Skip to content
View askmy-stack's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report askmy-stack

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
askmy-stack/README.md
From single inference to autonomous loops: the model assists, the system executes

Abhinaysai Kamineni

AI Engineer & Researcher · agent memory · agent reliability


💡 The Perspective

"Intelligence without strong infrastructure and right design is merely a research experiment."


🔗 Find me online

Portfolio LinkedIn GitHub Medium Hugging Face


⚡ What I Do

  • 🧠 Agent memory — decisions captured through Kafka into a Neo4j graph, injected back over MCP.
  • 🛡️ Agent reliability — catch degradation before the task fails, then recover deliberately.
  • 📡 Decision intelligence — noisy geopolitical and shipping signals resolved into calibrated risk bands.
  • 🔬 Applied deep learning — 3D biomedical imaging and long-horizon clinical time series.

🛠️ The Tech Ecosystem

Languages, ML and serving Data and streaming Cloud and operations
Neo4j Airflow LangChain Anthropic MCP native Next.js

Pinned Loading

  1. eeg-seizure-detection eeg-seizure-detection Public

    Benchmark of 15+ neural architectures on 916 hours of pediatric EEG (CHB-MIT) for seizure detection.

    Python 2 1

  2. startupintel startupintel Public

    Open-source startup intelligence platform powered by specialized ML bots.

    Python 1 2

  3. cortex cortex Public

    Organizational memory for AI agents captures decisions into a knowledge graph and serves them over MCP.

    Python 1

  4. meridian meridian Public

    Real-time supply chain risk intelligence powered by geopolitical signals, AIS vessel tracking, and a live knowledge graph.

    Python

  5. tool-semantics tool-semantics Public

    Behavioral compatibility testing for MCP tools and AI-agent interfaces know when a change breaks the agent, not just the schema.

    Python

  6. parallax parallax Public

    Parallax runtime reliability, diagnosis, and recovery for autonomous AI agents (AgentFailBench · semantic monitoring · RecoverAI).

    Python