Naman KundraI build AI agents

A commander agent plans hypotheses and hands one precise question to each of four specialists (metrics, logs, changes, code). They work in parallel and write to an evidence board. Risky fixes go through a trust gate. The whole investigation is a Temporal workflow, so killing the worker mid-incident just resumes it, with no repeated LLM calls. It was also onboarded onto real Linux hosts, including an unmodified WordPress stack, with auto-discovered service graphs.

Hybrid retrieval (Postgres full-text + pgvector, fused with RRF) is followed by an LLM reranker. An agent loop splits multi-part questions, searches in parallel, checks whether the evidence is enough, and follows up once if it isn't. Answers stream over SSE with citation chips. It has per-IP rate limits and an injection scan on ingest.

An accept loop hands sockets to a worker pool. Each connection reserves a backend under one mutex using least-connections, round-robin, IP-hash or Rendezvous hashing, then proxies bidirectionally with select(). A health checker probes backends every 5 s, a stats thread serves JSON, and SIGHUP reloads config live.