Cluster

Agent engineering

Coding agents, MCP, context systems, evaluation and the controls required for dependable automation.

Blog posts
80
Topic
AI and agents

Start with the cornerstone

Inbox, without the noise

Get the next AI and agents field note

One concise email when we publish. No tracking pixels, and no inbox filler.

Latest in this collection

Wavect editorial header for Google AX, with a shield representing agent execution boundaries AI & Agents

Google AX Agent Executor: Budgets and Self-Hosting

A sandbox is not a spending cap. What Google AX really controls, what survives suspend/resume, and which dependencies matter when you want to own your AI.

Kevin Riedl Kevin Riedl
Read
Raw agent traces becoming a persistent wiki and a validated SKILL.md file AI & Agents

WikiSkill: How Agents Evolve SKILL.md from Experience

WikiSkill compiles agent traces into a persistent evidence wiki, then validates atomic changes to SKILL.md. We review the benchmarks, transfer results, limits and production architecture.

Kevin Riedl Kevin Riedl
Read
Octop connecting users, AI agents, tools and self-hosted data in one application stack AI & Agents

Tencent Octop Review: What Builders Actually Get for Free

Tencent released Octop under MIT, with multi-user agents, a dashboard, automation and storage. We examine what is really included, what is not and what a production fork still costs.

Kevin Riedl Kevin Riedl
Read
Wigolo fans one AI agent query across search engines, reranks evidence locally and exposes ten web tools through MCP AI & Agents

Wigolo Review: Local Web Intelligence for AI Agents

Wigolo gives AI agents local-first search, fetch, crawl and research without a paid search API. We verify the ten-tool surface, cache, privacy, AGPL license and production limits.

Kevin Riedl Kevin Riedl
Read
Layered context cards representing persistent AI agent memory in Wavect editorial artwork AI & Agents

Supermemory: AI Agent Memory, RAG and Local Setup

Give your AI agent context between sessions without building the memory pipeline yourself. A practical Supermemory guide with API code, local setup and an honest benchmark review.

Kevin Riedl Kevin Riedl
Read
Wavect editorial shield artwork for choosing bounded AI agent design patterns AI & Agents

AI Agent Design Patterns: Start Simple, Verify Actions

More loops are not automatically better. Choose the smallest agent architecture that solves the failure, and separate a proposed action from permission to execute it.

Kevin Riedl Kevin Riedl
Read

Complete article directory

  1. Google AX Agent Executor: Budgets and Self-Hosting
  2. WikiSkill: How Agents Evolve SKILL.md from Experience
  3. Tencent Octop Review: What Builders Actually Get for Free
  4. Wigolo Review: Local Web Intelligence for AI Agents
  5. Supermemory: AI Agent Memory, RAG and Local Setup
  6. AI Agent Design Patterns: Start Simple, Verify Actions
  7. Claude Mods: Setup, Function Hooks and Security
  8. Voicebox: Local Voice Cloning, Dictation and MCP Setup
  9. Valyu’s 0.6B Multi-Agent Router: Results, Limits and When to Train One
  10. OpenAI Agents API Review: Migration, Costs and Data Controls
  11. Spotify shunt Review: Setup, Savings and Limits
  12. OpenBot Review: Self-Hosted AI Coworkers, Costs & Controls
  13. Ramp Inspect Architecture 2026: Background Coding Agents at Scale
  14. Model Hardware Standard: Enterprise Guide to Physical AI
  15. Fonio AI Review 2026: Pricing, API, GDPR & Build vs Buy
  16. Mosaic (YC S26) Review: Shared Memory for Team AI Agents
  17. Ripwire Review 2026: AI Repo Context Without Embeddings?
  18. Atomic Multi-File Edits for AI Coding Agents: The Semaprax Lesson
  19. AI Agent Knowledge Transfer: Use Frontier Models Once, Then Scale Cheaper
  20. claude-rotate: One Proxy for Multiple Claude Max Accounts
  21. Feynman Review: Is This Open-Source AI Research Agent Ready for Teams?
  22. Obscura Browser Review: Claims, Limits and Production Fit
  23. Claude Code Design System: 4 Parts for On-Brand UI
  24. ChatGPT Can Now Log In Without Seeing Your Password
  25. AI Agent Harness, Explained: The Reliability Layer Around an LLM
  26. Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust
  27. LangChain Deep Agents Review: Is the Agent Harness Ready for Production?
  28. OpenViking Review: Filesystem Memory for AI Agents
  29. LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
  30. TrueForge Review: Is the Open-Source Agent Harness Production-Ready?
  31. Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
  32. Localized URL Slugs vs hreflang: Why We Keep One English Slug
  33. Can an AI Agent Use Your Product, or Only Read About It?
  34. Graft Review 2026: Do Agent Repo Maps Belong in Git?
  35. How Coding Agents Keep Token Bills in Check with Output Compression
  36. Smarter Token Usage with Your AI Coding Agent
  37. DeepSeek Harness Review: Is the Plugin Stack Production-Ready?
  38. OpenSandbox Review: Is Self-Hosting Worth It?
  39. Cloudflare Kitesurf Review: Cost, Limits and Production Fit
  40. GitHub Spec Kit Review: Is It Worth the Process?
  41. Internal AI Agent Marketplace: A 2026 Enterprise Build Guide
  42. Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide
  43. MCP Cloud vs Manufact Cloud: MCP Hosting Guide
  44. How to Make AI Writing Sound Human with Agent Skills
  45. NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?
  46. Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026
  47. Hyperagent Review: Cloud AI Agents Without a Server
  48. Hark Handoff Review: The Agent That Actually Clicks
  49. Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?
  50. PII Redaction Before LLM Prompts: A Practical Pipeline
  51. Agent Reach Review: Costs, Security and Real Limits
  52. Cloudflare Wallets for AI Agents: What Is Live?
  53. YC QM Agent Review: Is Quartermaster Ready for Work?
  54. jcode vs Claude Code: Is the Rust Harness Worth Switching To?
  55. Lightpanda Browser for AI Agents: Production Guide
  56. Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?
  57. Multi-Model AI Coding Agent Stack: A Team Buying Guide
  58. Is MCP Stateless Now? Your Server Migration Checklist
  59. MCP Is Not a Security Boundary: Protect Agent Data
  60. Can AI Agents Talk to Each Other? A Band Setup Guide
  61. LeanCTX Technical Field Report: 64.1% Less Context
  62. CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
  63. Enterprise MCP Authorization Architecture
  64. OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent
  65. Meterless Review 2026: Is This AI Agent Context Layer Ready?
  66. Claude Code vs OpenCode: Which Costs Less for a Team in 2026?
  67. Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?
  68. AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days
  69. T3MP3ST Review 2026: Can It Replace a Penetration Test?
  70. Open Knowledge Format (OKF): The Enterprise Guide
  71. AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills
  72. How to Use Claude Fable 5.1 in Claude Code
  73. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  74. The Bottleneck Was Never Intelligence. It Was Context.
  75. ChatGPT Enterprise vs Copilot vs Custom RAG
  76. MCP vs RAG vs Agent Skills vs Custom GPTs
  77. AI Agent Pilot in 30/60/90 Days
  78. Permissions-First RAG over SharePoint, Confluence, Drive
  79. RAG Production-Readiness Checklist for EU Companies
  80. Why AI Agent Projects Get Cancelled