You know the feeling. The agent that nailed everything this morning is now making mistakes a beginner would not make. It just got noticeably worse over the sess…

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems13 min

How to Actually Package Agent Workflows as Hermes Plugins - Full Course

Most people still judge agents by model quality. Packaging workflows as Hermes plugins is the hard part: contracts, distribution, and operator loops.

Jul 13, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems11 min

Fable Masterclass: stop spending Mythos-class intelligence like a chat app

They will route every task to the most expensive brain in the room.

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems9 min

How to Actually Run a Claude Memory Stack: 90 Days of Receipts

Most people treat Claude memory like a bigger notebook.

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems11 min

The 4 Layers of AI Work: Prompt Engineering Is Only Layer 1

The argument over prompt engineering versus context engineering is already stale.

Jul 13, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems6 min

Mission Control v2.1.0 Is Out - Self-Hosted Mission Control for AI Agents

Self-hosted mission control for AI agent fleets: what v2.1.0 is for, how to install the mental model, and the operator checklist after clone.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems5 min

4 Layers Every Production AI Agent Needs

Model, tools, context, harness - the compact production checklist before you trust an agent with real work.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems6 min

Context Limits Are the Silent Killer of AI Agents

Why agents go sloppy mid-session without a clean error - and the four practices that stop silent context death.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems10 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.

Mar 10, 2026

74K349745

// newsletter

Free · no spam

Agent OS checklist + field notes

Skills, memory, jobs, handoff - one checklist. Occasional notes when something ships. Hands-on later: packages from $3K.

Checklist arrives in about a minute
·
Path to fixed packages
·
Unsubscribe anytime

Checklist + notes. No spam.

nyk

Agent ops, Solana infra, OSS, and the ventures under this name. Book a fixed package or hire the studio.

Book a call

Ventures
About
Selected work
OSS
Packages
Studio
Consulting
Case studies
Resources
Checklist
Blog
Notes
Contact
Privacy

nyk.dev · agents · Solana · open source

Loading grid

Home
Blog
Agent systems

blog · category

Agent systems

Agent design, harnesses, memory, and operating patterns.

9 notes

All36 Guides20 Agent systems9 Engineering4 Strategy2 Growth1

Agent design, harnesses, memory, and operating patterns.

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems11 min

Your AI Agent Didn't Get Dumber. Your Context Did.

You know the feeling. The agent that nailed everything this morning is now making mistakes a beginner would not make. It just got noticeably worse over the sess…

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems13 min

How to Actually Package Agent Workflows as Hermes Plugins - Full Course

Most people still judge agents by model quality. Packaging workflows as Hermes plugins is the hard part: contracts, distribution, and operator loops.

Jul 13, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems11 min

Fable Masterclass: stop spending Mythos-class intelligence like a chat app

They will route every task to the most expensive brain in the room.

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems9 min

How to Actually Run a Claude Memory Stack: 90 Days of Receipts

Most people treat Claude memory like a bigger notebook.

Jul 13, 2026

𝕏X Article (opens in a new tab)

// AGENT SYSTEMS

Agent systems11 min

The 4 Layers of AI Work: Prompt Engineering Is Only Layer 1

The argument over prompt engineering versus context engineering is already stale.

Jul 13, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems6 min

Mission Control v2.1.0 Is Out - Self-Hosted Mission Control for AI Agents

Self-hosted mission control for AI agent fleets: what v2.1.0 is for, how to install the mental model, and the operator checklist after clone.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems5 min

4 Layers Every Production AI Agent Needs

Model, tools, context, harness - the compact production checklist before you trust an agent with real work.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems6 min

Context Limits Are the Silent Killer of AI Agents

Why agents go sloppy mid-session without a clean error - and the four practices that stop silent context death.

Jul 7, 2026

𝕏On X (opens in a new tab)

// AGENT SYSTEMS

Agent systems10 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.

Mar 10, 2026

74K349745

// newsletter

Free · no spam

Agent OS checklist + field notes

Skills, memory, jobs, handoff - one checklist. Occasional notes when something ships. Hands-on later: packages from $3K.

Checklist arrives in about a minute
·
Path to fixed packages
·
Unsubscribe anytime

Checklist + notes. No spam.

nyk

Agent ops, Solana infra, OSS, and the ventures under this name. Book a fixed package or hire the studio.

Book a call

Ventures
About
Selected work
OSS
Packages
Studio
Consulting
Case studies
Resources
Checklist
Blog
Notes
Contact
Privacy

nyk.dev · agents · Solana · open source