Skip to content
View aayushi-sing's full-sized avatar
0 followers · 1 following

Block or report aayushi-sing

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.

Content in all repositories owned by your account will be closed.
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
aayushi-sing/README.md

AI systems builder — multi-agent pipelines, RAG, and evaluation-driven development.

I build LLM agent systems and retrieval pipelines, and I care more about whether they fail gracefully than whether the demo looks good.

Currently building

  • ScoutAgent — a six-agent CrewAI pipeline (plan → research → analyze → critique → report) for autonomous startup research, grounded in live web data. Live demo
  • Research Memory Agent — a persistent RAG system that reasons across previously uploaded documents, with cross-document concept discovery and contradiction detection. Live demo

How I work I treat evaluation and failure-case analysis as part of building the system, not an afterthought, tracking things like malformed model output, latency, and where a pipeline breaks under real inputs, not just whether the happy path works.

Stack Python · CrewAI · LangChain ·RAG · LLM FastAPI · ChromaDB · ONNX Runtime

Pinned Loading

  1. research_memory_agent research_memory_agent Public

    AI-powered research assistant with persistent semantic memory, contradiction detection, idea synthesis, and knowledge graph visualization

    Python

  2. scoutagent scoutagent Public

    Autonomous startup research platform using CrewAI, Tavily Search, and persistent memory to generate investment-grade intelligence reports.

    Python

  3. task-manager-api task-manager-api Public

    REST API built with FastAPI, SQLAlchemy & MySQL — features JWT auth, role-based access control, task filtering/pagination, and 51 automated tests.

    Python

  4. openagent-eval openagent-eval Public

    Forked from OpenAgentHQ/openagent-eval

    Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

    Python

  5. Onboarding-Funnel-Analytics Onboarding-Funnel-Analytics Public

    Question-driven funnel analytics on a fintech onboarding flow (50K synthetic users). SQL (CTEs, window functions), Python ETL, and a Streamlit dashboard identify where users drop off, which segment…

    Python