I build software people can reason about.
Developer tools and AI-native systems. I design the infrastructure that lets agents — human and automated — operate without friction. A decade of product engineering.
What I'm working on
I build systems where the contract between components is precise enough that both engineers and AI agents can reason about what's happening — typed pipelines, clear queue handoffs, error messages that tell you exactly what broke and why. The same principle applies whether you're debugging a deliverability issue or reasoning about an AI agent's state.
Smriti comes from the same instinct applied to the development layer. Every AI session starts fresh — decisions lost, context duplicated, zero continuity across teammates. Smriti captures Claude Code, Cursor, and Codex sessions locally, indexes them with hybrid search, and synthesises context on demand using a local LLM. Team knowledge syncs through git. Nothing touches the cloud.
Before that, a decade across frontend engineering, video streaming infrastructure, and developer experience. I also consult on developer tools, API design, and the systems that surround AI-assisted engineering workflows.
Work
- ● Smriti ↗Shared memory for AI-powered engineering teams. Captures and indexes Claude Code, Cursor, and Codex sessions locally, then shares team knowledge through git. No cloud required.
- Open-core HR API for teams that need real control — leave, attendance, shifts, people, and fine-grained field-level access. Self-hostable.
- A Bun/TypeScript CLI for the Tabstack AI API — built live on stream, in a single sitting. Extract any page as structured JSON, run multi-source research, drive browser automation, and pipe everything through standard Unix tools. Includes a self-installing agent skill and a local credit tracking system.
what i work on
Where I'm useful
Six areas, and the problems each one actually solves. If yours is on this list, an email gets a real answer rather than a discovery call.
- Agent system design
Designing typed agent pipelines: stage contracts, queue handoffs, worker boundaries, retry and failure semantics.
Best for: A multi-step LLM pipeline that fails in ways nobody can reproduce · Moving an agent prototype onto infrastructure that can be operated · Deciding where determinism belongs and where the model belongs.
- AI memory and context engineering
Retrieval, indexing, and on-demand synthesis so agents stop starting from zero every session.
Best for: Engineering teams losing decisions between AI coding sessions · Hybrid search over a corpus that keyword search alone cannot serve · Local-first context capture with no cloud dependency.
- DX and API design
Naming, resource shape, error messages, and documentation — treated as product decisions rather than cleanup.
Best for: An API that is powerful but nobody can learn · Preparing a product surface for both human developers and agent callers · OpenAPI descriptions that are accurate enough to drive function calling.
- Developer tooling
CLIs, SDKs, and the feedback loop around them.
Best for: A CLI that needs to be scriptable by both people and agents · Shortening the edit-run-observe loop on a slow codebase.
- Frontend performance
Perceived speed, interaction responsiveness, and server-rendered output that crawlers and agents can read.
Best for: A React or Svelte app that benchmarks fine and still feels slow · A client-rendered site invisible to AI crawlers.
- Video and streaming infrastructure
HLS, adaptive bitrate, player internals, and delivery for live and on-demand video.
Best for: Startup time and rebuffering problems · Player and ABR ladder decisions.
Writing
- 2026-08-21 I uninstalled a mouse driver. It was twelve things. 7 min read
- 2026-08-17 The one percent internet 10 min read
- 2026-07-25 I thought my daemon was one process. It's actually five. 8 min read
- 2026-06-12 State of Agentic Harnesses — June 2026 6 min read
- 2026-06-11 Builder Retrospective: May 2025 → June 2026 16 min read
- 2026-05-27 15 packages, 1 dev. The dependency graph is the architecture. 7 min read
- 2026-05-18 The thing you can only know by staying 4 min read
- 2026-05-06 I thought gcloud compute ssh was ssh. It's six things 11 min read
- 2026-04-08 India is Gmail's #1 market, and nobody's building for it 9 min read
- 2026-03-31 RCM on Import of Services from Foreign Cloud Providers 8 min read
- 2026-03-31 The Tax Knowledge Most Solo Developers Never Get 9 min read
- 2026-03-26 State of Agentic Harnesses — March 2026 4 min read
contact
Want to work together?
Available for contracts and consulting in developer tools, AI systems, and API design.