Work

mokata

The memory and seatbelt for your AI coding agent.

Spec-driven TDD for AI coding agents. No code is written until the spec passes a completeness gate and every acceptance criterion maps to a failing test. Every durable write to code, memory or config is proposed by the model and approved by a person, out of band, and recorded on a hash-chained audit ledger.

Works with Claude Code, Cursor, Copilot, Codex, Windsurf, Gemini and Aider. Local-first, no telemetry, Apache-2.0.

Try the seatbelt

You are the agent. Story: checkout rejects an empty cart. Take the proper step, or try a shortcut and watch the gate stop it.

Brainstormapproach-approval
Speccompleteness
Testred-before-green
Developspec-scope
Reviewspec-then-quality
Shiphuman-landed

Next step

Brainstorm is open. The agent cannot write implementation until a person approves exactly one approach.

Run-state gates on the agent’s own file writes

approach-approvalblocking
spec-persistedblocking
no-code-without-failing-testblocking
spec-scopewaits for spec

$ mokata init --profile standard --yes

mokata initialized with profile ‘standard’.

$ /brainstorm "checkout rejects an empty cart"

mokata · brainstorm (engaged) two approaches on the table: A raise ValueError on an empty cart B return 0 and log a warning

The spec-persisted, failing-test and memory-write messages are mokata’s published output. The other lines are paraphrased from its docs.

MCP tools: 62
Agent skills: 26
Enforced gates: 9

pip install mokata && mokata setup claude

mokata.ai The 60-second demo Source on GitHub

Liquidity Lock Global Markets

Senior Quant and Head of Engineering

Oct 2022 to now, Bangalore

Designed and implemented the institutional trading platform from scratch, hands-on across database architecture, backend and frontend, on PostgreSQL, Express, React and Node.js.
Own the platform and engineering org behind Liquidity Lock’s institutional trading infrastructure: architecture, team build-out and delivery roadmap.
Set technical direction and hiring strategy for a team building trading, risk and data infrastructure from the ground up.
Operate as the connective layer between trading strategy, engineering execution and business priorities.

NatWest Markets

Desk Quant and Quant Analyst Lead, Senior Vice President

Jan 2020 to Sep 2022

Led the India front office quant analyst teams in Chennai and Bangalore across regulatory projects, fixed income research and desk quant strategy.
Built a unified analytical framework for the fixed income trading, sales and research teams.
Owned relative value indicators and tools for Gilts, EGBs and UK and Euro linkers.
FRTB front office regulatory analysis, methodology testing and validation.
Fixed income research using predictive analysis and machine learning.
Core committee member setting Python development guidelines for the front office. Ran Python and machine learning training.

NatWest Markets

Rates Derivative Strat, Vice President

Sep 2018 to Jan 2020

Set up the Quant Analytics Modelling Team.
Built a Python framework for front office P&L analysis for PLA testing under FRTB, analysing 500k trades over five years to find gaps in risk measures.
Improved the calculation methodology for several risk measures.
Developed and finalised methodologies for market rolling, FX adjustments and CSA curve decompositions.
Wrote Python packages used by trading and risk quants to find P&L gaps and automate reports.

Evalueserve

Index Quants

Dec 2015 to Aug 2018, Gurgaon

Developed a multi-asset index engine as part of a fintech solution for a leading Swiss asset management client.
Index research, development and maintenance for multiple client accounts, in Python and VBA.
Converted multiple pilots into long-term projects.

Quantsbin

Open source, 2019, no longer maintained

An open-source options analytics library for vanilla option pricing, Greeks and derivatives analysis, with 500+ stars on GitHub.

View on GitHub