Skip to content
View anmoldhingra1's full-sized avatar
6 followers · 27 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Public SponsorAchievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: Public SponsorAchievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Block or report anmoldhingra1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
anmoldhingra1/README.md

Anmol Dhingra

I build production AI systems that turn static content into interactive, voiced experiences.

I'm the solo founder of Rerato, a voice-AI orchestration layer for generating AI-hosted experiences from documents, URLs, transcripts, or topics. Trivana.ai is the first public alpha: AI-hosted gameshows with 3,811 experiences generated.

Before Rerato, I spent 9 years building AI in regulated environments across cybersecurity, financial services, NLP, voice, graph ML, and MLOps.

What I work on:

  • Voice-AI orchestration and host scripting
  • LLM evaluation and grounded generation
  • Low-latency runtime and inference systems
  • Multi-agent workflow design
  • Emotion/personality-aware conversational AI

Public repos here are small technical slices from that work. Production Rerato and Trivana code stays private.

Start here:

Voice is not the moat. Orchestration is.

Pinned Loading

  1. agent-flow agent-flow Public

    Lightweight multi-agent orchestration framework for LLM workflows: sequential, parallel, and conditional agent handoffs with shared state.

    Python 1 1

  2. realtime-ai-serve realtime-ai-serve Public

    Low-latency streaming inference server for real-time AI applications: token streaming, batching, hot swaps, and backpressure.

    Python 2

  3. rerato-api-examples rerato-api-examples Public

    Safe public examples for integrating with the Rerato API.

  4. voice-persona-engine voice-persona-engine Public

    Small framework for consistent AI personas: trait vectors, response shaping, and voice/personality experiments across LLM outputs.

    Python 1

  5. llm-eval-harness llm-eval-harness Public

    Minimal evaluation harness for LLM applications: test cases, structured reports, custom evaluators, and regression checks.

    Python 1

  6. speaker-diarization-pipeline speaker-diarization-pipeline Public

    Speaker diarization pipeline for agent/customer audio: segment, label, and prepare voice data for conversation analytics.

    Python 1