Search Results for "safety" - Page 2
Sort By:
Showing 62 open source projects for "safety"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning,...
-
2
VibeVoice
Open-source multi-speaker long-form text-to-speech model
...The model integrates a Qwen2.5-based large language model with a diffusion head to produce realistic acoustic details and capture conversational context. Training involved curriculum learning with increasing sequence lengths up to 65K tokens, allowing VibeVoice to handle very long dialogues effectively. Safety mechanisms include an audible disclaimer and imperceptible watermarking in all generated audio to mitigate misuse risks. -
3
OpenAI Agents SDK
A lightweight, powerful framework for multi-agent workflows
The OpenAI Agents Python SDK is a powerful yet lightweight framework for developing multi-agent workflows. This framework enables developers to create and manage agents that can coordinate tasks autonomously, using a set of instructions, tools, guardrails, and handoffs. The SDK allows users to configure workflows in which agents can pass control to other agents as necessary, ensuring dynamic task management. It also includes a built-in tracing system for tracking, debugging, and optimizing... -
4
urllib3
Python HTTP library with thread-safe connection pooling
urllib3 is a powerful, user-friendly HTTP client for Python. Much of the Python ecosystem already uses urllib3 and you should too. Thread safety, connection pooling. Client-side TLS/SSL verification. File uploads with multipart encoding. Helpers for retrying requests and dealing with HTTP redirects. Support for gzip, deflate, brotli, and zstd encoding. Proxy support for HTTP and SOCKS. 100% test coverage. Professional support for urllib3 is available as part of the Tidelift Subscription. ... -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
5
Rogue
AI Agent Evaluator & Red Team Platform
Rogue is an open-source evaluation and red-team framework designed to test the reliability, safety, and policy compliance of AI agents. The platform automatically interacts with an AI agent by generating dynamic scenarios and multi-turn conversations that simulate real-world interactions. Instead of relying solely on static test scripts, Rogue uses an agent-as-a-judge architecture where one agent probes another agent to detect failures or unexpected behaviors. -
6
LLaMA Models
Utilities intended for use with Llama models
This repository serves as the central hub for the Llama foundation model family, consolidating model cards, licenses and use policies, and utilities that support inference and fine-tuning across releases. It ties together other stack components (like safety tooling and developer SDKs) and provides canonical references for model variants and their intended usage. The project’s issues and releases reflect an actively used coordination point for the ecosystem, where guidance, utilities, and compatibility notes are published. It complements separate repos that carry code and demos (for example inference kernels or cookbook content) by keeping authoritative metadata and specs here. ... -
7
Future AGI
Open-source platform for evaluating, observing, and improving LLM
...It supports both cloud and self-hosted deployment models, making it useful for teams with different privacy, infrastructure, and compliance needs. Future AGI is especially relevant for agent-heavy products where reliability, regression testing, and safety checks matter before and after release. Its main value is turning AI agent development into a measurable engineering process instead of an informal cycle of prompting, guessing, and manual review. -
8
repren
Rename anything
Repren is a “rename anything” command-line tool that performs regex-based search and replace across file contents while also renaming or moving files and directories according to patterns. It’s meant for sweeping refactors: change a class or package name everywhere and update filenames to match in one pass. The design favors explicitness and safety, providing dry-run output so you can preview exactly what will change before executing it. It handles recursive directory walks, lets you filter which files to touch, and supports multiple patterns in a single run to keep transformations consistent. Because it’s script-friendly, it slots well into project maintenance, codebase migrations, or release engineering tasks. ... -
9
Semantic Router
Superfast AI decision making and processing of multi-modal data
Semantic Router is a superfast decision-making layer for your LLMs and agents. Rather than waiting for slow, unreliable LLM generations to make tool-use or safety decisions, we use the magic of semantic vector space — routing our requests using semantic meaning. Combining LLMs with deterministic rules means we can be confident that our AI systems behave as intended. Cramming agent tools into the limited context window is expensive, slow, and fundamentally limited. Semantic Router enables lightning-fast and cheap tool usage that can scale to many thousands of tools. ... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
Pedalboard
A Python library for audio
pedalboard is a Python library for working with audio: reading, writing, rendering, adding effects, and more. It supports the most popular audio file formats and a number of common audio effects out of the box and also allows the use of VST3® and Audio Unit formats for loading third-party software instruments and effects. pedalboard was built by Spotify’s Audio Intelligence Lab to enable using studio-quality audio effects from within Python and TensorFlow. Internally at Spotify, pedalboard... -
