N.V.J.K KartikKartik

Checked September 2026

Receipts

Every factual claim on this site points to one of these. Shared work names the people it was shared with, and preprints are labelled as preprints.

Every source

  1. arXiv:2509.14647 — AgentCompass (preprint, v1, 18 Sep 2025)Title, author order (Kartik first), date, preprint status, abstract.
  2. AgentCompass full text (arXiv HTML)Four-stage pipeline, five-category error taxonomy, episodic/semantic memory, TRAIL results table.
  3. Springer — T4E 2024 Proceedings Vol. 2, pp. 43–51Title, author order (Kartik first), series, pages, published online 23 Oct 2025 (via Crossref metadata).
  4. Crossref metadata for DOI 10.1007/978-981-95-1734-3_6Author list, online publication date, page range.
  5. IEEE Xplore — Advancing Speaker Diarization With Whisper… (TALE 2024)Method (pyannote + Whisper, custom VAD, embedding clustering), 137 recordings, DER 0.26 vs Deepgram/Otter.
  6. IEEE TALE 2024 — AwardsBest Student Paper; full author order (Aarsh Desai first, Kartik second).
  7. IIT Bombay Educational Technology — AwardsIndependent listing of the TALE 2024 Best Student Paper.
  8. Badhe & Rajendran — multimodal follow-up on SSMR triggers (Springer, 2026)The group later proposed extending verbal-only trigger detection with video (posture, head movement).
  9. github.com/hackfest-dev/HF24-NexusNexus crypto exchange with emotional monitoring (Hackfest 2024). Kartik’s commits: project setup (Vite + React), dashboard/coin/crypto pages, stress metric, market volatility, trade analysis route, mood logging, educational content.
  10. github.com/NVJKKartik/HivemindHivemind (2023, EJS; began as a course project). Kartik’s commits: Firebase PDF upload and rendering, authenticated book reader, discussion forum messaging, notepad, image upload, WebGazer in the book finder. With priyeshgupta14, PlatJack (Aarsh Desai), VinayakRai5.
  11. github.com/NVJKKartik/Alumni_connectAlumni Connect Flutter app (profiles, search, chat, posts, job listings). Contributors: Ashxsh1 (Aarsh Desai, lead), NVJKKartik, VinayakRai5, priyeshgupta14.
  12. github.com/VinayakRai5/Centio.AICentio.AI assistant (chat, assistant tasks, researcher, docs RAG). Kartik is a contributor; his BrainBox repo carries the same app.
  13. github.com/PlatJack/DRS-Hackathon-2Emotion detector for online classes, aimed at students with disabilities. Kartik is a contributor.
  14. github.com/NVJKKartik/AI-Task_AllocationLangChain task-allocation agent (2025).
  15. LIDC-IDRI dataset (The Cancer Imaging Archive)Public lung CT dataset used for the NIT Puducherry work.
  16. USPTO Official Gazette — US 12,608,610 B1Title, inventors (Kartik fourth of four), assignee Future AGI Inc., filed 27 May 2025, issued 21 Apr 2026, claim 1.
  17. github.com/future-agi/traceAIWhat traceAI is, OpenTelemetry-native, integrations, Apache-2.0 license, contributor ranking.
  18. traceAI v1.0.0 release (published by @NVJKKartik, 11 Mar 2026)Four languages; 46 Python packages, 39 TypeScript packages, 24 Java modules, C# core SDK.
  19. traceAI contributors graphKartik is the top contributor: 215 commits, then JayaSurya-27 (145) and sarthakFuture (29), on 26 Sep 2026.
  20. npm — ~nvjkkartikListed as a maintainer on 54 packages (@traceai/*, @future-agi/*, @agentcc/*) on 2026-09-25.
  21. PyPI — nvjkkartikProfile link only; package count not verified (page is bot-protected).
  22. Hugging Face — nvjkkartikllama2-qlora-hi-7b (Nov 2023) and Mistral emotion–cause pair model repos.
  23. GitHub — NVJKKartikPersonal repositories listed under Experiments.
