> ask nyk anything_

// about

Co-Founder & CEO at Builderz. I ship AI agent infrastructure, DeFi systems, and developer tooling across Solana and beyond. Obsessed with context engineering, high-frequency trading systems, and building things that compound.

155+repos
2.5K+stars
32+products
200+followers
Agent InfrastructureContext EngineeringDeFi Systems

// open source

Mission ControlAgent fleet ops: tasks, quality gates, cost visibility, realtime.
2.6k
OpenClaw to HermesMigrate from OpenClaw to Hermes Agent — complete, battle-tested migration tool.
4
Awesome Agent CortexThe sovereign agent stack — practical scripts, on-chain identity, and knowledge graphs for AI agents that think, remember, and own themselves.
74
Marketing DashboardMarketing Operations Control Center for AI agent teams (CRM, outreach, content, analytics).
136
xintX intelligence CLI for monitoring and research workflows.
52
xint-rsSingle-binary Rust variant optimized for speed and portability.
8
LACPLocal Agent Control Plane: Claude/Codex control-plane for memory, retrieval gates, and telemetry.
4
dictxLocal-first speech workflow product.
Council of High IntelligenceOpen-sourced multi-perspective reasoning skill.
2
Solana dApp ScaffoldProduction-ready Solana starter kit.
47
// work
pump.science

pump.science

Gamified longevity research platform merging scientific exploration with interactive digital experiences.

SolanaDeFiScience
SeaTrees

SeaTrees

Carbon credit transparency platform on Solana tracking environmental impact.

SolanaImpactCarbon
SEND

SEND

High-stakes blockchain game combining NFT mechanics with game theory.

SolanaNFTGaming
B-Pay

B-Pay

Payment, team management, and invoicing platform for Cynova Enterprise.

PaymentsEnterpriseSaaS
Renaissance

Renaissance

2023 Grizzlython Hackathon winner; user-friendly royalty solution.

SolanaNFTRoyalties
Solana Tool Suite

Solana Tool Suite

Comprehensive toolkit: hashlist finder, filter tools, snapshots, airdrops, royalty payments.

SolanaToolingAirdrops
// articles
How I Run Claude Agents on 1M Context Without Drift
engineering14 min

How I Run Claude Agents on 1M Context Without Drift

The problem was never the window size. It was context rot — performance degrades as conversations fill, not because the model forgets, but because signal drowns in noise.

3.6K49106
Vibe Code A DeFi Quant Bot Without Blowing Up
engineering12 min

Vibe Code A DeFi Quant Bot Without Blowing Up

Most people think the hard part is writing the bot. It isn't. The hard part is building risk rules that the bot cannot negotiate with.

8.4K4274
If You Have Multiple Interests, Stop Trying To Pick One
strategy7 min

If You Have Multiple Interests, Stop Trying To Pick One

Pick one identity and repeat it for 40 years — that model breaks when the world rewrites itself every quarter. Your curiosity is raw material, not a weakness.

13.4K64104
The Ultimate Vibe Coding Beginner's Guide
engineering15 min

The Ultimate Vibe Coding Beginner's Guide

AI tools increased output 10% while collapsing code quality by 60%. The exact failure pattern, why it happens, and the checklist to survive the transition.

25K104143
Context Engineering Is The Only Engineering That Matters Now
engineering12 min

Context Engineering Is The Only Engineering That Matters Now

An arXiv paper documented a Claude Code project with 26,000 lines of context architecture — more instructions than actual code. Their agents stopped hallucinating.

82.7K5261354
The Harness Is The Product. The Model Never Was
agents10 min

The Harness Is The Product. The Model Never Was

LangChain jumped from Top 30 to Top 5 by changing zero model parameters. The teams shipping production agents have the best harness, not the best model access.

74K349745
Claude + Obsidian: The Memory Stack That Compounds
engineering8 min

Claude + Obsidian: The Memory Stack That Compounds

Teams burn 30-40 minutes per Claude session re-explaining what they already knew. A three-tier memory system that makes output compound instead of plateau.

213.7K8332639
Your Next Buyer Won't Fill Out a Form. It Will Hit an MCP Endpoint With a Budget.
agents9 min

Your Next Buyer Won't Fill Out a Form. It Will Hit an MCP Endpoint With a Budget.

Visa reported a 4,700% jump in AI-driven retail traffic. Within 12 months, MCP buying shifts revenue upstream. Most GTM teams still optimize for humans.

7.7K2234
Why AI Needs Crypto (And How to Sell to Agents in a Shifting Market)
strategy8 min

Why AI Needs Crypto (And How to Sell to Agents in a Shifting Market)

Most people frame AI vs crypto as a rivalry. Wrong framing. If AI is the intelligence layer, crypto is becoming the transaction layer for autonomous software.

2.2K53
The Claude + Codex Local Stack Playbook That Cut One Loop by 78.5%
engineering10 min

The Claude + Codex Local Stack Playbook That Cut One Loop by 78.5%

Everyone says 'fix prompts' — in practice, the bottleneck is shell init, hook chains, and context drift. A measured pass cut zsh startup from 1.794s to 0.386s.

28655