Collection

Models and infrastructure

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

Blog posts
78
Topic
AI and agents

Start here

Latest in this collection

A large euro symbol above segmented cost markers AI & Agents

Odoo AI credits: budget a reviewed quotation workflow

Budget the quotation queue before increasing volume. Separate Odoo credits, subscription uplift, initial review and correction work in a runnable synthetic ledger.

Kevin Riedl
Read
A shared starting point branches into 3 labeled paths AI & Agents

Odoo Helpdesk AI: classify, draft or escalate?

Separate ticket labels, internal reply drafts and human handoff. Use proposed support cases to test permissions and missed escalations.

Kevin Riedl
Read
Brackets framing an ontology derivation certificate in teal and violet AI & Agents

How to Validate Open Ontologies Derivation Certificates

Run a reproducible graph test, distinguish a forged-proof rejection from a checker failure, and inspect what a smaller RAG context still supports.

Kevin Riedl
Read
Separate paths for crawl requests and extracted records AI & Agents

Does Scrapling Save Scraped Items in Checkpoints?

A local pause, resume and replay test shows which records survive, when JSON exports replace earlier items, and which data a checkpoint saves.

Kevin Riedl
Read
Two overlapping waveforms illustrate conversational timing in voice AI AI & Agents

Cue Turn Detection: Phone Numbers, Benchmarks and Limits

A pause is not a finished phone number. What Pype’s Cue v1 improves, what the benchmarks measure, and how to test correct, confirmed capture.

Kevin Riedl
Read
Wavect editorial header for Agent Mesh, with a shield representing controlled access to tools AI & Agents

Google SAM is now Agent Mesh: MCP tools across machines

Connect approved tools across machines. Understand the control plane, signed EU labels and the checks a useful first pilot should pass.

Kevin Riedl
Read

Complete article directory

  1. Odoo AI credits: budget a reviewed quotation workflow
  2. Odoo Helpdesk AI: classify, draft or escalate?
  3. How to Validate Open Ontologies Derivation Certificates
  4. Does Scrapling Save Scraped Items in Checkpoints?
  5. Cue Turn Detection: Phone Numbers, Benchmarks and Limits
  6. Google SAM is now Agent Mesh: MCP tools across machines
  7. EdgeQuake: PostgreSQL GraphRAG for MCP agent memory
  8. BitNet on CPU: 2B4T, real RAM needs and the 100B claim
  9. SuperPenguin: AI Cost per PR, Customer and Feature
  10. Claude Dashboards + Motion: From KPIs to Video
  11. OpenAI Intelligent UI vs OpenUI: Generative UI for Business Apps
  12. Wally by RunAnywhere: Cost per Accepted Coding Task
  13. Reducto for German Invoices: Measure Human Review Effort
  14. Claude Model Router: What Switches the Model, and When?
  15. Context Language Models vs Compaction: What to Pilot
  16. Caveman 3.0 for Claude Code: Local Input Compression, Recovery and Benchmarks
  17. LiteLLM Lens: Agent Trace Analysis with SQL and APIs
  18. SmythOS Studio Self-Hosting: Docker Setup, Costs and Limits
  19. DeerFlow 2.2: Docker Setup, Sandboxes and Memory
  20. CLM-8B Self-Hosting: vLLM, Action Cache and Verifiers
  21. LiteAgents SDK: Per-Turn Routing, Setup and Migration
  22. mcp-memory-service: Shared Memory for Claude Code and Cursor
  23. Claude Opus 5.5: Best Uses, Prompts and Effort Settings
  24. SwarmLLM Review 2026: Browser P2P LLM Inference Across Phones and Laptops
  25. Phonely Alma Review: Is the Voice LLM Ready for Production?
  26. Utopia Review: Temporal Knowledge Graph for Enterprise
  27. NVIDIA PAIR Review: Local AI Routing and the AMD Gap
  28. Tencent Hy4 Preview Review: What Changes with the Full Hy4 Release?
  29. PageLM Review: Self-Hosting and Commercial Use
  30. M6 Mac mini vs M5 Mac Studio for Local AI: Buyer’s Guide
  31. FreeToken AI Review: Run Frontier MoE Models on Consumer GPUs?
  32. Darkbloom AI Review: Private Inference on Idle Macs
  33. Ox Alpha Revealed as GLM-5.3-Flash: What Changed
  34. Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?
  35. Thunder Compute’s $13M GPU Virtualization Bet: Enterprise Buyer’s Guide
  36. AirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works
  37. Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting Screenshots
  38. Netflix’s vLLM and Triton Stack: 7 Production Lessons
  39. Transformers.js Browser AI: When Local Inference Belongs in Your Product
  40. How to Self-Host LiteLLM in Production: 2026 Guide
  41. AI-Ready Company Wiki: Architecture and Build Guide
  42. Does Claude Watermark Text? The 2026 API Answer
  43. OpenKB Review: Knowledge Compiler vs RAG
  44. Unsloth Desktop Review: A Private Local AI Workstation?
  45. NeMo Switchyard 0.2: Agent Model Routing Without Training?
  46. Firecrawl AnyDoc Review: 14 Formats to Markdown
  47. Muse Glimmer 30B: Is Meta’s Local Agent Model Production-Ready?
  48. OmniRoute AI Routing: Setup and Production Checklist
  49. Gemini Robotics 2: Whole-Body Control and the Pilot Decision
  50. pdf-inspector Review: Route PDFs Before OCR
  51. Local Multimodal AI Coding Assistant: Voice, OCR and Privacy
  52. DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?
  53. Fine-Tune Gemma 4 Free with Unsloth and Colab
  54. Taalas HC1 Review: Is a Hardwired LLM ASIC Worth It?
  55. llmfit Guide: Which Local LLM Fits Your Hardware?
  56. Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality
  57. Compress RAG Vectors to 2 Bits: Is Data-Oblivious Quantization Production-Ready?
  58. LMCache Reported 13.7x Lower Mean TTFT with a Shared KV Cache
  59. Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?
  60. NVIDIA Nemotron 3.5 ASR: Is Free Self-Hosted STT Ready for Voice Agents?
  61. Kimi K3 for EU Companies: API Cost, Data Risk, and a Pilot Plan
  62. Mesh LLM Review: Can One Large LLM Run Across Multiple Computers?
  63. Bonsai 27B Review: Can a 27B LLM Really Run on a Phone?
  64. Soofi S: Is Germany’s Sovereign LLM Ready for Business?
  65. Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.
  66. When Local Models Beat APIs: A Break-Even Calculator for EU Companies
  67. LLM Cost Calculator 2026: Cost per Task, Not Cost per Token
  68. Pxpipe Review: Can Images Cut Claude Code Token Costs 60%?
  69. Cheaper Per Token Can Still Cost More Per Task
  70. Anthropic Says No Open-Weights Ban. The Cost War Is Still Real.
  71. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  72. LLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM
  73. Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off
  74. Open-Weight LLMs 2026: DeepSeek, Qwen, Kimi, GLM, Llama and Muse
  75. How to Cut LLM Token Costs in 2026
  76. When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge
  77. RAG vs Fine-Tuning vs Long-Context 2026
  78. LLM API Costs 2026. Architecture Shift
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.