Topic

AI and agents

Engineering, operating and evaluating AI systems, coding agents and model infrastructure.

Blog posts
101
Focused clusters
02

Focused clusters

55 posts

Agent engineering

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

Cluster →
46 posts

Models and infrastructure

Model selection, inference economics, local deployment, compression and serving architecture.

Cluster →

Start with the cornerstone

Latest in this collection

Ox Alpha free stealth AI model routed through OpenCode Zen and OpenRouter with privacy and cost checks AI & Agents

Ox Alpha Free AI Model: Setup, Privacy and Buyer Guide

Use the 1M-context stealth coding model through OpenCode or OpenRouter. Compare IDs, privacy terms, hidden costs and a safe team evaluation plan.

Kevin Riedl Kevin Riedl
Read
Rust compiler graph connecting persistent declaration identities to verified semantic patches AI & Agents

Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust

A compiler engineering walkthrough of persistent IDs, checked HIR, deterministic graphs and replayable patches in the experimental SEMAPRAX language.

Kevin Riedl Kevin Riedl
Read
LangChain Deep Agents connects planning, subagents, files, approvals, sandboxes and production traces AI & Agents

LangChain Deep Agents Review: Is the Agent Harness Ready for Production?

A buyer-focused Deep Agents review covering architecture, v0.7 changes, security boundaries, operating costs and a measurable production pilot.

Kevin Riedl Kevin Riedl
Read
Four Pika Audio API models mapped to sound effects, speech, music and synchronized video soundtracks with cost controls AI & Agents

Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?

Pika lists SFX at $0.0002 per second, plus three more audio models. See the real break-even, API limits, quality gates and production fit before you switch.

Kevin Riedl Kevin Riedl
Read
GPU workloads sharing a pooled accelerator fleet through a virtualization layer AI & Agents

Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide

Thunder Compute says GPU pooling can recover stranded capacity. Compare network virtualization with MIG, vGPU and passthrough, then scope a measurable enterprise pilot.

Kevin Riedl Kevin Riedl
Read
OpenViking filesystem connecting agent memory, RAG resources and skills through viking paths AI & Agents

OpenViking Review 2026: Is Filesystem Memory Production-Ready?

Buyer review of OpenViking for agent memory and RAG: architecture, AGPL risk, security controls, operating cost and a measurable two-week pilot.

