Skip to content
View gaurav0107's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report gaurav0107

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
gaurav0107/README.md
┌─────────────────────────────────────────────────────────────┐
│  GAURAV DUBEY · Senior Engineer                             │
│  Expedia Group · Gurgaon, India · ↑ since 2022              │
└─────────────────────────────────────────────────────────────┘

I build agentic systems that catch fraud before it ships — LLMs orchestrated through deterministic graphs, grounded in policy, and observable enough to put on call.

11 years in. Java & distributed systems → Python & ML platforms → now full-time on agent infrastructure.


Featured

A workbench for prompt iteration. Edit a prompt, sweep it across a real dataset, let a judge model score the result, accept the suggested edits, promote the winner. The same engine runs in CI to gate regressions.

TypeScript · v2.2.1 · single-file binary, local-first

Autonomous open-source contribution plugin for Claude Code. Orchestrates six specialist agents — issue selection, repo profiling, planning, building, merge-probability scoring, comment resolution — without hand-holding.

Claude Code plugin · v0.4.1 · seven merged releases


Open-source contributions

last synced · 2026-11-01

┌─ impact ──────────────────────────────────────────────────────────────┐
│ 84 merged  ·  23 open  ·  2.5M⭐ reached
│          █▃▁ ▁    ▄█▁  ▁█  ▄    prs over last 30 days
└───────────────────────────────────────────────────────────────────────┘
repository ⭐ merged open latest title
obra/superpowers 310k #1987 #2504 fix(codex): fall back to sha256sum when shasum is unavailable
affaan-m/ECC 294k #3748 #3669 #3601 #3562 #3560 #2606 #2577 #2491 #2490 #2488 #2466 #2429 #2413 #2401 #2399 #2386 #2374 #2373 #2372 #2369 #2339 #2177 #2163 #2161 #2159 #2134 #2041 #1701 #1682 #1669 #1490 — fix(hooks): keep inline resolver backslash-free so hooks parse on W...
huggingface/transformers 168k #45611 — Raise clear error for problem_type="single_label_classification" wi...
denoland/deno 108k #36321 #37012 fix: strip leading UTF-8 BOM from .env and .npmrc files
google-gemini/gemini-cli 108k #25822 — fix(cli): add missing response key to custom theme text schema
ant-design/ant-design 100k #58551 #58241 #59550 fix(Table): keep selection column width in virtual mode
unslothai/unsloth 78k #7156 #7113 #7082 — Studio: add option to disable the in-memory API monitor
headroomlabs-ai/headroom 78k #1513 #4506 #4504 #4497 fix(proxy): keep Gemini memory context on entries with non-text parts
tesseract-ocr/tesseract 77k #4563 — Fix crash when LSTM is missing in disabled-legacy build (#4448)
apache/superset 75k #42489 #42220 — fix(core): stop discarding API errors that quote an HTML tag
mem0ai/mem0 68k #5202 — fix(vector_stores): pass namespace as top-level kwarg to UpstashVec...
ZhuLinsen/daily_stock_analysis 67k #2368 — fix: use full English stock analysis prompt templates when REPORT_L...
starship/starship 60k #7497 #7495 docs(preset): add Void Linux symbol to catppuccin-powerline
go-gitea/gitea 58k #38479 — fix(packages): serve noarch Alpine index for any requested architec...
aaif-goose/goose 56k #13239 #13248 #13242 feat(cli): change thinking effort mid-session with /model --effort
run-llama/llama_index 52k #21891 — fix(openrouter): support llama-index-llms-openai-like 0.7
ClickHouse/ClickHouse 50k #106916 — Common: mask sensitive data on Exception::addMessage
DeusData/codebase-memory-mcp 47k #2777 #2769 #2764 #2760 #2754 #2752 #2746 — fix(daemon): log the effective auto_index_limit in daemon.autoindex...
apache/airflow 47k #65685 — Honor AUTH_ROLE_PUBLIC in FastAPI API server
LibreChat-AI/LibreChat 46k #13171 #12825 #14415 📧 fix: Add .msg (application/vnd.ms-outlook) Support to File Upload
mitmproxy/mitmproxy 46k #8326 #8294 #8293 #8280 proxy: bracket IPv6 literals in upstream CONNECT authority
HKUDS/LightRAG 40k #3498 — 🐛 fix(api): stop the ollama bracket prompt from corrupting the query
koalaman/shellcheck 40k #3560 #3558 — fix(SC2312): treat echo as deliberately handling the return value
keycloak/keycloak 37k #50809 #50429 Honor configured admin realm in ClientManager.isInternalClient
SeleniumHQ/selenium 34k #17567 — [rust] honor --browser-version in Selenium Manager Electron driver ...
conductor-oss/conductor 32k #1239 — fix(rest): log 4xx client exceptions at WARN instead of ERROR
Lightning-AI/pytorch-lightning 31k #21686 #21796 #21791 #21759 fix: log the convenience epoch metric once per step (#20902)
better-auth/better-auth 30k #10368 #10383 fix(session): use authoritative session reads in token and delete-a...
nrwl/nx 29k #36397 #36485 fix(core): mark all projects affected when a global package is not ...
envoyproxy/envoy 29k #45510 — docs: remove broken Ubuntu noble install instructions
reflex-dev/reflex 28k #6776 #7670 #7668 #7631 fix(hosting-cli): fail cloud config when PyYAML is missing
mlflow/mlflow 28k #23488 — Support optimizing chat-type prompts in optimize_prompts
oxc-project/oxc 23k #23909 #23015 #22752 #27578 fix(linter/prefer-each): resolve test functions through their imports
mochajs/mocha 22k #6016 #6120 feat: print each error within AggregateErrors
lima-vm/lima 22k #5165 #5090 — shell: clean up stale ssh.sock on --reconnect when the master is al...
pydantic/pydantic-ai 20k #5815 #5681 — Auto-enable Anthropic Files API beta when messages contain Uploaded...
langchain4j/langchain4j 13k #5272 — Skills: add DefaultFileSystemSkill.toBuilder() and round-trip tools...

