- 👨🏻💻 alias: @anxkhn
- 💼 software engineer @ microsoft | ex- hackerrank (yc s11) | fampay (yc s19) | general mills
- ☀️ gsoc '25 @ google deepmind | gsoc '26 mentor @ circuitverse
- 💻 currently tinkering with voice and llms
- 🔎 primarily into backend engineering and gen ai
- 📧 reach out:
anxkhn (at) duck (dot) com→ click to email - 🎉 socials: @anxkhn everywhere → twitter / linkedin
🚀 some stuff I've built:
- 🎓 CertiSure: B2B certification platform w/ bulk generation + QR validation
- 🗺️ AuraTrips: AI-based travel itinerary generator using LLaMA + RAG
- 🔐 CodeClip: Password-protected snippet sharing + LLM-based code explainer
- 📦 FFpy / FlashFlask / OpynGPT: Dev-first PyPI tools (48K+ downloads)
🏆 highlights:
- 🥈 winner in 6+ hackathons
- 📜 published LLM research @ CML 2025 Springer LNNS
- 🏅 recipient of Principal's Excellence Award @ TSEC
🗂️ check out my portfolio and resume 👀
🟢 open to working on exciting projects in applied ai, backend & software engineering · let's talk →
| Programming: |
|
| Frontend: |
|
| UI Libraries: |
|
| Backend: |
|
| Database: |
|
| AI / ML: |
|
| LLM & Vector Infra: |
|
| Tools: |
|
my open source contributions
I like building products and making them better. A lot of that happens in the open. Right now that is 523 contributions across 95 repositories, mostly on projects I care about or can usefully improve.
| repository | about | contributions | stars |
|---|---|---|---|
| ollama/ollama | run open-source and frontier models locally | 2 PRs | 182k |
| unslothai/unsloth | local UI to run and train LLMs and diffusion models | 7 PRs | 77k |
| docling-project/docling | document parsing pipeline for gen AI | 14 PRs | 68k |
| mem0ai/mem0 | universal memory layer for AI agents | 1 PR | 66k |
| BerriAI/litellm | unified API to call 100+ LLM providers | 1 PR | 60k |
| ComposioHQ/composio | toolkits, auth, and workbench for AI agents that take action | 6 PRs | 30k |
| 78/xiaozhi-esp32 | ESP32 voice chatbot that talks to LLMs and controls devices over MCP | 1 PR | 30k |
| openai/openai-agents-python | OpenAI's Python framework for multi-agent workflows | 5 PRs | 30k |
| deepset-ai/haystack | AI orchestration framework for RAG, agents, and LLM apps | 1 PR | 27k |
| promptfoo/promptfoo | OpenAI's LLM eval, red-teaming, and prompt testing toolkit | 6 PRs | 26k |
| comet-ml/opik | debug, evaluate, and monitor LLM apps and agent workflows | 2 PRs | 22k |
| google/adk-python | Google's Agent Development Kit for building and evaluating agents | 18 commits | 22k |
| SWE-agent/SWE-agent | autonomous agent that fixes GitHub issues with your LM | 6 PRs | 20k |
| googleapis/mcp-toolbox | Google's open-source MCP server for databases | 9 PRs | 17k |
| pipecat-ai/pipecat | open-source framework for voice agents and realtime AI | 6 PRs | 16k |
| ollama/ollama-python | official Python library for Ollama | 2 PRs | 11k |
| omnigent-ai/omnigent | open-source AI agent framework and meta-harness | 22 PRs | 10k |
| NVIDIA/garak | NVIDIA's LLM vulnerability scanner | 7 PRs | 9k |
| k8sgpt-ai/k8sgpt | AI-powered Kubernetes troubleshooting CLI | 19 PRs | 8k |
| kagent-dev/kagent | cloud-native agentic AI for Kubernetes | 10 PRs | 4k |
| agent-of-empires/agent-of-empires | manage multiple coding agents from TUI or web | 1 PR | 3k |
| coddingtonbear/obsidian-local-rest-api | local REST API and MCP server for an Obsidian vault | 1 PR | 3k |
