All AI Agents

The open-source LLM observability platform for developers.

Arize AI is unified AI observability and LLM evaluation platform - built for AI engineers, by AI engineers.

Simulation & Evaluation for AI Voice & Chat Agents. YC S24.

The LLM engineering platform thousands of developers love. Easily trace and debug your LLM outputs in production. Keywords AI is basically Datadog for AI applications. Get started with 2 lines of code.

Open Source LLM Engineering Platform. Langfuse is the 𝗺𝗼𝘀𝘁 𝗽𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲 𝗟𝗟𝗠𝗢𝗽𝘀 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺. It helps teams collaboratively develop, monitor, evaluate, and debug AI applications. Langfuse can be 𝘀𝗲𝗹𝗳-𝗵𝗼𝘀𝘁𝗲𝗱 in minutes and is battle-tested and used in production by thousands of users from YC startups to large companies like Khan Academy or Twilio. Langfuse builds on a proven track record of reliability and performance. Developers can trace any Large Language model or framework using our SDKs for Python and JS/TS, our open API or our native integrations (OpenAI, Langchain, Llama-Index, Vercel AI SDK). Beyond tracing, developers use 𝗟𝗮𝗻𝗴𝗳𝘂𝘀𝗲 𝗣𝗿𝗼𝗺𝗽𝘁 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁, 𝗶𝘁𝘀 𝗼𝗽𝗲𝗻 𝗔𝗣𝗜𝘀, 𝗮𝗻𝗱 𝘁𝗲𝘀𝘁𝗶𝗻𝗴 𝗮𝗻𝗱 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 to improve the quality of their applications. Product managers can 𝗮𝗻𝗮𝗹𝘆𝘇𝗲, 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗲, 𝗮𝗻𝗱 𝗱𝗲𝗯𝘂𝗴 𝗔𝗜 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝘀 by accessing detailed metrics on costs, latencies, and user feedback in the Langfuse Dashboard. They can bring 𝗵𝘂𝗺𝗮𝗻𝘀 𝗶𝗻 𝘁𝗵𝗲 𝗹𝗼𝗼𝗽 by setting up annotation workflows for human labelers to score their application. Langfuse can also be used to 𝗺𝗼𝗻𝗶𝘁𝗼𝗿 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗿𝗶𝘀𝗸𝘀 through security framework and evaluation pipelines. Langfuse enables 𝗻𝗼𝗻-𝘁𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝘁𝗲𝗮𝗺 𝗺𝗲𝗺𝗯𝗲𝗿𝘀 to iterate on prompts and model configurations directly within the Langfuse UI or use the Langfuse Playground for fast prompt testing.

Ship agents with confidence. LangSmith is a unified observability & evals platform where teams can debug, test, and monitor AI app performance — whether building with LangChain or not.

AI (Gateway, Guardrails, Governance)∙ Processing 50 Billion+ LLM tokens every day.

Build trust into AI with Fiddler - the pioneer in AI Observability. Monitor, explain, analyze, and improve your ML models and LLM applications.

Multi-observability Enterprise-grade SRE automation Platform.

Manage, Improve, and Collaborate with all your AI Agents in one place.

Manage your risk at the speed of AI. AI Guardian is a governance, risk and compliance (GRC) software platform that tracks and manages the use of AI across your business, flagging risks and identifying actions to minimize those risks. AI Guardian enables AI-driven innovation and performance improvement through governance and compliance systems, mitigating AI-related risks and balancing speed with safety. AI Guardian provides: - A centralized system of record for AI projects - At-a-glance visibility into AI projects across your business - AI Policy Intelligence to foster transparency and accountability - Risk tracking and mitigation across the five categories of AI-driven risk

Making the next 1 billion agents fast, safe, and reliable. Agents suck. We're fixing that.

Relari helps businesses build reliable, production-ready AI agents—fast. With Nuvi, our natural language-based agent builder, teams can go from idea to deployed agent without writing code. At the core is our Agent Contract framework, which defines agent behavior up front, ensures performance through testing, and speeds up iteration cycles. Trusted by leading companies—from high-growth startups to large enterprises—to power customer experiences and internal workflows with AI.

Fusing neuro-symbolic GenAI and intelligent agents to give companies an edge. In today’s volatile landscape, intelligence alone isn’t enough—leaders need wisdom to anticipate risks, seize opportunities, and act decisively. Weave AI fuses neuro-symbolic GenAI with intelligent agents to transform fragmented data into proactive, explainable, and actionable insights. Our platform integrates structured and unstructured data at scale, uncovering emerging risks, competitive shifts, regulatory challenges, and untapped opportunities. Financial institutions rely on Weave AI to spot opportunities and anticipate compliance and systemic risks, while enterprises navigate market dynamics, operational threats, and growth potential. As risks and opportunities evolve, Weave AI keeps leaders ahead with proactive, defensible decisions.

A platform for operationalising Responsible AI principles in Gen AI enabled enterprise business processes.

🌊 An open-source alternative to OpenAI Operator A playground for testing web agents powered by Steel.dev. Experience how different AI agents can surf and interact with the web just like humans do.

A research prototype exploring the future of human-agent interaction, starting with browsers. Google project.

Repetitive work is dead. Browser Use empowers anyone to automate repetitive online tasks, no code required.

AI assistants specifically designed to help with web browsing, research, and online tasks. We make intelligent commerce effortless.

Chat Recap AI uses advanced artificial intelligence to analyze your WhatsApp & Telegram conversations. Discover patterns, emotions, and relationship insights with our powerful AI chat analysis tool.

Forging Superintelligence. Putting AI to work for you, with #RunnerH sparking the agentic AI revolution.

Emergence Web Automation (BETA). Meet our multi-agent orchestrator for enterprises, delivering human-level browser control with machine-level scalability.

A Chrome extension for asking questions over websites. Site RAG can index a single page of the website, or crawl the entire site. It then generates embeddings for the indexed documents, and stores them in a vector store database. When a user asks a question, Site RAG will either fetch relevant documents from the current page, or the entire site (customizable).

Building a web agent is a complex task. You need to understand the user's intent, convert it into headless browser operations, and execute actions, each of which can be incredibly complex on their own.

Operator can be asked to handle a wide variety of repetitive browser tasks such as filling out forms, ordering groceries, and even creating memes. The ability to use the same interfaces and tools that humans interact with on a daily basis broadens the utility of AI, helping people save time on everyday tasks while opening up new engagement opportunities for businesses.

The Agent Inbox UI is a generic app which can connect to, and interact with any LangGraph app that uses interrupt events for human-in-the-loop workflows.

Building an End-to-End Web Agent with Large Multimodal Models.

Your WooCommerce AI Sidekick. More Sales. Less Work. AI tools that help you generate compelling WooCommerce product content, boosting conversions and saving you hours every week.

AI agent and automation. Easily extract and monitor data from webpages, intelligently create automation workflows, and automate webpage actions and tasks.

MultiOn is the Motor Cortex layer for AI, enabling autonomous actions on the web using natural language commands with millions of concurrent AI Agents ready to run.