Kevin Riedl Kevin Riedl
Read

Complete article directory

  1. Ox Alpha Free AI Model: Setup, Privacy and Buyer Guide
  2. Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust
  3. LangChain Deep Agents Review: Is the Agent Harness Ready for Production?
  4. Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?
  5. Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide
  6. OpenViking Review 2026: Is Filesystem Memory Production-Ready?
  7. LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
  8. AirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works
  9. TrueForge Review: Is the Open-Source Agent Harness Production-Ready?
  10. Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
  11. Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting Screenshots
  12. Localized URLs Break hreflang: Keep One English Slug
  13. Can an AI Agent Use Your Product, or Only Read About It?
  14. Graft Review 2026: Do Agent Repo Maps Belong in Git?
  15. How Coding Agents Keep Token Bills in Check with Output Compression
  16. Smarter Token Usage with Your AI Coding Agent
  17. DeepSeek Harness Review: Is the Plugin Stack Production-Ready?
  18. Netflix's vLLM and Triton Stack: 7 Production Lessons
  19. OpenSandbox Review: Is Self-Hosting Worth It?
  20. Transformers.js Browser AI: When Local Inference Belongs in Your Product
  21. Cloudflare Kitesurf Review: Cost, Limits and Production Fit
  22. GitHub Spec Kit Review: Is It Worth the Process?
  23. Internal AI Agent Marketplace: A 2026 Enterprise Build Guide
  24. How to Self-Host LiteLLM in Production: 2026 Guide
  25. AI-Ready Company Wiki: Architecture and Build Guide
  26. Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide
  27. Does Claude Watermark Text? The 2026 API Answer
  28. OpenKB Review: Knowledge Compiler vs RAG
  29. Unsloth Desktop Review: A Private Local AI Workstation?
  30. NeMo Switchyard 0.2: Agent Model Routing Without Training?
  31. Firecrawl AnyDoc Review: 14 Formats to Markdown
  32. MCP Cloud vs Manufact Cloud: MCP Hosting Guide
  33. Muse Glimmer 30B: Is Meta's Local Agent Model Production-Ready?
  34. How to Make AI Writing Sound Human with Agent Skills
  35. NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?
  36. OmniRoute AI Routing: Setup and Production Checklist
  37. Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026
  38. Hyperagent Review: Cloud AI Agents Without a Server
  39. Gemini Robotics 2: Whole-Body Control and the Pilot Decision
  40. Hark Handoff Review: The Agent That Actually Clicks
  41. Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?
  42. pdf-inspector Review: Route PDFs Before OCR
  43. PII Redaction Before LLM Prompts: A Practical Pipeline
  44. Agent Reach Review: Costs, Security and Real Limits
  45. Cloudflare Wallets for AI Agents: What Is Live?
  46. Local Multimodal AI Coding Assistant: Voice, OCR and Privacy
  47. DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?
  48. YC QM Agent Review: Is Quartermaster Ready for Work?
  49. jcode vs Claude Code: Is the Rust Harness Worth Switching To?
  50. Lightpanda Browser for AI Agents: Production Guide
  51. Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?
  52. Multi-Model AI Coding Agent Stack: A Team Buying Guide
  53. Is MCP Stateless Now? Your Server Migration Checklist
  54. MCP Is Not a Security Boundary: Protect Agent Data
  55. Fine-Tune Gemma 4 Free with Unsloth and Colab
  56. Can AI Agents Talk to Each Other? A Band Setup Guide
  57. Taalas HC1 Review: Is a Hardwired LLM ASIC Worth It?
  58. LeanCTX Technical Field Report: 64.1% Less Context
  59. llmfit Guide: Which Local LLM Fits Your Hardware?
  60. CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
  61. Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality
  62. Enterprise MCP Authorization Architecture
  63. Cut RAG Vector Memory 16x: Is Data-Oblivious Quantization Ready for Production?
  64. Shared KV Cache Cut LLM Inference Latency 14x, With No New GPUs
  65. Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?
  66. OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent
  67. Cisco Antares Review: 1B Local AI for Vulnerability Localization
  68. Meterless Review 2026: Is This AI Agent Context Layer Ready?
  69. NVIDIA Nemotron 3.5 ASR: Is Free Self-Hosted STT Ready for Voice Agents?
  70. Claude Code vs OpenCode: Which Costs Less for a Team in 2026?
  71. Kimi K3 for EU Companies: API Cost, Data Risk, and a Pilot Plan
  72. Mesh LLM Review: Can One Large LLM Run Across Multiple Computers?
  73. Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?
  74. Bonsai 27B Review: Can a 27B LLM Really Run on a Phone?
  75. Soofi S: Is Germany's Sovereign LLM Ready for Business?
  76. AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days
  77. T3MP3ST Review 2026: Can It Replace a Penetration Test?
  78. Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.
  79. Open Knowledge Format (OKF): The Enterprise Guide
  80. AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills
  81. When Local Models Beat APIs: A Break-Even Calculator for EU Companies
  82. LLM Cost Calculator 2026: Cost per Task, Not Cost per Token
  83. Pxpipe Review: Can Images Cut Claude Code Token Costs 60%?
  84. Cheaper Per Token. More Expensive Per Answer.
  85. How to Use Claude Fable 5 in Claude Code
  86. Dario Declared War on Open Source. The Real War Is Over Your AI Bill.
  87. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  88. LLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM
  89. Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off
  90. Best Open-Weight LLMs 2026: DeepSeek vs Qwen vs Kimi vs GLM vs Llama
  91. The Bottleneck Was Never Intelligence. It Was Context.
  92. ChatGPT Enterprise vs Copilot vs Custom RAG
  93. MCP vs RAG vs Agent Skills vs Custom GPTs
  94. How to Cut LLM Token Costs in 2026
  95. AI Agent Pilot in 30/60/90 Days
  96. Permissions-First RAG over SharePoint, Confluence, Drive
  97. RAG Production-Readiness Checklist for EU Companies
  98. When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge
  99. Why 40% of AI Agent Projects Die
  100. RAG vs Fine-Tuning vs Long-Context 2026
  101. LLM API Costs 2026. Architecture Shift