Agentspan: Open-source runtime for durable AI agent workflows with crash recovery and observability
Agentspan is an open-source server and SDK for running AI agents as durable workflows. You can define agents programmatically, execute them server-side, and inspect each run and execution state in…
Read the full articleYou might also wanna read
AgentMon: Codenotary's Enterprise Monitoring for AI Agent Networks
Codenotary launched AgentMon, the first enterprise-grade monitoring platform designed specifically for agentic AI networks. It tracks token
Vercel's Agent Stack: A Unified Framework for Building Production-Grade AI Agents
Build production-grade AI agents with Vercel's Agent Stack. Connect to any model, run durable multi-step workflows, and securely link agents

Modular: Agentic Building Blocks: Creating AI Agents with MAX Serve and OpenAI Function Calling
Agentic Building Blocks: Creating AI Agents with MAX Serve and OpenAI Function Calling
AgentLens: Redefining How We Measure Code Agents
AgentLens offers a holistic benchmark for code agents, focusing on user experience and trajectory. It goes beyond pass/fail metrics.
Codenotary launches AgentMon 3 with adaptive runtime security policies for AI agents, now on AWS Marketplace
Codenotary's AgentMon 3 introduces adaptive runtime security policies that learn from AI agent behavior and threats.
Why AI agents stall in production: Hypernetworks as a solution for autonomous operation
Why AI agents stall in production: fine-tuning forgets, RAG leaks context. Hypernetworks generate a task-specific model from your policies a

Comments
Sign in to join the conversation.
No comments yet. Be the first.