Tagged "agent-design"
5 articles tagged agent-design, 25 February 2026 to 26 March 2026. Newest first.
-
Meta Releases HyperAgents: Self-Improving AI
Meta has released HyperAgents, a research framework for building self-improving AI agents. The open-source release could inform local agent deployment patterns and autonomous system design.
-
Show HN: Open Agent Spec – Treat AI Agents Like Typed Functions, Not Prompt Chains
A new specification enables developers to define AI agents with strong typing and structured interfaces, moving beyond unstructured prompt chaining for more reliable local deployments.
-
Ex-Manus Backend Lead Shares: Moving Beyond Function Calling in Agent Design
A former backend engineer at Manus shares production insights after 2 years building AI agents, revealing why they abandoned function calling entirely and presenting alternative architectural patterns. The post distills hard-won lessons about reliable agent design for production deployments.
-
Analysis Reveals Claude Code Sends 62,600 Characters of Tool Definitions Per Turn
A detailed technical analysis traces how Claude Code uses context window tokens, comparing it against five different CLI implementations. The findings highlight inefficiencies in current tool-passing approaches for local LLM deployment.
-
PyTorch Foundation Announces New Members as Agentic AI Demand Grows
The PyTorch Foundation is expanding its membership and focusing on agentic AI frameworks, reflecting growing demand for agent-based systems that can run locally. The foundation's initiatives support development of inference frameworks suitable for edge deployment.