> kiran@portfolio

man ~/projects/*

# projects

// the tools I built because the existing ones annoyed me enough to fix it myself.

// exhibit A — this very site compiling. more casts land on projects as I record them.

npm run build

drwxr-xr-x TruADHD/

live / launched Aug 2026public

An independently verified ADHD provider directory for Pune & PCMC.

WHY
Finding a qualified ADHD professional in India means weeks of guesswork against unreliable listings. TruADHD hand-verifies every provider against public credentials, with no paid rankings or ads — verification is the only gate to being listed.
IMPACT
15 verified providers across 4 categories, 6 in-depth guides, category×city SEO pages, fully prerendered and crawlable, live at truadhd.com
STACK
AstroTypeScriptZodTurso (libSQL)ResendVercel
open --web →

drwxr-xr-x Wizard/

usable / actively versionedpublic

Persistent memory, skills, modes, and work triage for AI coding agents.

WHY
Agents kept losing the thread between sessions. Wizard became the local-first memory layer I wanted: session hooks, 20 MCP tools, 17 agent skills, working modes, PII scrubbing, FTS5 search, analytics, and optional Notion/Obsidian write-back.
IMPACT
v2.2.42, 20 MCP tools, 17 skills, 6 read-only resources, session hooks, Streamlit dashboard, SQLite/FTS5 backend
STACK
Python 3.13+FastMCPSQLiteFTS5SQLModelLiteLLMTyper
open --github →

drwxr-xr-x Alchemist/

private / in active buildprivate

A local-first Rust agentic coding CLI built around harness strength, not model faith.

WHY
Local models are weaker at tool-calling than hosted frontier models. Alchemist compensates with a bounded shared executor, jailed native tools, deterministic TOML workflows, MCP server mounting, confirmation policies, and strict crate boundaries.
IMPACT
single execution core for free-form agent loops and deterministic workflows; no unsafe/unwrap/expect/panic/todo/dbg in non-test code by workspace lint
STACK
RustLM StudioMCPTOML workflowsReedlineTokioClippy
private/internal repo

drwxr-xr-x Forge/

usable internal platformprivate

An internal ops platform that replaced four spreadsheets and a group chat.

WHY
A 3D-printing business needed order management, cost calculation, inventory tracking, slicing, CRM sync, and pricing workflows in one place instead of duct-taped spreadsheets, so I scoped and built the operating system around it.
IMPACT
cost calculator, catalogue, orders, inventory, print jobs, AI quote assistant, MCP server, Rust slicer-preset CLI
STACK
Next.jsHonoPostgreSQLSupabaseRustMCPDocker
private/internal repo

drwxr-xr-x Wand.nvim/

usable daily driverpublic

A Neovim distribution built for one very specific user: me.

WHY
Off-the-shelf configs always fought me on something. Easier to write 7,000+ lines of Lua than compromise on my workflow.
IMPACT
sub-100ms cold boot, full LSP/DAP/test stack included
STACK
LuaNeovimMasonTelescopeDAP
open --github →

drwxr-xr-x Ritual/

usable daily setuppublic

Dotfiles that set up a brand-new machine before your coffee's ready.

WHY
Rebuilding a dev machine from scratch used to eat a weekend. Now it eats one `curl` command.
IMPACT
one-command bootstrap, drift-detected, per-machine templating via Go templates
STACK
ChezmoiGo templatesFishTailscale
open --github →

drwxr-xr-x CtrlAlchemy/

private / in active buildprivate

A YouTube automation platform where every content action is a tracked task.

WHY
Content workflows get messy once transcripts, ideation, generation, analytics, moderation, and publishing all become separate moving parts. CtrlAlchemy treats the whole thing as observable tasks with specialized agents, evals, tracing, and local/prod model routing.
IMPACT
15+ specialized agents, task-first architecture, OpenTelemetry/Prometheus observability, A2A signing, Vertex AI + Ollama model paths
STACK
GoFlutterPostgreSQLOllamaVertex AIOpenTelemetryTerraform
private/internal repo

drwxr-xr-x RAG Agentic Code Analysis/

prototype / learning artifactpublic

Ask a codebase questions instead of grepping it for an hour.

WHY
Wanted to know if multi-agent RAG actually holds up on real code, not toy examples, so I pointed it at real repos and made it show its work.
IMPACT
tracks latency, token cost, and confidence per query, no black-box answers
STACK
LangChainChromaDBAST parsingStreamlit
open --github →

drwxr-xr-x Ctrl Alt Tech/

active publishing channelpublic

A YouTube channel for the engineering layer nobody puts in the demo.

WHY
The interesting part of senior engineering rarely makes it into tutorials: the tradeoffs, the dead ends, the "why we didn't do it that way." So I started filming that part instead.
IMPACT
355 subscribers, 40K+ views
STACK
YouTubeGodotGDScript
open --youtube →