Fork · AI video editing
OpenCut — approval-gated edit agent
An agent that inspects footage, transcribes it and proposes a complete edit plan. It cannot press render. Hash-verified provenance on every asset it touches, integrated into the editor's own review interface and tested on real footage.
The same rule that should hold for any agent near a send, publish or deploy button. Published write-up — and an honest market read: we're not the only people building this.
Contribution · Upstream merged
WorldMonitor — India & Cinema variants
Two new configurations and a custom map layer covering 23 hubs, contributed back to the upstream project rather than kept as a private fork. Around fifteen files, plus a published article with original diagrams.
PR #5724 upstream. Different proof from the rest: not “we built a thing” but “a maintainer took our code.”
Field notes · Agent orchestration
Hyperagent fleet over MCP
Alpha testing a 40-agent fleet driven from an entirely different application — relays, fan-outs, and a public skill shipped from the work. The platform's quality loop caught its own agent fabricating facts; some of the flagged “fabrications” turned out to be true.
Two published essays. A system being wrong out loud is worth more than one that never admits doubt.
Substrate · Agent runtime
NanoClaw
The MIT-licensed agent runtime BizClaw is built on and Smriti runs against. Documentation reviewed and written up publicly — the open-source layer directly beneath a commercial deployment.
The thing we contributed to is the thing we deployed.
MCP server · Research tooling
Competitive Intelligence MCP
A server exposing event search, brief generation, dashboard creation and saved-article analysis to any compatible client — built to make competitor research repeatable instead of ad hoc.
Running in production on our own research workflow.
Plugins & skills · Released
Plugins, skills and a knowledge wiki
A chief-of-staff plugin (briefings, meetings, planning, comms), a team status digest, a recent-research engine, and an LLM knowledge wiki — packaged as installable plugins and skills rather than kept as personal prompts.
The same packaging discipline applied to client deliverables.
Two of these were built with no client, no brief and no deadline — and both independently arrived at the same rule as the paid work. OpenCut's agent can plan an entire edit but cannot render it. Hyperagent's quality loop flagged its own output as fabricated, and was sometimes wrong to.
That's the point of showing them. A principle you apply when a client is paying is a policy. A principle you apply when nobody's watching is a practice.
Start a conversation
Tell us what's actually breaking.
Not what you think the AI solution is — that part is usually wrong, including when we guess it. Describe the problem and you'll get an honest read on whether it's worth building.
First conversations are with Lakshmi Narayana U, Founder & Principal Consultant.