Agent Observability Eval

DeepResearch Bench, hosted on Hugging Face, the AI community building the future. Offers documentation and API…

Hugging Face's AI agent that automates post-training

Execution Control Layer for AI Agents. VAP is where nondeterminism stops. If your agents call paid APIs direct…

Claude team/agency command centre

[YC Fall 2024] Voice AI and Chat AI agents: Testing and Observability

Production stack for Gen AI builders. AI gateway, observability, guardrails, governance, and prompt management…

What agent observability looks like in a multiagent, multimodal world with complex routing and logic plus MCP …

Unified LLM Observability and Agent Evaluation Platform for AI Applications—from development to production.

Perspective AI is a research platform that converts rigid forms into conversational AI experiences, capturing …

Mitzu is an analytics agent that autonomously answers questions, monitors KPIs, and runs deep analysis on data…

Canvas Agent: rebuilt workspace that doubles as chat and autonomous agent for debugging nondeterministic LLM a…

AI-native observability agent for production systems. Traces multi-hop agentic workflows, reconstructs decisio…

Watches your workflows. Builds your Agents. Automatically.

AI-native business intelligence

AI product launch/infrastructure