# hey, i'm ravi π
whoami
ravi ranjan Β· bengaluru, india
i build things. lately, most of them think a little.
github Β· x Β· medium Β· systemlore Β· aioice
cat about.md
I've been shipping software for about a decade β long enough to have a graveyard of early iOS experiments, a couple of Flutter apps people actually starred, and a growing pile of AI systems I'm genuinely excited about. I'm a generalist at heart: I go wide across mobile, backend, infra, and ML, and I learn by building real things rather than reading about them.
These days I'm most drawn to AI that has to earn its keep β agents that do real work, RAG that cites its sources, tools that make other engineers faster. I spend most of my time on the unglamorous parts: Does it actually work? Can you tell why it did that? Does it run without me babysitting it? That's usually the difference between a demo and something people rely on.
I also have a soft spot for tools that run on your own machine β no API keys, no phoning home.
ls projects/ --active
portico β self-hostable browser automation for regulated portals (healthcare payer / EHR), where PHI can't leave your VPC. The interesting bit: an LLM authors and repairs the automation, but never runs on the hot path β so a healthy run moves at browser speed, not model speed.
org-context β a context engine for coding agents. It ingests a team's code, PRs, tickets, and incidents and serves permission-aware, source-backed context over REST, MCP, and CLI. Basically: give your agents the same context a senior engineer has.
study_graph β a study buddy that runs entirely offline. Drop in your PDFs and notes, ask questions, get cited answers and flashcards β local models, local database, zero API keys.
lumen β a local-first desktop workbench for poking at,
debugging, and operating Kubernetes clusters without living in kubectl.
patient-engagement platform private β rules-first, ML-assisted WhatsApp outreach for a health team, where the model suggests but never overrides the safety rules, and every recommendation is fully auditable.
ls projects/ --archived
Before any of the AI stuff, I was a mobile dev. A couple of those apps are still my most-starred repos β which is either humbling or motivating depending on the day.
doordish β 45 Β·
smart-home-dashboard β 31 β Flutter, back when Flutter was new.
ask --local "anything about ravi"
Retrieval over this page plus a small language model, entirely on your device β nothing you type leaves your browser.
claude mcp add --transport http ravixdaisy https://ravixdaisy.com/mcpcat beliefs.md
Ship it, then make it good. Something in production teaches you more than a perfect plan.
If the AI can't explain itself, it doesn't get to decide. Confidence without a reason is a liability.
Small and self-contained beats big and needy. I'd rather hand you something that runs on your laptop today.
echo $STACK
TypeScript Β· Python Β· React Β· FastAPI Β· Node Β·
PostgreSQL Β· Playwright Β· LangGraph Β· Ollama & local LLMs Β·
pgvector Β· Docker Β· Kubernetes β and whatever the problem actually needs.
ls graveyard/
cause of death: scope creep Β· app store review Β· no eval suite
./break-this-site.sh
# kills the real nginx container serving this page. docker's restart policy and health checks bring it back β usually in a couple of seconds. not a simulation.
β healthy
contact --open-to "good problems"
Always up for good problems β AI products, dev tooling, open source, or anything worth building well.
let's talk β [email protected] Β· π bengaluru, india