Skip to content
View NithiN-1808's full-sized avatar
1 follower · 0 following

Block or report NithiN-1808

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
NithiN-1808/README.md

Hi, I'm Nithin 👋

I build open-source tooling for agentic AI systems — the infrastructure layer that makes AI agents more reliable, testable, and production-ready.

Currently based in Bengaluru 🇮🇳 | Open to AI/ML engineering roles

LinkedIn PyPI Email

🔧 What I build

I focus on the gap between prototype agents and production agents — fault tolerance, search-based reasoning, and testing infrastructure for LLM-powered systems.

📦 Published Packages

agentchaos-tools — Chaos testing for agentic AI

PyPI version Python

Fault injection hooks for openai-agents-python. Simulate tool failures, latency spikes, and corrupted outputs to verify your agent handles real-world conditions gracefully.

from agentchaos import FaultInjectionHooks, ToolFault, FaultType

hooks = FaultInjectionHooks(
    faults=[
        ToolFault(tool_name="web_search", fault_type=FaultType.EXCEPTION, rate=0.5),
        ToolFault(tool_name="calculator", fault_type=FaultType.LATENCY, latency_seconds=2.0),
    ],
    seed=42,
)
result = await Runner.run(agent, "Search for something", hooks=hooks)
hooks.report()
# agentchaos report — 1 fault(s) triggered:
#   1. [EXCEPTION] tool='web_search'
pip install agentchaos-tools

smolagents-lats — Tree search reasoning for smolagents

PyPI version Python

Implementation of LATS (Language Agent Tree Search) for HuggingFace's smolagents. Replaces the linear ReAct loop with a UCT-guided search tree — agents expand branches, score them, and reflect on failed paths before backtracking.

from smolagents_lats import LATSAgent

agent = LATSAgent(tools=[], model=model, n_branches=3, max_depth=4)
result = agent.run("What is the 10th Fibonacci number?")
pip install smolagents-lats

🛠 Tech Stack

Python OpenAI HuggingFace LangChain AWS Docker Git

AI / Agents: openai-agents-python · smolagents · crewAI · strands-agents · LangGraph
Testing & Reliability: chaos engineering · fault injection · pytest
Concepts: ReAct · LATS · MCTS · multi-agent systems · RAG

📊 GitHub Stats

🤝 Let's connect

I'm actively building in the agentic AI space and always open to interesting conversations, collaborations, or opportunities.

📬 [nithinr1808@gmail.com] · LinkedIn

Pinned Loading

  1. agentchaos agentchaos Public

    Chaos testing for agentic AI — fault injection hooks for openai-agents-python

    Python

  2. smolagents-lats smolagents-lats Public

    Python

  3. agentic-financial-rag agentic-financial-rag Public

    Agentic RAG pipeline over SEC 10-K filings — CrewAI multi-agent orchestration, LLaMA-3 (Ollama), FAISS + ChromaDB hybrid retrieval, RAGAS evaluation, FastAPI + Streamlit. Fully local, no API keys n…

    Python

  4. Seller-Support-Multi-Agent-System Seller-Support-Multi-Agent-System Public

    A multi-agent system for answering Amazon Seller Central queries using Strands Agents, LangGraph, MCP, ChromaDB, and Ollama for fully local LLM inference.

    Python

  5. codearch codearch Public

    🏗️ Drop any GitHub URL → 4 AI agents map the codebase → get an elite onboarding report. Built with LangGraph, Ollama & FastAPI. 100% local, no API keys.

    HTML