---
title: "AI and agentsWavect"
canonical: https://wavect.io/blog/topics/ai-agents/
language: en
description: "Engineering, operating and evaluating AI systems, coding agents and model infrastructure."
image: "https://wavect.io/img/general/bak/open_graph_preview.jpg"
---

Topic

# AI and agents

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

## Focused clusters

### [Agent engineering](/blog/clusters/agent-engineering/)

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

### [Models and infrastructure](/blog/clusters/models-infrastructure/)

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

## Start with the cornerstone

- [**Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?**A buyer-focused guide to execution graphs, experiment DAGs and knowledge graphs, including when to skip them, what provenance requires and how to run a measured pilot.](/blog/graph-engineering-ai-agents/)
- [**Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off**The GPU is the cheap part. Here is the real cost of self-hosting open weights, the tokens/day break-even vs hosted APIs, when data residency forces your hand, and the vLLM production stack.](/blog/self-hosting-llms-eu-cost/)

## Latest in this collection

### [Ox Alpha Free AI Model: Setup, Privacy and Buyer Guide](/blog/ox-alpha-free-ai-model-guide-2026/)

- **Details:** AI & Agents · 23 Aug 2026

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

### [Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust](/blog/semantic-identity-rust-agent-edits/)

- **Details:** AI & Agents · 23 Aug 2026

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

### [LangChain Deep Agents Review: Is the Agent Harness Ready for Production?](/blog/langchain-deep-agents-review/)

- **Details:** AI & Agents · 23 Aug 2026

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

### [Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?](/blog/pika-audio-models-api-pricing-2026/)

- **Details:** AI & Agents · 21 Aug 2026

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.

