gantry
A coding agent skill for Claude Code, Codex, and other .agents hosts that keeps engineers in the design loop while AI writes the code. Code generation is gated behind collaborative pseudocode the engineer must approve, and every decision is kept in a .gantry doc. Forward, continue, and rebuild modes cover new code, revisited designs, and auditing existing code. MIT licensed.
gantry is an open source coding agent skill package Karthik built for Claude Code, Codex, and generic .agents compatible hosts. Its goal is to keep engineers in the design loop while AI writes the code, so the code stays comprehensible to its author and to onboarders months later. Key details: One primitive: collaborative pseudocode with a hard approval gate before any code is written. The gate fails closed until the engineer has reviewed the current pseudocode and separately authorized implementation; a passing format check never counts as approval Routes to one of three modes by inspecting the working tree. Forward mode authors something new from pseudocode the engineer writes or has the AI draft, with references resolved and edge cases surfaced inline. Continue mode drift checks an existing .gantry doc against the current code before extending it. Rebuild mode runs the primitive in reverse: the engineer writes pseudocode of what they think a function does, and the mismatches with the real body expose gaps in their mental model The .gantry/ .md doc is the source of truth: what was decided, which edge cases were surfaced, what was accepted, edited, or rejected and why, and the code as written Guidance levels (guided, collaborative, concise) change how much explanation it gives without changing the approval gate Ships a browser editor for drafting and reviewing docs No build step and no npm dependencies: two skill folders backed by Node's standard library, with bash and PowerShell installers MIT licensed
For startups and founding teams
Karthik Thyagarajan is a founder-engineer studying Computer Science and Artificial Intelligence at Purdue. At Samsung Research America, he co-architected an always-on AI agent runtime for XR glasses. He is currently building Tavi, a voice teammate for engineering standups, and co-founded buildpurdue, a founder community at Purdue. His work spans agent infrastructure, on-device AI, product engineering, and evaluation.
For an early team building AI products, his strongest demonstrated fit is owning a broad technical problem from product decisions through implementation and evaluation. His current interests are live voice and video AI, AI-first wearables, and infrastructure that lets agents discover and use internet services.
Substantial ownership of agent systems
At Samsung Research America (May to August 2026), he co-architected an always-on agent orchestrator in Kotlin and owned half of a 25+ module runtime. His reported on-device router achieved 95% signal suppression and 90% intent-routing accuracy. His work also covered tool permissions, model routing, memory, and phone control, connecting model behavior to a usable device experience.
Builds teams and operating systems around a problem
As buildpurdue's co-founder and co-president, he helped turn an informal gathering into a founder community with a selective cohort, weekly co-working, funding, and founder-led problem-solving workshops. He built much of its web platform and integrated CRM, applications, events, and check-ins. His account describes data on around 500 students and a mailing list of about 1,000.
Makes technical claims testable
He built PARM, an open-source causal benchmark for when an agent should use personal memory: 157 frozen scenarios and 471 executable cases, with deterministic scoring and versioned replay artifacts. Its portfolio account explicitly distinguishes development results from held-out claims. He also built google-tools-mcp, a published MCP server exposing 169 Google Workspace tools through one OAuth flow.
Pursues difficult product problems
He is currently building Tavi, a voice teammate intended to answer codebase questions and handle small action items during engineering standups. The project tackles multi-person turn-taking, when to stay quiet, sandboxed coding, and synthetic meeting evaluations. This is ongoing work, rather than a claim of shipped adoption. His published interests explain the direction behind it.
Co-founder who ships and thinks about distribution
At Repple (November 2025 to June 2026), he co-founded a competitive fitness app released on the App Store and built the entire FastAPI, PostgreSQL, and Supabase backend, including synchronized workouts, ELO matchmaking, and weekly competition logic. His firsthand account also describes marketing before the UI existed, campus distribution, and why local community density mattered to the product.
This brief summarizes Karthik's public portfolio and firsthand accounts. Employment contributions and internal performance metrics are self-reported; linked code and artifacts provide additional evidence where available.