  24. DEV — kartik-nvjkArticles snapshotted into the Writing section.
  25. Medium — @kartik.nvjArticles snapshotted into the Writing section.
  26. LinkedInProfile link only; not machine-readable, nothing on the site is sourced from it.
  27. Previous portfolio, as it stood before this redesign (self-reported)Self-reported: IIIT Dharwad (Data Science & AI), research at IIT Bombay Educational Technology, CRF approach for SSMR.
  28. future-agi/agent-learning-kit PR #13 — Version 1.0.0 (merged 27 Feb 2026)Unified evaluate() with engine routing, 72+ local metrics, multimodal judge, feedback loop, streaming, OTel spans, distributed backends, uv migration. Authored by Kartik; 38 of 39 commits his, one from nik13.
  29. future-agi/agent-opt PR #6 — first release to main (merged 2 Oct 2025)Optimizers shipped (random search, ProTeGi, meta-prompt, GEPA, Bayesian, PromptWizard). Commit authors: Kartik (working prototype, simplified loop, Bayesian search) and azain-commits (most other optimizers, evaluator integration).
  30. future-agi/simulate-sdk PR #4 — chat simulation (merged 30 Dec 2025)Agent wrappers for OpenAI, LangChain, Anthropic, Gemini; tool calls and outputs; traced conversations; timeouts; platform runs; LiveKit engine split out. All 28 commits by Kartik.
  31. future-agi/agent-command-center-sdk PR #1 — AgentCC SDK v1.0.0 and the public repository (merged 22 Apr 2026)v1.0.0 of agentcc (Python), @agentcc/client, @agentcc/langchain, @agentcc/llamaindex, @agentcc/react, @agentcc/vercel, as one commit by Kartik. The SDKs were first written by nik13 in an internal repository and were already on npm and PyPI as 0.1.0 (9 Apr 2026).
  32. future-agi/future-agi PR #2302 — Anthropic server tools on the OpenAI-format endpoint (merged 25 Aug 2026)Non-function tools were silently dropped by the Anthropic translator; the fix keeps and replays the caller’s original bytes. Authored by Kartik.
  33. future-agi/future-agi PR #853 — Error Feed cluster RCA agent, perf sweep, billing (merged 27 Jun 2026)Root-cause agent over ClickHouse traces (at launch: per-trace summaries on a lite model, the investigation on the main model, ~$0.03–0.08 a run), streamed Fix tab, cached synthesis, billing wiring. Feed endpoints before → after: overview ~1.5 s → 49 ms, trends ~800 ms → 280 ms, sidebar ~1.2 s → 100 ms, list ~1.7 s → 47 ms. Authored by Kartik: 83 of 113 commits. velalagan-pixel (19) built the redesigned Overview and Fix tab UI; the KarthikAvinashFI, commitPirate and cdileep23 commits are unrelated dev-branch fixes carried in by a merge. The agent itself is in ee (internal ee#121, all 54 commits by Kartik). It also folds Gemini thinking tokens into completion tokens, which the cost header had left out.
  34. future-agi/future-agi — Kartik’s merged annotation and ClickHouse PRs20 merged PRs, 3–31 Jul 2026: 16 on annotations, 4 on Error Feed and its scanner. Annotation reads to ClickHouse: #1427, #1495, #1604, #1607. Error Feed: #1510, #1644. Memory: #1160, #1434 (annotations), #1373, #1455 (trace scanner). Project scoping: #1565. Queue performance: #1591, #1593, #1831, #1852, #1861, #1865, #1871, #1876, #1878. The link lists all of Kartik’s merged PRs in the repository, not only these 20.
  35. future-agi/future-agi PR #1510 — make Error Feed ClickHouse-native (merged 11 Jul 2026)Every feed read, the deep-analysis worker and the live scanner moved to ClickHouse to survive the tracer Postgres-table drop; proven by dropping the tables in tests and renaming them away on a live stack. Authored by Kartik.
