Skip to content
View goutamadwant's full-sized avatar
🎯
Focusing
🎯
Focusing
44 followers · 218 following
  • Livermore, California
  • 23:48 (UTC -07:00)

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Highlights

Block or report goutamadwant

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
goutamadwant/README.md

Hi, I'm Goutam

Principal Engineer building agent reliability tooling, AI infrastructure, and cloud-native distributed systems.

GitHub Developer Program member | AI agents | MCP security | LLM infrastructure | AWS | Java | Python

Python Java AWS Spring AI Agents LLM Systems Agent Testing MCP RAG Research

I work on open-source tools for testing, securing, and operating AI systems. My focus is practical research: methods that can be tested, reproduced, and used by engineers building real platforms.

Current Open Source Projects

Agent Testing & MCP Security

  • 🧪 toolcallcheck - offline regression tests for tool-calling agents.
  • 🔌 mcp-pool - async connection pooling for MCP client sessions.
  • 🛡️ mcp-shield-pii - PII detection and reversible redaction for MCP traffic.
  • 🚦 mcp-egress-guard - policy enforcement and audit logs for MCP egress.

LLM Infrastructure

  • 🧭 kvfleet - KV-cache-aware routing for self-hosted and hybrid LLM fleets.
  • 🧬 vectormigrate - safer embedding and vector-index migrations.
  • 🧩 promptspecj - OpenAPI-style prompt contracts for Java and Spring AI.

Developer & Data Tools

  • 📈 bigocheck - zero-dependency empirical complexity checks.
  • ⚡ pdperf - static lints for slow Pandas anti-patterns.
  • 🏗️ pydanticforge - infer Pydantic v2 models from evolving JSON streams.
  • ✨ schemaglow - schema diff and contract-drift detection.
  • 🗺️ tracemap - terminal and web visualization for traceroute data.

Research Paper Implementations

Research & Engineering Focus

  • Agent reliability: deterministic tool-call testing, privacy, and egress policy.
  • AI infrastructure: LLM routing, MCP session management, and vector migration.
  • Developer tooling: prompt contracts, complexity checks, static analysis, and schema drift.
  • Cloud-native systems: reliable services, event-driven platforms, and operational automation.

Collaboration

I am interested in focused open-source work around agent security, AI infrastructure, developer productivity, and cloud-native AI platforms.

GitHub: github.com/goutamadwant

Pinned Loading

  1. bigocheck bigocheck Public

    Zero-dependency empirical Big-O complexity checker for Python with CLI, assertions, and pytest integration

    Python 2

  2. rag-evidence-coverage-evaluator rag-evidence-coverage-evaluator Public

    A comprehensive framework for evaluating evidence coverage and faithfulness in RAG systems

    Python 1

  3. rag-chain-of-logic-coverage rag-chain-of-logic-coverage Public

    Official implementation of CoL-CE: A framework for evaluating reasoning validity in RAG systems

    Python 1

  4. mcp-shield-pii mcp-shield-pii Public

    🛡️ Real-time PII redaction proxy for MCP (Model Context Protocol) — detects and masks 23 entity types before they reach the LLM. Drop-in privacy layer for Claude Desktop with zero-latency regex + N…

    Python

  5. promptspecj promptspecj Public

    OpenAPI-style prompt contracts for Java and Spring AI.

    Java

  6. tracemap tracemap Public

    Modern traceroute visualization for the terminal and the web. Table-first (MTR-style) output, interactive TUI, HTML/SVG maps, ASN + GeoIP enrichment, replay, diff, and privacy-aware design.

    Python