Skip to content
View amitvijapur's full-sized avatar
💭
building or larping u tell me
💭
building or larping u tell me

Block or report amitvijapur

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
amitvijapur/README.md

AMIT

CS @ Durham · Quant Systems · Agent Infrastructure · Open Source

Visitors LinkedIn Substack Email


I build trading systems, agentic infrastructure, and the routing layers that decide who should do the work — a model, a machine, or a person.


⚡ featured

🥇 Top 5 of 53 — GenAI Fund Agentic AI Build Week 2026, Founder Mode track, built solo

An operating system for a workforce of humans and AI agents. It decides who should do each piece of work — an AI agent, a human, or an agent that proposes and a human who approves. Every task is routed through an interpretable score, every irreversible action is gated behind a signed human approval, and the system learns which workers to trust from judged, human-confirmed outcomes.

Reputation buys autonomy on reversible work, and buys nothing on irreversible work.

Next.js 16 · TypeScript · Supabase · OpenAI · Langfuse · 60 tests passing


A meta-router for Claude Code. It sits above every workflow system in the stack and decides, per task, which system, which specialist, and which effort tier — then logs the decision and learns from the outcome.

A friendly response to Karpathy's LLM Council: multi-model voting is one useful tool, but routing is the harder problem.

Python · Shell · Markdown


A modular backtesting engine in Rust, built on Polars. Strategies are swappable behind a Strategy trait, execution is realistic (next-bar fills, commission, slippage), and it ships with Kelly position sizing, grid-search parameter optimisation, and walk-forward validation to catch overfitting. Includes a Rust-versus-pandas benchmark.

Rust · Polars · clap


A live Bitcoin trading simulator. Streams real-time price from the Binance WebSocket API, computes SMA, EMA and RSI on the client, and simulates market and limit orders with full portfolio and P&L tracking.

Node.js · Express · vanilla JS · Chart.js


🔧 merged into other people's code

Five PRs merged in three weeks, all into tools I use daily. Each one started as a bug I hit myself, was reproduced before it was fixed, and shipped with regression tests.

project what landed
Understand-Anything 77.5k A PostToolUse hook read its payload from a stale env var instead of stdin, so it silently saw nothing
Scrapling 72.6k The response cache dropped cookies on browser-engine responses, breaking session reuse
last30days 57.3k A silent fallback masked YouTube transcript failures, so a broken fetch looked identical to an empty result
fastmcp 3.2k MCP resource subscriptions — a new feature, shipped in v4.8.0
toolport 108 Witsy MCP client support, credited by the maintainer in the README

In review: two PRs into mcp-atlassian (★5.7k) closing a space-filter bypass across the Confluence tools. The allowlist was checked against the space you named, but not against the parent page the write actually landed under — so the page was created in a filtered space and the error only surfaced afterwards.


🏆 hackathons & build weeks

🥇 GenAI Fund Agentic AI Build Week 2026 — Ho Chi Minh City

Top 5 of 53 · Founder Mode track · Problem P4, "Human-AgentOS" · built solo

Shipped warrant in a single build day: a closed loop for human/AI workforce allocation. A task arrives with capability requirements and a reversibility flag; a router scores every registered worker on capability match, cost, latency and evidenced reliability; irreversible actions structurally require human authority regardless of reputation; work executes for real, outcomes are judged, and the next identical task routes differently.

Simulated workload, real executions — every execution, score and posterior update is recorded in an append-only evidence log.


🛠 stack

Python TypeScript JavaScript Rust C C++ Java SQL Solidity Bash

React Next.js Node.js Supabase Polars Pandas NumPy TensorFlow scikit-learn Git


📐 background

CS @ Durham University — going into second year, deep in quant systems, algorithmic trading and agent infrastructure. Building real products alongside the degree, not after it.

Before Durham: 3rd Sergeant, Singapore Army (Military Police) — commanded a 10-man team in high-pressure, compliance-driven environments. Learned to think in systems and manage risk before I knew what those words meant in trading.


📝 writing

I write about crypto, tokenomics, quant and emerging tech on Substack.

Latest: Crypto-Currencies & Tokenomics: Their Relevance in the Next Decade


🎯 outside the terminal

long distance running  ·
street photography     ·
specialty coffee       ·
guitar                 ·

Popular repositories Loading

  1. cortex cortex Public

    Meta-router for coding agents — built for Claude Code, runs on Cursor, Codex, Gemini CLI, Aider & Windsurf. Sits above every workflow system and routes each task. A friendly response to Karpathy's …

    HTML 5

  2. btc-trading-simulator btc-trading-simulator Public

    Web-based Bitcoin market analysis platform with real-time data ingestion, technical indicators, and time-series visualization.

    JavaScript

  3. amitvijapur amitvijapur Public

  4. polars polars Public

    Forked from pola-rs/polars

    Extremely fast Query Engine for DataFrames, written in Rust

    Rust

  5. orchestrator orchestrator Public

    HTML

  6. claude-skills claude-skills Public

    HTML