┌─────────────────────────────────────────────────────────────┐
│ 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.
|
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 |
last synced · 2026-10-01
┌─ impact ──────────────────────────────────────────────────────────────┐
│ 68 merged · 12 open · 2.2M⭐ reached
│ █ prs over last 30 days
└───────────────────────────────────────────────────────────────────────┘
| repository | ⭐ | merged | open | latest title |
|---|---|---|---|---|
| obra/superpowers | 293k | #1987 | — | test: realign antigravity + pi mapping assertions with pruned refer... |
| affaan-m/ECC | 270k | #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(continuous-learning-v2): warn when the observer never survives ... |
| huggingface/transformers | 166k | #45611 | — | Raise clear error for problem_type="single_label_classification" wi... |
| denoland/deno | 108k | #36321 | — | fix(ext/node): apply backpressure in Readable.toWeb() |
| google-gemini/gemini-cli | 107k | #25822 | #28183 | fix(vscode-ide-companion): preserve terminal focus when closing dif... |
| ant-design/ant-design | 99k | #58551 #58241 | — | fix(Typography): inherit font size in editable textarea |
| unslothai/unsloth | 77k | #7156 #7113 #7082 | — | Studio: add option to disable the in-memory API monitor |
| tesseract-ocr/tesseract | 76k | #4563 | — | Fix crash when LSTM is missing in disabled-legacy build (#4448) |
| apache/superset | 74k | #42489 #42220 | — | fix(core): stop discarding API errors that quote an HTML tag |
| headroomlabs-ai/headroom | 74k | #1513 | — | fix(proxy): retry passthrough on transient upstream connection close |
| mem0ai/mem0 | 66k | #5202 | — | fix(vector_stores): pass namespace as top-level kwarg to UpstashVec... |
| ZhuLinsen/daily_stock_analysis | 65k | #2368 | — | fix: use full English stock analysis prompt templates when REPORT_L... |
| go-gitea/gitea | 58k | #38479 | — | fix(packages): serve noarch Alpine index for any requested architec... |
| run-llama/llama_index | 52k | #21891 | #22371 | refactor(core): deduplicate SimpleDirectoryReader load_file/aload_file |
| ClickHouse/ClickHouse | 50k | #106916 | — | Common: mask sensitive data on Exception::addMessage |
| apache/airflow | 47k | #65685 | — | Honor AUTH_ROLE_PUBLIC in FastAPI API server |
| mitmproxy/mitmproxy | 45k | #8326 #8294 | #8293 #8280 | proxy: bracket IPv6 literals in upstream CONNECT authority |
| LibreChat-AI/LibreChat | 45k | #13171 #12825 | #14415 | 📧 fix: Add .msg (application/vnd.ms-outlook) Support to File Upload |
| HKUDS/LightRAG | 39k | #3498 | — | 🐛 fix(api): stop the ollama bracket prompt from corrupting the query |
| 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 | — | fix(init): declare RadixThemesPlugin in default rxconfig template |
| mlflow/mlflow | 28k | #23488 | — | Support optimizing chat-type prompts in optimize_prompts |
| oxc-project/oxc | 22k | #23909 #23015 #22752 | — | fix(linter/unicorn/prefer-at): skip object numeric-key access |
| 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.
- 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
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
- 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.
- Email — gauravdubey0107@gmail.com
- LinkedIn — linkedin.com/in/gaurav1792
- GitHub — @gaurav0107