| UKGovernmentBEIS/inspect_ai | framework for large language model evaluations | 5 PRs | 3k |
| org2AI/ORG2 | system of record for how agents build software | 1 PR | 3k |
| yctimlin/mcp_excalidraw | MCP server for creating and editing Excalidraw diagrams | 1 PR | 2k |
| a2aproject/a2a-python | Python library for running agents as A2A servers | 1 PR | 2k |
| google-deepmind/concordia | library for generative agents in simulated worlds | 2 PRs | 2k |
| google-deepmind/mujoco_warp | GPU-optimized MuJoCo physics simulator from DeepMind | 2 PRs | 1k |
| sipyourdrink-ltd/bernstein | deterministic orchestrator for CLI coding agents | 1 PR | 1k |
| johannesjo/parallel-code | run Claude Code, Codex, and Gemini in parallel worktrees | 1 PR | 1k |
| dapr/dapr-agents | autonomous AI agents with Dapr workflow and telemetry | 11 PRs | 751 |
| a2aproject/a2a-js | TypeScript SDK for A2A clients and servers | 6 PRs | 629 |
| google-deepmind/simply | minimal JAX research codebase for LLMs | 1 PR | 577 |
| AbdelStark/awesome-typesafe-jev | community field guide to TypeSafe's Jev typed judgments | 2 PRs | 539 |
| mco-org/mco | CLI orchestration for AI coding agents in parallel | 1 PR | 528 |
| a2aproject/a2a-go | Go library for A2A clients and servers | 2 PRs | 475 |
| llm-d/llm-d-router | intelligent router entry point for LLM inference requests | 9 PRs | 364 |
| repository | about | contributions | stars |
|---|---|---|---|
| react/react | library for web and native user interfaces | 4 PRs | 251k |
| torvalds/linux | Linux kernel source tree | 7 commits | 250k |
| astral-sh/uv | extremely fast Python package and project manager | 2 PRs | 90k |
| rails/rails | full-stack web framework for Ruby | 2 PRs | 59k |
| reflex-dev/reflex | build web apps in pure Python | 11 PRs | 29k |
| kucherenko/jscpd | copy/paste detector for source code | 1 PR | 6k |
| repository | about | contributions | stars |
|---|---|---|---|
| prometheus/prometheus | monitoring system and time series database | 4 PRs | 66k |
| thanos-io/thanos | highly available Prometheus with long-term storage | 1 PR | 14k |
| cortexproject/cortex | horizontally scalable multi-tenant Prometheus | 1 PR | 6k |
| perses/perses | CNCF sandbox for observability visualization | 24 PRs | 2k |
| repository | about | contributions | stars |
|---|---|---|---|
| cypress-io/cypress | end-to-end testing for anything that runs in a browser | 11 PRs | 51k |
| apify/crawlee | web scraping and browser automation for Node.js | 13 PRs | 26k |
| Skyvern-AI/skyvern | AI browser agent for web workflows | 2 PRs | 23k |
| e2b-dev/E2B | open-source secure sandboxes for enterprise-grade agents | 3 PRs | 14k |
| apify/crawlee-python | web scraping and browser automation for Python | 24 PRs | 10k |
| dagger/container-use | isolated container environments for coding agents | 1 PR | 4k |
| repository | about | contributions | stars |
|---|---|---|---|
| apache/airflow | platform to author, schedule, and monitor workflows | 4 PRs | 47k |
| apache/arrow | columnar in-memory format for fast analytical data | 1 PR | 17k |
| fivetran/great_expectations | data quality and validation framework | 3 PRs | 12k |
| sqlfluff/sqlfluff | modular SQL linter and auto-formatter | 15 PRs | 10k |
| apache/iceberg | open table format for large analytic datasets | 4 PRs | 9k |
| dlt-hub/dlt | Python data load tool (dlt) for easy data loading | 3 PRs | 6k |