11
Guardrails
Framework for validating and controlling LLM outputs in AI apps
...Guardrails also supports generating structured data from language models, allowing developers to enforce schemas or type constraints on responses. A companion ecosystem known as a hub provides reusable validators that can be combined into input and output guards to address different reliability and safety concerns. -
12
TypeChat
Library for building type-safe natural language interfaces with LLMs
...Traditional natural language interfaces often relied on complex decision trees to interpret user intent and gather required inputs. With the rise of large language models, developers can interpret user requests more easily, but they still face challenges related to output reliability, safety, and structured responses. TypeChat addresses these challenges by replacing traditional prompt engineering with a concept called schema engineering. Instead of writing complex prompts, developers define types that represent the intents supported by their applications. It then uses those type definitions to construct prompts for language models and translate user input into structured data that follows the defined schema. -
13
Hallucination Leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations
...The results are published as a leaderboard that allows researchers and developers to compare model reliability and factual consistency. By focusing on hallucination rates rather than traditional metrics such as accuracy or fluency, the benchmark highlights an important aspect of AI system safety and trustworthiness. The leaderboard is regularly updated as new models are released and evaluation methods evolve. -
14
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. ... -
15
ZeusDB Vector Database
Blazing-fast vector DB with similarity search and metadata filtering
...Developers get multiple ingestion paths—batch, streaming, and upsert—making it easy to keep embeddings synchronized as content changes. Hybrid search is a core design goal, allowing you to mix vector, keyword, and filter queries in a single request for practical relevance. Observability and safety round out the system, with metrics, tracing, and guardrails to manage recalls, deletions, and privacy-sensitive data at scale. -
16
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. ... -
17
Serena
Agent toolkit providing semantic retrieval and editing capabilities
Serena is a coding-focused agent toolkit that turns an LLM into a practical software-engineering agent with semantic retrieval and editing over real repositories. It operates as an MCP server (and other integrations), exposing IDE-like tools so agents can locate symbols, reason about code structure, make targeted edits, and validate changes. The toolkit is LLM-agnostic and framework-agnostic, positioning itself as a drop-in capability for different chat UIs, orchestrators, or custom agent... -
18
X's Recommendation Algorithm
Source code for the X Recommendation Algorithm
...Written primarily in Scala, it shows the architecture of large-scale recommendation systems, including candidate sourcing, ranking, and heuristics. While certain components (such as safety layers, spam detection, or private data) are excluded, the release provides valuable insights into the design of real-world machine learning–driven ranking systems. The project is intended as a reference for researchers, developers, and the public to study, experiment with, and better understand the mechanisms behind social media content. -
19
Django Cachalot
No effort, no worry, maximum performance
...Cachalot officially supports Python 3.7-3.10 and Django 2.2, 3.2, and 4.0-4.1 with the databases PostgreSQL, SQLite, and MySQL. Note: an upper limit on Django version is set for your safety. Please do not ignore it. To start developing, install the requirements and run the tests via tox. Currently, benchmarks are supported on Linux and Mac/Darwin. You will need a database called "cachalot" on MySQL and PostgreSQL. Additionally, on PostgreSQL, you will need to create a role called "cachalot." You can also run the benchmark, and it'll raise errors with specific instructions for how to fix it. ... -
20
Open Vision Agents by Stream
Build Vision Agents quickly with any model or video provider
Open Vision Agents by Stream is an open source framework from Stream for building real time, multimodal AI agents that watch, listen, and respond to live video streams. It focuses on combining video understanding models, such as YOLO and Roboflow based detectors, with real time large language models like OpenAI Realtime and Gemini Live to create interactive experiences. The framework uses Stream’s ultra low latency edge network so agents can join sessions quickly and maintain very low audio... -
21
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... -
22
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 -
23
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. -
24
bidict
The bidirectional mapping library for Python
Depended on by Google, Venmo, CERN, Baidu, Tencent, and teams across the world since 2009. Familiar, Pythonic APIs that are carefully designed for safety, simplicity, flexibility, and ergonomics. Lightweight, with no runtime dependencies outside Python's standard library. Implemented in concise, well-factored, fully type-hinted Python code that is optimized for running efficiently as well as for long-term maintenance and stability. Extensively documented. 100% test coverage running continuously across all supported Python versions. ... -
25
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.
