Search Results for "safety"
Sort By:
Showing 20 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.
-
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
1
Swift Concurrency Agent Skill
Add expert Swift Concurrency guidance to your AI coding tool
...Rather than teaching basic Swift, it targets the nuanced behaviors of concurrency primitives, actor isolation, and safety annotations like @MainActor and Sendable. It also clarifies how to reason about structured tasks, cancellation, and performance trade-offs. -
2
Phantasm
Toolkits to create a human-in-the-loop approval layer
Phantasm offers toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents' workflows in real-time, ensuring safety and reliability in AI operations. -
3
GitHub Agentic Workflows
GitHub Agentic Workflows
...By writing intent in markdown files, a developer can quickly generate .yml Actions workflows that perform tasks such as summarizing issues, automating triage, generating reports, or maintaining documentation, all without manually crafting YAML logic from scratch. The system emphasizes safety and guardrails, running agents in sandboxed environments with minimal permissions by default, and using “safe outputs” to constrain what the workflow can write back into the repository. It includes tooling for compiling, testing, and iterating on agentic workflows locally and integrates with GitHub’s existing Actions ecosystem. -
4
Agentic Coding Flywheel Setup
System tool for beginners wanting agentic engineering capabilities
...With a single shell installer, ACFS transforms a fresh compute environment into a ready-to-use development setup that includes modern shells, language runtimes, AI coding agents (like Claude Code, Codex CLI, and Gemini CLI), and a coordinated toolchain for orchestration and safety. The system is designed for developers who want to run multi-agent coding assistants on personal or VPS hosts with minimal manual configuration. It comes with a battle-tested suite of utilities for agent coordination, orchestration, and developer productivity enhancements, such as named tmux panes, agent mail coordination layers, and cloud CLI integrations. -
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.
-
5
AI Agents Masterclass
Follow along with my AI Agents Masterclass videos
...The project includes structured lessons, code examples, and practical exercises that cover foundational concepts like prompt engineering, chaining agents, tool usage, plan execution, evaluation, and safety considerations. It breaks down how autonomous agents interact with external systems, handle iterative reasoning, and integrate with third-party services or APIs to perform real tasks — for example, web search, browsing, scheduling, or coding assistance. Students of the masterclass can follow written modules or Jupyter notebooks that illustrate concepts step by step and progressively build more capable agents. ... -
6
WorkAny
Desktop Agent for Any Task
...It acts as a unified environment where users can ask the AI to generate documents, presentations, websites, spreadsheets, organize files, or write code — all with real-time streaming outputs directly in the app, so you see results as the AI produces them. Powered by a combination of Claude Code as the primary runtime agent and a sandbox execution environment for safety, WorkAny integrates an agent SDK, MCP (Model Context Protocol) support, and custom skills to handle diverse tasks with contextual understanding. Users can connect multiple model providers, including OpenAI, OpenRouter, or custom endpoints, and WorkAny supports parallel task execution with asynchronous result viewing, enhancing productivity. -
7
Superagent
Superagent protects your AI applications
Superagent is an open-source AI safety platform built to protect applications from prompt injections, data leaks, and harmful outputs. It embeds real-time safety directly into AI workflows, helping teams secure models before threats cause damage. Superagent provides guardrails that block jailbreaks, prompt manipulation, and sensitive data exfiltration. It includes redaction tools to remove PII, PHI, and secrets automatically from text. -
8
Claw Code
AI agent harness for AI coding agents
...It emphasizes harness engineering—how agents are structured, how they interact with tools, and how they maintain context during execution. The system is being actively expanded, with a Rust-based runtime in development to improve performance and memory safety. Overall, Claw Code serves as a research-driven platform for advancing agent-based software development systems. -
9
OpenHands
Open-source autonomous AI software engineer
...So we're building all our agents in the open on GitHub, under the MIT license. Our agents can do anything a human developer can: they write code, run commands, and use the web. We're partnering with AI safety experts like Invariant Labs to balance innovation with security. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Ralph AI Agent
AI agent loop that runs repeatedly until all PRD items are complete