| apache/calcite | dynamic data management framework | 3 PRs | 5k |
| unitycatalog/unitycatalog | open multi-modal catalog for data and AI | 3 PRs | 4k |
| SQLMesh/sqlmesh | scalable data transformation framework, dbt-compatible | 9 PRs | 3k |
| apache/parquet-java | Apache Parquet columnar format for Java | 3 PRs | 3k |
| apache/polaris | open catalog for Apache Iceberg | 6 PRs | 2k |
| openGemini/openGemini | CNCF distributed time-series database | 9 PRs | 1k |
| apache/iceberg-python | PyIceberg, Python library for Apache Iceberg tables | 13 PRs | 1k |
| repository | about | contributions | stars |
|---|---|---|---|
| kestra-io/kestra | event-driven orchestration and scheduling platform | 14 PRs | 28k |
| dapr/dapr | portable runtime for distributed cloud and edge apps | 7 PRs | 26k |
| rook/rook | storage orchestration for Kubernetes | 12 PRs | 14k |
| higress-group/higress | AI-native API gateway | 1 PR | 9k |
| tektoncd/pipeline | cloud-native CI/CD pipeline resource for Kubernetes | 10 PRs | 9k |
| kubevela/kubevela | modern cloud-native application platform | 6 PRs | 8k |
| flyteorg/flyte | dynamic AI workflow orchestration for data and models | 1 PR | 8k |
| cloud-custodian/cloud-custodian | rules engine for cloud security, cost, and governance | 11 PRs | 6k |
| kserve/kserve | standardized AI inference platform on Kubernetes | 1 PR | 6k |
| volcano-sh/volcano | cloud-native batch system under CNCF | 2 PRs | 6k |
| strimzi/strimzi-kafka-operator | Apache Kafka on Kubernetes | 3 PRs | 6k |
| kgateway-dev/kgateway | cloud-native API gateway and AI gateway | 1 PR | 6k |
| dragonflyoss/dragonfly | P2P data distribution and image acceleration | 5 PRs | 3k |
| open-feature/flagd | feature flag daemon with a Unix philosophy | 10 PRs | 1k |
| openebs/dynamic-localpv-provisioner | dynamic node-local persistent volumes for Kubernetes | 8 PRs | 212 |
| kubeflow/sdk | Python SDK to run AI workloads on Kubernetes | 3 PRs | 149 |
| repository | about | contributions | stars |
|---|---|---|---|
| TheAlgorithms/C | educational algorithms and data structures in C | 1 PR | 22k |
| fastapi/sqlmodel | SQL library for Python, with types shared by Pydantic and SQLAlchemy | 1 PR | 18k |
| chaitanyagiri/munder-difflin | local multi-agent harness | 1 PR | 8k |
| open-telemetry/opentelemetry-collector | collector that receives, processes, and exports traces, metrics, and logs | 1 PR | 8k |
| google-deepmind/open_spiel | research framework for reinforcement learning in games | 2 PRs | 6k |
| CircuitVerse/CircuitVerse | online digital logic circuit simulator | 2 PRs | 1k |
| code100x/daily-code | daily coding practice platform | 2 PRs | 956 |
| google/sam | private network where AI agents publish and call each other's tools | 1 PR | 947 |
| 0xku/leetcode-compensation | India software engineering salaries from LeetCode compensation | 4 PRs | 417 |
| codinasion/codinasion | open-source collaboration and learning projects | 4 PRs | 318 |
| fossunited/fossunited | FOSS United community platform | 1 PR | 215 |
| google-deepmind/jax_privacy | differentially private training for models in JAX and Keras | 1 PR | 198 |
| fayazara/Kaze | local speech-to-text app | 1 PR | 176 |
Feel free to refer to my personal code repositories responsibly.
All repositories are licensed under GPL v3.0.
All code must be disclosed under a GPL v3.0-compatible license.
Read more about the license here.