  36. future-agi/future-agi PR #1644 — prune feed ClickHouse reads (merged 18 Jul 2026)Benchmarked on a 10M-row spans table: list 19.7 s → ~150 ms, cluster detail 17 s → ~200 ms, overview 15–17 s → ~200 ms, trends 14–24 s → ~160 ms, traces tab >30 s → ~150 ms. Authored by Kartik.
  37. future-agi/future-agi PR #2979 — grouping, scored evals and causal breadcrumbs (merged 23 Sep 2026)Grouping on by default for eligible projects, with a kill-switch and budget controls; choice, threshold and numeric eval failures eligible for clustering; each finding shows its origin, decisive and symptom steps. Authored by Kartik (21 of 23 commits; atharva-bhange 2). Merged into a stacked branch and released in v1.40.0 (23 Sep 2026); the PR notes quality at scale was still to be verified after deployment.
  38. future-agi/future-agi PR #1495 — ClickHouse-native reads for annotation sources (merged 11 Jul 2026)Annotation reads of trace, span and session data moved to ClickHouse; tenant-gated, fail-closed; lean batched reads; supersedes the drop-safety draft #1214, which guarded the Postgres reads instead of removing them. 575 annotation tests passing across 12 suites. Authored by Kartik.
  39. PyPI Stats — fi-instrumentation-oteltraceAI’s core Python instrumentation package: 14,383 downloads in the month to 26 Sep 2026 (traceai-openai: 11,864).
  40. GitHub — future-agi/traceAI222 stars and 44 forks on 26 Sep 2026.
  41. GitHub — future-agi/future-agiThe open-source platform repository Error Feed and the annotation reads ship in: 2,077 stars and 644 forks on 26 Sep 2026.
  42. future-agi/simulate-sdk PR #1 — Version 0.1.1, the first release (merged 9 Oct 2025)Simulate SDK’s first version, all 20 commits by Kartik from the repository’s initial commit (6 Oct 2025): LiveKit integration, RTC, transcription, call recording, the simulated-customer agent definition, end-call handling. Released as agent-simulate 0.1.1 on PyPI (9 Oct 2025). Kartik has 60 of the repository’s 70 commits (26 Sep 2026).
  43. future-agi/traceAI — Kartik’s merged PRs, including the v1 SDKs (#127–#131) and TypeScript support (#9)All authored by Kartik: C# SDK (#127, 10 of 10 commits), Java SDK (#128, 7 of 7), 31 new TypeScript packages (#129), TypeScript move to gen_ai conventions (#130), 23 new Python instrumentors (#131), merged 23–24 Feb 2026. TypeScript support (#9, merged 20 May 2025): FITracer, register, OpenAI, Anthropic and LangChain instrumentation, 28 of 32 commits (sarthakFuture 4). The v1.0.0 notes say TypeScript grew from 8 packages to 39.
  44. future-agi/future-agi PR #2019 — scanner and cluster-RCA port, deterministic RCA read path (merged 7 Aug 2026)Measured on a live production run: ClickHouse was 551 ms of a five-minute investigation and 88% of wall clock was model turns. The read tool stopped sending the span tree to a cheaper model; it renders budgeted verbatim I/O deterministically, budgeted per trace with failing spans first, plus a 90 s per-turn deadline. Authored by Kartik (21 of 24 commits; 3 ported from hadarishav’s scanner branch).
  45. future-agi/future-agi PR #2942 — Error Feed investigation handoff (merged 23 Sep 2026, released in v1.40.0)Opt-in traces are handed to a separate investigation worker; durable investigation jobs, normalized findings and evidence are stored and read back in Error Feed and cluster RCA; legacy scans are backfilled. Authored by Kartik (32 of 32 commits). In the v1.40.0 release (23 Sep 2026), 47 of 59 commits are Kartik’s and 12 are atharva-bhange’s (grouping jobs, severity and fix-layer assessments).