Sorted by upstream star count. Closed-unmerged PRs skipped. · All open PRs + month-by-month opened/merged →


Now

  • Role — Senior Engineer at Expedia Group, on the Fraud & Risk platform team
  • Building — multi-agent fraud reasoning over LangGraph + MCP
  • Shipped — privacy-preserving LLM gateway with three-tier tokenisation, eval-gated in CI
  • Open to — collaboration on agent infrastructure, eval tooling, MCP servers

Stack

  AI       LangGraph · LangChain · MCP SDK · FastAPI · Pydantic · Presidio · spaCy
  Models   Bedrock · SageMaker · Claude · OpenAI · Groq · Ollama · OpenRouter
  Data     PostgreSQL · DynamoDB · Redis · Elasticsearch · Kafka · Airflow
  Core     Java · Python · Golang · TypeScript · AWS · Docker · K8s · Vault
  Crypto   HKDF · HMAC-SHA256 · CRC8 · per-conversation key derivation
  Eval     LangSmith · OpenTelemetry · Grafana · property-based · golden sets

Principles

  • Benchmarks over vibes. Datastores picked with IOPS and $/hr; LLM routes picked with eval numbers.
  • Security is the first tenet, not the last. Name the threats, name the controls.
  • Entity thinking. If you're debugging individual events, you're already behind the fraud ring.

Contact

visits

Pinned Loading

  1. gaurav0107 gaurav0107 Public

    Profile README

    Shell 2 1

  2. rubric rubric Public

    Prompt Finetuning framework

    TypeScript 2

  3. superhuman superhuman Public

    Autonomous open-source contribution agent for Claude Code & Codex. A multi-agent harness that picks an issue, writes the fix, scores its own pull request on a 10-dimension merge-probability rubric,…

    Shell 5 3

  4. langprobe/langprobe langprobe/langprobe Public

    Python 2 1