliability, Availability, Maintainability, and Safety (RAMS) analyses. ReliaFree is intended to be an Open Source alternative to proprietary RAMS analyses solutions.
-
17
The PyAALib project is a Python implementation of the Asynchronous Action Framework based in Pure Object Oriented Concepts to develop asynchronous communication between threads (thread safety) and external process.
-
18
AALib/PyAALib - Asynchronous Action Library Project - The project is a Framework based on Pure Object Oriented Concepts to develop asynchronous communication between threads (thread safety) and external process. Platforms: Windows, MacOSX, Linux,Sola
-
19
RTL-Check is a framework for static analysis of programs from a safety and security perspective. It performs analysis on RTL, which is the low-level intermediate representation generated by GCC
-
20
SVATS [Safety Verification Analysis added To Spice] is a Pyhton written EDA tool used for adding repetitive analysis capabilities to perform FMEAs on analog and mixed analog-digital electronic circuits using Berkeley Spice-like simulation SW
-
21
llmverify-npm
You need a safety layer between your LLM and your users.
Stop shipping unsafe AI output. Local-first verification, safety monitoring, and guardrails for any LLM 100% Local | No Telemetry | Privacy-First | 500 free calls/day Links Product Page: subodhkc.com/products/llmverify npm: npmjs.com/package/llmverify GitHub: github.com/subodhkc/llmverify-npm Python Package (PyPI): github.com/subodhkc/llmverify Author: Subodh KC — AI governance, compliance, and security leader Feature One-liner What it catches Verify output await verify(aiResponse) Hallucinations, harmful content, quality issues Block injections isInputSafe(userMessage) Prompt injection, jailbreaks, malicious input Redact PII redactPII(text) Emails, phones, SSNs, credit cards, API keys Fix broken JSON repairJSON(broken) Missing brackets, trailing commas, unquoted keys Monitor health monitorLLM(client) Latency spikes, token drift, behavioral changes Sentinel tests sentinel.quick(client, model) LLM regressions b
