About this episode
TNews includes Mark announcing his new Sagents library for building AI agents with human-in-the-loop oversight and real-time debugging capabilities, José Valim's blog post on why Elixir is the best language for AI based on recent completion rate studies, LiveDebugger v0.6.0 with custom events and enhanced exception handling, an analysis of Elixir developer salaries showing US senior remote positions at ~$163k median, Peter Ullrich's new MCP server implementation for Elixir, a revamp of Lua for Elixir with improved tooling, Elixir Hub's new events section for finding conferences and meetups, and a discussion on whether AI advancements like Opus 4.6 are eliminating the SDK advantage of more popular languages, and more!e
Show Notes online - http://podcast.thinkingelixir.com/292
Elixir Community News
https://paraxial.io/ – Paraxial.io is sponsoring today's show! Sign up for a free trial of Paraxial.io today and mention Thinking Elixir when you schedule a demo for a special offer.
https://github.com/sagents-ai – Github organization home to the Sagents projects
https://github.com/sagents-ai/sagents – Mark announces Sagents - "Sage Agents" library combining wisdom with LLM-based agents, featuring HITL, SubAgents, GenServer architecture, Phoenix.Presence integration, middleware system, and more
https://github.com/sagents-ai/sagents_live_debugger – Phoenix LiveView dashboard for debugging and monitoring Sagents agents in real-time with visibility into agent execution, message history, tool calls, and events
https://github.com/sagents-ai/agents_demo – Demonstration Phoenix LiveView application showcasing Sagents's multi-conversation agent architecture with isolated AI agents and real-time updates
https://x.com/josevalim/status/2019422467446698493 – José Valim announces his new blog post on why Elixir is the best language for AI
https://dashbit.co/blog/why-elixir-best-language-for-ai – José Valim's blog post explaining why Elixir is best for AI, focusing on immutability,
