Hacker News with Generative AI: Agents

How to Build an Agent (ampcode.com)
It’s not that hard to build a fully functioning, code-editing agent.
Scenario: Using Agents to Test Your Agents (github.com/langwatch)
Scenario is a library for testing agents end-to-end as a human would, but without having to manually do it. The automated testing agent covers every single scenario for you.
Collaborative, agent to agent scenarios (google.github.io)
Oak – Open Agentic Knowledge (github.com/jentic)
Agents depend on APIs as much as AI. Chatbots chat, but agents act, and they act through APIs: checking calendars, booking flights, analyzing data, reconciling accounts, and controlling smart buildings. To realize this potential, we must build a common knowledge foundation that empowers AI to interact with the world's APIs reliably and without artificial barriers or unnecessary intermediaries.
Cyberattacks by AI agents are coming (technologyreview.com)
Agents are the talk of the AI industry—they’re capable of planning, reasoning, and executing complex tasks like scheduling meetings, ordering groceries, or even taking over your computer to change settings on your behalf. But the same sophisticated abilities that make agents helpful assistants could also make them powerful tools for conducting cyberattacks. They could readily be used to identify vulnerable targets, hijack their systems, and steal valuable data from unsuspecting victims.
Show HN: Arrakis – Open-source, self-hostable sandboxing service for AI Agents (github.com/abshkbh)
AI agents can generate malicious or buggy code that can attack the host system its run on.
Show HN: AgentKit – JavaScript Alternative to OpenAI Agents SDK with Native MCP (github.com/inngest)
Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
Imagine an Agent that can hot-reload tools. Open-source (github.com/ShaojieJiang)
An Agentic platform that allows you to define extensions.
Strengthening AI Agent Hijacking Evaluations (nist.gov)
Large AI models are increasingly used to power agentic systems, or “agents,” which can automate complex tasks on behalf of users.
Show HN: Evolving Agents Framework (github.com/matiasmolinas)
A production-grade framework for creating, managing, and evolving AI agents with intelligent agent-to-agent communication. The framework enables you to build collaborative agent ecosystems that can semantically understand requirements, evolve based on past experiences, and communicate effectively to solve complex tasks.
Show HN: Fast-agent – Compose MCP enabled Agents and Workflows in minutes (github.com/evalstate)
fast-agent enables you to create and interact with sophisticated Agents and Workflows in minutes.
What happens to SaaS in a world with computer-using agents? (docs.google.com)
In this world, simple SaaS products risk commodification, as agents will obfuscate the need for humans to interact with them.
Show HN: Mcp-Agent – Build effective agents with Model Context Protocol (github.com/lastmile-ai)
Build effective agents with Model Context Protocol using simple, composable patterns.
Show HN: I built an open source computer-use SDK enabling agents to authenticate (github.com/cuse-dev)
An open-source framework for building AI agents that can interact with computers
Show HN: Durable Swarm – A Framework for Building Reliable AI Agents (github.com/dbos-inc)
Agents Thinking Fast and Slow: A Talker-Reasoner Architecture (arxiv.org)
Large language models have enabled agents of all kinds to interact with users through natural conversation.
We accidentally created the perfect DB for AI agents (twitter.com)
Show HN: Nous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI (github.com/TrafficGuard)
Llama-agents: an async-first framework for building production ready agents (github.com/run-llama)
Show HN: An Open Source project for enhancing AI Agents in taking action (github.com/npi-ai)
Wilbur: A backtracking and self-training agent for performing tasks on the web (bardeen.ai)