Skip to content
View aman-jaglan's full-sized avatar

Highlights

  • Pro

Block or report aman-jaglan

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
aman-jaglan/README.md

Hi, I'm Aman

AI Nerd

Python TypeScript PyTorch FastAPI React Docker PostgreSQL HuggingFace

Research | HuggingFace


Current -- Rockland Systems

Previous -- Co-Founder @ Marshmallo AI

Built Marlo, the agent learning platform. Capture behavior, evaluate outcomes, and turn failures into learnings that deploy back into the agent. Intelligence compounds over time.

  • Marlo SDK -- Python & TypeScript SDKs for capturing agent traces, tool calls, and reasoning
  • Marlo Inbox -- AI email & calendar assistant powered by Marlo
  • Marlo Docs -- Documentation for the platform

Research

Continual Learning, Not Training: Online Adaptation For Agents

ATLAS achieves 54.1% success with GPT-5-mini as Student, outperforming GPT-5 (High) by 13% while reducing cost by 86%. Cross-validation improves accuracy from 28% to 41% without retraining.


Previous -- Arc Computer

Built the open-source continual learning stack for production LLM agents.

  • ATLAS -- Continual learning framework. Teacher-Student architecture with cross-domain transfer and inference-time adaptation. +15.7% accuracy, +31% task completion, 97% non-degradation rate.
  • Atlas SDK -- Runtime wrapper capturing causality traces. Enables offline training via GRPO and GKD.
  • CL-Bench -- Benchmark for evaluating agent continual learning in stateful environments. Production-realistic CRM workflows with multi-turn conversations and state mutations.
  • HuggingFace Models -- Open weights for continual learning research.

Side Projects

  • OpenSearch -- AI research engine that searches, analyzes, and generates cited reports with charts(Better Perplexity)
  • ReplicaDB -- Single platform for data and analytics needs
  • CI Code Companion -- AI-powered GitLab CI/CD tool using Vertex AI for auto-generating tests, docs, and pipeline templates

Focus

  • Continual learning for autonomous agents
  • Reinforcement learning from production feedback
  • Multi Agentic Systems
  • AI -> AI interaction
  • Cross Domain transfer in AI
  • Agent reliability at scale

Connect

Pinned Loading

  1. Arc-Computer/ATLAS Arc-Computer/ATLAS Public

    A Continual Learning Framework for Production LLM Agents

    Python 43 6

  2. Arc-Computer/atlas-sdk Arc-Computer/atlas-sdk Public

    Atlas is infrastructure for continual learning in LLM agents.

    Python 17 4

  3. Marshmallo-AI/docs Marshmallo-AI/docs Public

    Documentation website for marshmallo.ai

    MDX 1

  4. Marshmallo-AI/Marlo Marshmallo-AI/Marlo Public

    Marlo makes your agent efficient consistant and make them learn over time

    Python 2