  46. future-agi/future-agi PR #2186 — gateway traces over OTLP/HTTP with prompts and completions (merged 18 Aug 2026, v1.28.0)An OTLP/HTTP exporter (the otel plugin could only print spans to stdout); bodies behind otel.include_bodies, redacted before truncation; byte-bounded batches; streamed completions assembled; image, embedding, rerank, search and OCR bodies. The stacked #2183, #2187 and #2188 were collapsed into it. Authored by Kartik (11 of 11 commits). It also fixed a runtime fatal (concurrent map read and write) when several post-parallel plugins shared one request context, which took the gateway down with every in-flight request.
  47. future-agi/future-agi PR #2231 — run the plugin pipeline on /v1/messages and Gemini generateContent (merged 21 Aug 2026)Those two handlers never called the plugin engine, so Anthropic-SDK and Google-GenAI-SDK traffic had no span, request log, cost, budget, credits or rate limits. Fixed on all eight paths, with a regression test over all 11 billable handlers. Its review fallout fixed the native Anthropic path hashing every prompt to one exact-cache key (a second request was served a content-less 200 without calling the provider) and the streaming usage tee leaking its goroutines on client disconnect. Authored by Kartik.
  48. npm — @agentcc/client versions0.1.0 published 9 Apr 2026 by azainfi; 1.0.0 published 22 Apr 2026 by nvjkkartik. PyPI agentcc: 0.1.0 on 9 Apr, 1.0.0 on 22 Apr 2026.
  49. Agent Command Center README (future-agi/future-agi, agentcc-gateway)The product’s own description: one OpenAI-compatible API, 15 routing strategies, exact and semantic caching, budgets, quotas and virtual keys, 18 built-in guardrail scanners, Prometheus and OpenTelemetry. It compares itself there with Portkey, Bifrost, LiteLLM and Helicone. Future AGI team product.
  50. Agent Command Center: cross-format translation (agentcc-gateway/internal/translation)The public code. Authorship is from internal PR future-agi-temp#57 (merged 21 Apr 2026, 20 of 20 commits by Kartik), which a visitor can’t open: requests to /v1/chat/completions, /v1/messages and /v1beta/models/* can route to any configured provider.
  51. future-agi/future-agi PR #936: enforce control-plane key expiry on synced keys (merged 18 Jun 2026)Expired keys synced from the Django control plane authenticated indefinitely: expires_at never left Django, so the gateway never saw it. Authored by Kartik (3 of 3 commits).
  52. Future AGI: trace error-analysis agent (futureagi/ee/agenthub/traceerroragent)The public, EE-licensed code, which Error Feed’s error analysis and investigation agent build on. Authorship is from internal PRs agentic-eval#338 and core-backend#1328 (merged 4 Sep 2025; 14 of 16 and 19 of 21 commits by Kartik, the rest gsapra), which a visitor can’t open: four passes over a trace, subtree batching over the token limit, episodic and semantic memory, HDBSCAN clustering.
  53. github.com/future-agi — open-source repositoriesagent-opt, agent-learning-kit, simulate-sdk, agent-command-center-sdk, futureagi-sdk, traceAI.

What isn’t evidence

The Nexus, Centio.AI and Alumni Connect screens are interface studies drawn in 2026 for this site, with sample data. Each project page shows the original next to its study.

The plates on the other easels illustrate an idea: the diarization lanes, the optimizer curve, the error cluster and the rest are drawings, not results. The patent drawing and the Hivemind screenshot are the real things.

The “Break the agent” demo is deterministic, runs in your browser, and is modelled on a bug I wrote about. It is not product output, and its scores are not benchmark results.

Posts in Writing are my own, snapshotted on 2026-09-25. The originals on DEV and Medium are canonical.