Make the
technical
click.

I’m Himanshu Jha. I build AI integrations and developer tools, then turn the code, failures and lessons into guides developers can use.

Watch the builds

Native AI workspace

OmniDev

Play a real recording

Your context. An agent that can use it.

Watch the Mac app inspect files, propose an edit and ask before running a command.

Native app recording · no narration · waiting time acceleratedInside the OmniDev build

Developer relationsTechnical writingRunnable examplesMeet the builder

Selected builds / See them in use

Less pitch. More product.

The software behind my writing. Watch the workflow, inspect the interface, then follow the implementation.

Agent memory

ContextFirewall

Play a real recording

See what gets remembered. And what gets blocked.

A recorded console walkthrough: memory graph, audited recall, reusable rules and forgetting.

Recorded sample project · on-screen explanations · no audioInside the ContextFirewall build

WebMCP tooling

Graft

Explore the product

A website becomes an inspectable tool.

Compare the source page with its generated contracts, then inspect the evidence behind a tool.

Browser capture · owned demonstration catalogInside the Graft build

Voice workflows

VOX

Explore the product

A spoken request becomes reviewable work.

Explore the saved run, sandbox workspace and mobile approval queue. The tickets are fictional.

Repository capture · historical run · fictional ticketsInside the VOX build

Explore all four case studies

Selected writing / Five deep dives

Build it.
Break it. Explain it.

Agent memory, evaluation and observability—explained through actual failures, source code, and the decisions that followed.

Agent memory / Graphs17 Oct 2026

EmbodiWeave: my agent read its own failure and repeated it, so I made the graph enforce it (FalkorDB + MCP)

A recorded failure changed the design: graph-enforced decisions, fixed promotion gates and a robot simulation that could refuse a regression.

Agent evaluation / Trust28 Sept 2026

ToolTrap: My support agent handed a customer a fake phone number. The fix worked, until the fake moved.

Testing fake-detail leakage, legitimate-detail retention and the limits of prompt-only defenses. Includes scorer corrections and held-out cases.

Observability / Engineering25 Jul 2026

We instrumented an AI agent swarm with SigNoz, and its own telemetry told us we were wrong about almost everything

Tracing a multi-agent system exposed mistaken assumptions about routing, budgets and review quality. The article follows the telemetry to the fix.

Memory / Architecture3 Jul 2026

I built a trust firewall for my AI agent's memory — on Cognee's four verbs

From Cognee’s memory lifecycle to a reviewed context pack: provenance, conflicting facts, embedding failures and the checks around recall.

Debugging / Open source20 Jul 2026

The smolagents bug that made my agent retry the same valid code three times

A minimal reproduction, an interpreter bug and a fix explained step by step. Recognized in DEV’s Summer Bug Smash runner-up announcement.

All writing on DEV

I like the moment
someone says,
“oh, now I get it.”

I also publish as Himanshu Kumar and use the handle himanshu748. My route into developer relations is through building. I work on agent memory, MCP tools, and backend systems, then explain the decisions in public.

I’m interested in helping developer-tool teams turn product knowledge into useful docs, technical articles, sample apps, and demos.

Start with a real questionGive the reader a reason to care before introducing the API.

Make the example inspectableShow the code, the output, and the limits.

Leave a useful next stepA command to run, a repo to explore, or a question worth testing.

See my engineering work