Agents tagged runtime

Open-source LLM evaluation framework (DeepEval) and managed platform from Confident AI for systematic testing. Confident AI offers DeepEval, an open-source LLM evaluation framework, and a managed platform for systematic LLM testing.

Enterprise platform for the CrewAI multi-agent framework with managed deployment, observability, and governance.

Enterprise AI platform for building custom AI assistants grounded in company knowledge with strong governance. Dust is an enterprise AI platform for building custom AI assistants grounded in company knowledge from Notion, Slack, Google Drive, GitHub, and other sources.

AI evaluation and observability platform for production LLM applications with focus on quality and reliability metrics.

Google's enterprise platform for AI agents grounded in company knowledge, with pre-built agents for business workflows.

Google Cloud's managed runtime for deploying and scaling AI agents with Gemini and broader model support. Vertex AI Agent Engine is Google Cloud's managed runtime for deploying and scaling AI agents built with frameworks like ADK, LangChain, LlamaIndex, and others.

No-code AI automation platform for building agentic workflows that combine LLMs with SaaS integrations. Gumloop is a no-code AI automation platform for building agentic workflows that combine LLMs with SaaS integrations.

Hugging Face's platform for hosting AI applications, demos, and agent-based applications with broad community use. Hugging Face Spaces is the leading platform for hosting AI applications, demos, and agent-based applications, with hundreds of thousands of community-created Spaces.

AI development platform for evaluations, prompt engineering, and human feedback collection in LLM applications. Humanloop is an AI development platform for evaluations, prompt engineering, and human feedback collection in LLM applications.

IBM's enterprise platform for building and deploying AI agents that automate business workflows across applications.

Open-source AI engineering platform for tracing, evaluation, prompt management, and labeling for production AI applications. Laminar is an open-source AI engineering platform for tracing, evaluation, prompt management, and labeling for production AI applications.

Open-source LLM observability platform with tracing, prompt management, and evaluations for AI applications. Langfuse is an open-source LLM observability platform with tracing, prompt management, evaluations, and analytics for AI applications and agents.

Managed deployment platform for LangGraph agents with state persistence, human-in-the-loop, and production scaling.

LLM observability and evaluation platform from LangChain for monitoring, debugging, and testing LLM applications and agents.

Managed cloud platform for Letta stateful agents with persistent memory and learning capabilities. Letta Cloud is the managed cloud platform for Letta (formerly MemGPT) stateful agents with persistent memory and learning capabilities.

Open-source proxy and SDK providing unified API access to 100+ LLM providers with routing, caching, and observability.