Skip to content
View TanishkaMarrott's full-sized avatar

Block or report TanishkaMarrott

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
TanishkaMarrott/README.md

AI Agent Systems Engineer  ·  Cloud & AWS Governance

I build autonomous AI agent systems that reason, remember, and act — from multi-agent deliberation and shared memory banks, to RAG pipelines, MCP tool servers, and LangGraph orchestration. My work sits at the intersection of LLM orchestration, AWS infrastructure engineering, and applied system design.

Currently: AWS Cloud Engineer at KodeKloud — designing and validating AI sentinel systems for multi-organisation AWS lab account governance.


🤖 Featured Work

Dual Agent Memory Two Claude agents (AWS Resource Finder + AWS Recommender) sharing a persistent Hindsight memory bank via the Claude Agent SDK. Agents retain world facts and experience facts across runs — demonstrates tool use, agentic loops, and cross-agent memory patterns.

LangGraph Agent Stateful research + synthesis agent built with LangGraph and Claude. Separates research (tool use loop) from synthesis (clean answer generation) using conditional graph edges, typed AgentState, ToolNode, and MemorySaver checkpointing.

Bedrock RAG Pipeline End-to-end RAG pipeline on AWS Bedrock — document ingestion to S3, Knowledge Base creation, ingestion job orchestration, and grounded generation via the RetrieveAndGenerate API with Claude. Structured citations on every response.

AWS SAR MCP Server FastMCP server exposing the AWS Service Authorization Reference as LLM-callable tools — look up IAM actions, find destructive operations by service, compare permissions, and search across all 300+ AWS services. Zero API key required.

mem0 Pipeline Developer memory pipeline using mem0 OSS (Qdrant vector store + Neo4j entity graph + Ollama) with Claude for cohort graph modelling, entity extraction, and automated insight generation from GitHub activity signals.

AI Sentinel Ecosystem 5-agent autonomous system — quorum governance, predictive autoscaling, cost enforcement, account recovery, and learner intelligence — governing AWS lab accounts across multiple AWS Organisations. Built on the Claude Code Agent SDK with a deterministic 20+ tool MCP layer.


🔧 Tech Stack

AI & Agents

Claude LangGraph AWS Bedrock FastMCP mem0 Qdrant Neo4j Ollama

Cloud & Infrastructure

AWS GCP Terraform Docker Kubernetes

Backend & DevSecOps

Python FastAPI MongoDB GitLab ArgoCD Vault Splunk


📜 Certifications

  • AWS Solutions Architect – Associate
  • GCP Professional Cloud Architect
  • HashiCorp Certified Terraform Associate
  • TOGAF 10 – Level 1  |  Member, Association of Enterprise Architects

📫 Connect

Pinned Loading

  1. dual-agent-memory dual-agent-memory Public

    Two Claude agents (AWS Resource Finder + AWS Recommender) with shared Hindsight memory bank | Claude Agent SDK · Hindsight · AWS · Python

    Python 1

  2. ai-sentinel-ecosystem ai-sentinel-ecosystem Public

    5-agent autonomous system governing AWS lab accounts — quorum deliberation, cost enforcement, predictive autoscaling, account recovery, learner intelligence. See also: https://github.com/TanishkaMa…

    Python 1

  3. langgraph-agent langgraph-agent Public

    Stateful multi-node agent built with LangGraph and Claude — research, reasoning, and synthesis with persistent graph state | LangGraph · Claude · Python

    Python 1

  4. bedrock-rag-pipeline bedrock-rag-pipeline Public

    RAG pipeline using AWS Bedrock Knowledge Base and Claude — document ingestion, semantic retrieval, and grounded generation | Bedrock · Claude · Python · boto3

    Python 1

  5. aws-sar-mcp aws-sar-mcp Public

    FastMCP server exposing the AWS Service Authorization Reference — query IAM actions, find destructive operations, and search across all AWS services | FastMCP · MCP · AWS IAM · Python

    Python 1

  6. mem0-pipeline mem0-pipeline Public

    Memory pipeline using mem0, Qdrant, and Neo4j — ingests GitHub activity, builds an entity knowledge graph, and uses Claude to generate developer insights

    Python 1