Digital résumé
Om Jee Mishra
Senior Software Developer
Multi-agent RAG, real-time voice, and the infrastructure under it — with a heavy bias toward building in the open.
I'm a Senior Software Developer with 3+ years shipping production systems at the intersection of full-stack engineering and applied AI. I architect multi-agent RAG platforms where a single agent runtime drives both streaming chat and realtime voice over the same tools, memory, and knowledge base — grounded in vector search, persistent conversational memory, and live CRM/EHR context, with server-authoritative workflows, prompt-injection defense, and per-turn LLM evals on top. I care about latency budgets, eval harnesses, and the boring reliability work that lets a team ship without rewriting on Monday — and I do a lot of that work in the open, contributing to RedPlanetHQ's Town and CORE.
Open source — built in the open
Open source is where I do my most deliberate engineering — small, well-tested, reviewable PRs against real production codebases. Two projects I care about most, with every merged PR one click away:
RedPlanetHQ/Town
Discord, but you walk around a pixel town — where the NPCs have skills
A pixel-world where AI NPCs walk around, chat, and act on real connected tools. My work made Town cheaper to self-host, gave NPCs real capabilities through CORE, and added the project's first test suite.
- Added Ollama as a third LLM provider (Ollama Cloud, OpenAI-compatible) so Town runs without a paid Anthropic/OpenAI key — with matching town-cli support and a fix so streamed Ollama chats correctly debit aura (#37, #45, #47)
- Wired CORE integrations into NPCs: signed-in visitors can lend an NPC their own CORE tools for a conversation, with per-person token routing so one NPC acts on two accounts safely (#72, merged via #73; owner-side panel in #71)
- Bootstrapped testing — added Vitest and 61 unit tests over security-relevant modules (prompt sanitisation, town-code, events) (#34)
- Fixed onboarding by adding the missing .env.example files the setup guide referenced (#20)
- 7 pull requests, 5 landed in main — spanning provider support, agent capabilities and tests
RedPlanetHQ/C.O.R.E.
Your Personal AI OS
A shared memory graph and MCP layer for AI agents. I contributed read-only tools, self-hosting fixes, and a deterministic test suite over previously untested agent internals.
- Shipped 16 read-only MCP tools across two features — a full Postman integration (14 tools) and skills-as-tools (list_skills / get_skill) for coding agents
- Unblocked self-hosted deployments end-to-end: fixed four defects on the local-Ollama path with zero change to the hosted OpenAI / Anthropic / Google providers
- Fixed production bugs across API-key deletion, multi-step chat rendering and Ghost HTML publishing, and closed an audit gap by populating IntegrationCallLog.source for API-triggered actions
- Added 62 fast, deterministic unit tests over previously untested agent helpers (action-plan parsing, tool-result truncation, history prep)
- 9 pull requests, all merged — roughly 4.1k lines contributed
Experience
Senior Software Developer · HexaHealth ↗
Architecting HealthGpt, the company's AI gateway — one agent runtime powering both a streaming text chatbot and a realtime voice assistant over shared tools, memory, RAG, and live patient context.
- Architected HealthGpt, the AI gateway — one Mastra agent runtime powering both a streaming text chatbot (SSE) and a realtime voice assistant (WebSocket ↔ Gemini Live) over shared tools, memory, and RAG
- Built namespaced Pinecone retrieval over treatments, hospitals, doctors, and uploaded medical PDFs, with an online ingestion pipeline and a query-rewriting symptom checker
- Hydrated each conversation with live CRM/EHR context from MySQL via LLM summarization, and shipped a server-authoritative, restart-safe appointment-booking engine that never fabricates a lead
- Hardened and instrumented both channels — prompt-injection defense, WebSocket rate guards, transcript-leak sanitization, sampled LLM-as-judge medical scorers, and end-to-end Langfuse tracing — with DB-driven, hot-swappable agent prompts, models, and tools
Software Developer · Wasserstoff RJ Innovations ↗
Owned the backend for Lit Law — microservices, RAG pipelines, real-time collaboration and payments in legal-tech.
- Built 40+ REST APIs over a gRPC microservices architecture (Node/Express, PostgreSQL, Redis, Drizzle) at 99.9% uptime and 2.3× throughput
- Shipped RAG for legal contract generation with custom embeddings + Pinecone — 48% retrieval latency reduction, scaling to 1,500+ concurrent users
- Delivered real-time collaboration (presence, concurrent editing) over SSE with a Next.js SSR front end
- Integrated Razorpay/Cashfree with 100% reliability across 500+ monthly signings; migrated 8,000+ posts across CMSs with zero data loss
Stack
Writing
I write about the systems I ship — with a heavy focus on open source and the infrastructure decisions that decide whether it survives production.
Education
GL Bajaj Group of Institutions
B.Tech, Computer Science Engineering