Collection

Agent engineering

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

Blog posts
80
Topic
AI and agents

Start here

Latest in this collection

Layered memory cards representing compact agent context with recoverable source evidence AI & Agents

TencentDB Agent Memory: Is SQLite Enough for Your AI Agent?

Local storage, inspectable memory and about 61% fewer tokens in one reported evaluation. What TencentDB changes, what still needs a model API and how we would test it.

Kevin Riedl
Read
Wavect editorial illustration for RTK 1.0 token filtering and evaluation AI & Agents

RTK AI 1.2: Real Token Savings, Setup and Licensing

RTK 1.2.0 improves how partial reads are counted and preserves more nextest failure detail. Check the license split, agent setup and proxy routes before measuring savings.

Kevin Riedl
Read
Layered turquoise geometry representing an Anatomy illustration assembled from editable parts AI & Agents

Anatomy for Claude Code: Interactive SVGs for Documentation

Turn a technical explanation into a figure readers can explore. Install Anatomy, choose HTML or React, and check the model before embedding it in your docs.

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

Google AX: Suspend/Resume, Restart Costs and Self-Hosting

Fast resume is not crash recovery. What Google AX preserves, what changed in its API, and how to test whether fewer replays justify the infrastructure.

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
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
Read

Complete article directory

  1. TencentDB Agent Memory: Is SQLite Enough for Your AI Agent?
  2. RTK AI 1.2: Real Token Savings, Setup and Licensing
  3. Anatomy for Claude Code: Interactive SVGs for Documentation
  4. Google AX: Suspend/Resume, Restart Costs and Self-Hosting
  5. WikiSkill: How Agents Evolve SKILL.md from Experience
  6. Tencent Octop Review: What Builders Actually Get for Free
  7. Wigolo Review: Local Web Intelligence for AI Agents
  8. Supermemory: AI Agent Memory, RAG and Local Setup
  9. AI Agent Design Patterns: Start Simple, Verify Actions
  10. Claude Mods: Setup, Function Hooks and Security
  11. Voicebox: Local Voice Cloning, Dictation and MCP Setup
  12. Valyu’s 0.6B Multi-Agent Router: Results, Limits and When to Train One
  13. OpenAI Agents API Review: Migration, Costs and Data Controls
  14. Spotify shunt Review: Setup, Savings and Limits
  15. OpenBot Review: Self-Hosted AI Coworkers, Costs & Controls
  16. Ramp Inspect Architecture 2026: Background Coding Agents at Scale
  17. Model Hardware Standard: Enterprise Guide to Physical AI
  18. Fonio AI Review 2026: Pricing, API, GDPR & Build vs Buy
  19. Mosaic (YC S26) Review: Shared Memory for Team AI Agents
  20. Ripwire Review 2026: AI Repo Context Without Embeddings?
  21. Atomic Multi-File Edits for AI Coding Agents: The Semaprax Lesson
  22. AI Agent Knowledge Transfer: Use Frontier Models Once, Then Scale Cheaper
  23. claude-rotate: One Proxy for Multiple Claude Max Accounts
  24. Feynman Review: Is This Open-Source AI Research Agent Ready for Teams?
  25. Obscura Browser Review: Claims, Limits and Production Fit
  26. Claude Code Design System: 4 Parts for On-Brand UI
  27. ChatGPT Can Now Log In Without Seeing Your Password
  28. AI Agent Harness, Explained: The Reliability Layer Around an LLM
  29. Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust
  30. LangChain Deep Agents Review: Is the Agent Harness Ready for Production?
  31. OpenViking Review: Filesystem Memory for AI Agents
  32. LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
  33. TrueForge Review: Is the Open-Source Agent Harness Production-Ready?
  34. Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
  35. Localized URL Slugs vs hreflang: Why We Keep One English Slug
  36. Can an AI Agent Use Your Product, or Only Read About It?
  37. Graft Review 2026: Do Agent Repo Maps Belong in Git?
  38. Codag for Coding Agents: Tool-Output Compression and Cost
  39. Smarter Token Usage: Measure Cost per Accepted Coding Task
  40. DeepSeek Harness Review: Is the Plugin Stack Production-Ready?
  41. Alibaba OpenSandbox: Self-Hosting and Production Limits
  42. Cloudflare Kitesurf Review: Cost, Limits and Production Fit
  43. GitHub Spec Kit Review: Is It Worth the Process?
  44. Internal AI Agent Marketplace: A 2026 Enterprise Build Guide
  45. Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide
  46. MCP Cloud vs Manufact Cloud: MCP Hosting Guide
  47. How to Make AI Writing Sound Human with Agent Skills
  48. NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?
  49. Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026
  50. Hyperagent Review: Cloud AI Agents Without a Server
  51. Hark Handoff Review: The Agent That Actually Clicks
  52. Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?
  53. Agent Reach Review: Costs, Security and Real Limits
  54. Cloudflare Wallets for AI Agents: What Is Live?
  55. YC QM Agent Review: Is Quartermaster Ready for Work?
  56. jcode vs Claude Code: Is the Rust Harness Worth Switching To?
  57. Lightpanda Browser for AI Agents: Production Guide
  58. Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?
  59. Multi-Model AI Coding Agent Stack: A Team Buying Guide
  60. Is MCP Stateless Now? Your Server Migration Checklist
  61. MCP Is Not a Security Boundary: Protect Agent Data
  62. Can AI Agents Talk to Each Other? A Band Setup Guide
  63. LeanCTX Technical Field Report: 64.1% Less Context
  64. CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
  65. Enterprise MCP Authorization Architecture
  66. Meterless Review 2026: Is This AI Agent Context Layer Ready?
  67. Claude Code vs OpenCode: Which Costs Less for a Team in 2026?
  68. Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?
  69. AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days
  70. T3MP3ST Review 2026: Can It Replace a Penetration Test?
  71. Open Knowledge Format (OKF): The Enterprise Guide
  72. AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills
  73. How to Use Claude Fable 5.2 in Claude Code
  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
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.