# Inside Anuvaya

Technical notes, engineering writeups, and design writing from Anuvaya Labs.

## Articles

- [Multi-Agent Conversational AI](https://inside.anuvaya.com/notes/multi-agent-orchestration): What production conversational AI takes once you stop treating it as request-response: instant talk, slow thinking, one hard invariant, and patience for users who don't wait their turn.
- [Terra: An Agent Framework Extracted from Production](https://inside.anuvaya.com/notes/terra): An Elixir agent framework built on gen_statem. Stateful processes, context aging, multi-agent coordination. Open source.
- [Rune - Long-Term Memory for AI Agents](https://inside.anuvaya.com/notes/rune): An append-only knowledge graph that captures how a user's life evolves over time. Deterministic, causal, and fast enough for real-time conversation.
- [Your Eval Is Broken for the Same Reason Your LLM Is](https://inside.anuvaya.com/notes/llm-evaluation): Lessons learned from building LLM evaluation systems - the right prompts, the right context, and knowing what to measure.
- [RCE - Realtime Context Engine](https://inside.anuvaya.com/notes/realtime-context-engine): A framework for managing dynamic knowledge bases, temporal data hierarchies, and externalized reasoning chains within conversational AI sessions.
- [Stateful Agent Orchestration - Human-Like Conversational AI](https://inside.anuvaya.com/notes/stateful-agent-orchestration): An orchestration architecture that enables human-like conversational behavior with natural delivery pacing, mid-response interruptibility, and graceful recovery.
- [The Boring Designer](https://inside.anuvaya.com/notes/the-boring-designer): A note on the importance of boring design.

## Feeds

- [RSS](https://inside.anuvaya.com/rss.xml)
- [Full text corpus](https://inside.anuvaya.com/llms-full.txt)