Skip to content
View Qalipso's full-sized avatar

Achievements

Achievement: QuickdrawAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Block or report Qalipso

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
Qalipso/README.md

What I do

I build production AI products with a focus on:

  • LLM evaluation — rubrics, LLM-as-judge, safety gates, regression reports
  • AI memory — RAG, structured context, second-brain systems
  • AI workflows — agents, automation, tools, calendars, reports
  • Product engineering — full-stack interfaces that make AI usable
  • Delivery leadership — 6 years shipping software with cross-functional teams

Featured work

AI Evaluation Tool

LLM output QA platform for testing AI responses before they reach users.

Includes: LLM-as-judge, claim grounding, safety gates, regression-style reports, human review.
Stack: Next.js · TypeScript · OpenAI · Zod · Vercel
Code: ai-evaluation-tool

Shadow

AI second brain / life analytics system for memory, tasks, goals, emotions, and personal workflows.

Focus: AI memory, daily signals, structured reflection, personal operating system.
Stack: Next.js · TypeScript · AI memory architecture
Code: shadow-ai-second-brain

RAG Memory Playground

Experiments around retrieval, structured memory, and project context for AI agents.

Focus: RAG, memory comparison, document/project context, retrieval quality.
Code: rag-memory-playground

Agent Studio

Workspace concept for managing AI agents, projects, task queues, statuses, logs, and memory.

Focus: multi-agent workflows, orchestration, project memory, AI operating systems.
Code: Agent-Studio-App

Core stack

AI: LLM evaluation · RAG · AI memory · prompt systems · agents · workflow automation
Engineering: TypeScript · Next.js · React · Node.js · REST APIs · Azure · Vercel
Delivery: stakeholder communication · QA workflows · technical planning · production delivery

Background

6 years in production software delivery — from implementation work to senior team lead.

I like building AI systems that survive real users, messy workflows, edge cases, and business constraints.

Contact

Pinned Loading

  1. ai-evaluation-tool ai-evaluation-tool Public

    Evidence-backed quality control for LLM outputs: rubrics, claim grounding, safety gates, human review, and reports.

    TypeScript 1

  2. Shadow-AI-Second-Brain Shadow-AI-Second-Brain Public

    AI memory engine with RAG recall, typed memory items, graph relationships, pgvector embeddings, and context-aware personal insights.

    TypeScript 1

  3. rag-memory-playground rag-memory-playground Public

    RAG Memory Playground — side-by-side retrieval comparison and memory engine

    TypeScript

  4. saas-delivery-case-flow saas-delivery-case-flow Public

    SaaS Delivery Case Flow — onboarding pipeline and case management UI

    TypeScript 1