...It provides a reactive loop where agents can repeatedly assess the current context, reason about the next best action using large language models, and execute actions across integrated tools and services. The runtime emphasizes safety boundaries by sandboxing operations, enforcing time and token limits, and isolating execution layers to prevent unpredictable side effects. Ralph also includes a built-in plugin system that lets developers attach custom tools, environment connectors, or monitoring hooks without modifying core logic. Designed for extensibility, the framework supports multi-model providers so agents can switch between models or fall back based on task needs. ... -
11
Inspect Petri
An alignment auditing agent capable of exploring alignment hypothesis
Inspect Petri is an open-source alignment auditing agent that lets researchers rapidly test concrete safety hypotheses against target models using realistic, multi-turn scenarios. Instead of building bespoke evals, Inspect Petri automatically generates audit environments from seed “special instructions,” orchestrates an auditor model to probe a target model, and simulates tool use and rollbacks to surface risky behaviors. Each interaction transcript is then scored by a judge model using a consistent rubric so results are comparable across runs and models. ... -
12
web-access
Skill for installing full networking capabilities for Claude Code
...It abstracts common web interactions such as page loading, data extraction, and navigation into reusable functions that can be invoked by agents. The system emphasizes safety and control, likely including mechanisms to manage permissions, rate limits, and content filtering. This allows agents to operate within defined boundaries while still benefiting from dynamic, up-to-date information. The architecture supports integration with broader agent frameworks, making it a key component for building systems that require external knowledge. ... -
13
A.I.G
Full-stack AI Red Teaming platform
AI-Infra-Guard is a powerful open-source security platform from Tencent’s Zhuque Lab designed to assess the safety and resilience of AI infrastructures, codebases, and components through automated scanning and evaluation tools. It brings together AI infrastructure vulnerability scanning, MCP server risk analysis, and jailbreak evaluation into a unified workflow so that enterprises and individuals can identify critical security issues without relying on external services. -
14
Poco Claw
A more beautiful and easier-to-use alternative to OpenClaw
Poco Claw is an AI agent platform designed as a more user-friendly and visually polished alternative to traditional OpenClaw implementations. It focuses on improving usability by providing a modern web interface combined with enhanced interaction capabilities such as built-in messaging and project organization tools. The system operates on a sandboxed runtime, ensuring that tasks executed by the agent are isolated from the host environment, which improves security and reliability. It extends... -
15
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... -
16
agent-browser
Browser automation CLI for AI agents
...It effectively provides a sandbox where AI agents can read, scroll, click, and interpret pages in context, allowing them to automate workflows, answer questions about page content, or generate structured summaries directly from the user’s current tab. The project emphasizes standards and safety, defining interfaces that let agents access DOM data, interpret events, and generate actionable insights without exposing sensitive credential-level access or violating policy boundaries. Users benefit from a tighter feedback loop: agents can observe user tasks in-situ and respond with contextually relevant actions or suggested steps, like form completion, navigation shortcuts, or detailed explanations of UI elements. -
17
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. -
18
TUUI
A desktop MCP client designed as a tool unitary utility integration
...Many components within the project have been directly converted or generated from the prototype project through AI. Given the considerations regarding the quality and safety of AI-generated content, this project employs strict syntax checks and naming conventions. Therefore, for any further development, please ensure that you use the linting tools I've set up to check and automatically fix syntax issues. -
19
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. ... -
20
cordum
Enterprise AI Agent Orchestration & Governance Platform.
...At its core lies the Cordum Agent Protocol (CAP) a high-performance, open standard (NATS/Redis) that decouples agent logic from control. This architecture ensures "Zero-Copy" security (keeping PII off the wire) and provides a centralized Safety Kernel to intercept hallucinations and unauthorized actions before execution. Key Features: Protocol-First: Language-agnostic orchestration (Python, Go, Node, Rust). Safety Kernel: Deterministic guardrails enforced at the infrastructure level. Human-in-the-Loop: Native approval workflows for critical agent actions. ...
- Previous
- You're on page 1
- Next