### [Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide](/blog/thunder-compute-gpu-virtualization-series-a/)

- **Details:** AI & Agents · 21 Aug 2026

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

### [OpenViking Review 2026: Is Filesystem Memory Production-Ready?](/blog/openviking-agent-memory-review/)

- **Details:** AI & Agents · 21 Aug 2026

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

## Complete article directory

1. [Ox Alpha Free AI Model: Setup, Privacy and Buyer Guide](/blog/ox-alpha-free-ai-model-guide-2026/) 23 Aug 2026
2. [Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust](/blog/semantic-identity-rust-agent-edits/) 23 Aug 2026
3. [LangChain Deep Agents Review: Is the Agent Harness Ready for Production?](/blog/langchain-deep-agents-review/) 23 Aug 2026
4. [Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?](/blog/pika-audio-models-api-pricing-2026/) 21 Aug 2026
5. [Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide](/blog/thunder-compute-gpu-virtualization-series-a/) 21 Aug 2026
6. [OpenViking Review 2026: Is Filesystem Memory Production-Ready?](/blog/openviking-agent-memory-review/) 21 Aug 2026
7. [LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit](/blog/llm-as-a-verifier/) 21 Aug 2026
8. [AirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works](/blog/airllm-layer-wise-inference-low-vram/) 20 Aug 2026
9. [TrueForge Review: Is the Open-Source Agent Harness Production-Ready?](/blog/trueforge-agent-harness-review/) 20 Aug 2026
10. [Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks](/blog/agent-readable-website-llms-txt-markdown-mirrors/) 18 Aug 2026
11. [Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting Screenshots](/blog/qwen3-8-27b-self-hosted-computer-use-agents/) 18 Aug 2026
12. [Localized URLs Break hreflang: Keep One English Slug](/blog/english-slugs-vs-localized-urls-hreflang/) 18 Aug 2026
13. [Can an AI Agent Use Your Product, or Only Read About It?](/blog/can-an-ai-agent-use-your-product/) 18 Aug 2026
14. [Graft Review 2026: Do Agent Repo Maps Belong in Git?](/blog/graft-review-agent-repo-map/) 18 Aug 2026
15. [How Coding Agents Keep Token Bills in Check with Output Compression](/blog/codag-cost-control/) 17 Aug 2026
16. [Smarter Token Usage with Your AI Coding Agent](/blog/smarter-token-usage-with-your-ai-coding-agent/) 17 Aug 2026
17. [DeepSeek Harness Review: Is the Plugin Stack Production-Ready?](/blog/deepseek-harness-enterprise-review/) 16 Aug 2026
18. [Netflix's vLLM and Triton Stack: 7 Production Lessons](/blog/netflix-vllm-triton-inference-stack/) 16 Aug 2026
19. [OpenSandbox Review: Is Self-Hosting Worth It?](/blog/opensandbox-ai-agent-sandbox-review/) 16 Aug 2026
20. [Transformers.js Browser AI: When Local Inference Belongs in Your Product](/blog/transformers-js-browser-ai-guide/) 15 Aug 2026
21. [Cloudflare Kitesurf Review: Cost, Limits and Production Fit](/blog/cloudflare-kitesurf-browser-ai-agents/) 14 Aug 2026
22. [GitHub Spec Kit Review: Is It Worth the Process?](/blog/github-spec-kit-production-guide/) 14 Aug 2026
23. [Internal AI Agent Marketplace: A 2026 Enterprise Build Guide](/blog/internal-ai-agent-marketplace/) 13 Aug 2026
24. [How to Self-Host LiteLLM in Production: 2026 Guide](/blog/self-host-litellm-production-2026/) 13 Aug 2026
25. [AI-Ready Company Wiki: Architecture and Build Guide](/blog/ai-ready-company-wiki/) 13 Aug 2026
26. [Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide](/blog/linux-for-ai-agents/) 12 Aug 2026
27. [Does Claude Watermark Text? The 2026 API Answer](/blog/claude-text-watermark-api-2026/) 11 Aug 2026
28. [OpenKB Review: Knowledge Compiler vs RAG](/blog/openkb-review-vs-rag/) 11 Aug 2026
29. [Unsloth Desktop Review: A Private Local AI Workstation?](/blog/unsloth-desktop-local-ai-workstation-review/) 11 Aug 2026
30. [NeMo Switchyard 0.2: Agent Model Routing Without Training?](/blog/nemo-switchyard-model-router/) 11 Aug 2026
31. [Firecrawl AnyDoc Review: 14 Formats to Markdown](/blog/firecrawl-anydoc-review/) 10 Aug 2026
32. [MCP Cloud vs Manufact Cloud: MCP Hosting Guide](/blog/mcp-cloud-vs-manufact-cloud/) 10 Aug 2026
33. [Muse Glimmer 30B: Is Meta's Local Agent Model Production-Ready?](/blog/muse-glimmer-30b-local-agent-guide/) 10 Aug 2026
34. [How to Make AI Writing Sound Human with Agent Skills](/blog/ai-writing-agent-skills/) 9 Aug 2026
35. [NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?](/blog/nvidia-nooa-object-oriented-agents-review/) 9 Aug 2026
36. [OmniRoute AI Routing: Setup and Production Checklist](/blog/omniroute-ai-routing-setup/) 9 Aug 2026
37. [Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026](/blog/strix-ai-pentesting-pilot-guide-2026/) 9 Aug 2026
38. [Hyperagent Review: Cloud AI Agents Without a Server](/blog/hyperagent-review-cloud-ai-agents/) 9 Aug 2026
39. [Gemini Robotics 2: Whole-Body Control and the Pilot Decision](/blog/gemini-robotics-2-whole-body-control/) 7 Aug 2026
40. [Hark Handoff Review: The Agent That Actually Clicks](/blog/hark-handoff-computer-use-agent-review/) 7 Aug 2026
41. [Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?](/blog/meta-muse-code-pricing-contributor-tier/) 7 Aug 2026
42. [pdf-inspector Review: Route PDFs Before OCR](/blog/pdf-inspector-ocr-routing/) 6 Aug 2026
43. [PII Redaction Before LLM Prompts: A Practical Pipeline](/blog/pii-redaction-before-llm-prompts/) 6 Aug 2026
44. [Agent Reach Review: Costs, Security and Real Limits](/blog/agent-reach-open-source-review/) 6 Aug 2026
45. [Cloudflare Wallets for AI Agents: What Is Live?](/blog/cloudflare-wallets-ai-agents/) 5 Aug 2026
46. [Local Multimodal AI Coding Assistant: Voice, OCR and Privacy](/blog/local-multimodal-ai-coding-assistant/) 5 Aug 2026
47. [DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?](/blog/deepseek-v4-flash-0731-local-ai-pc/) 3 Aug 2026
48. [YC QM Agent Review: Is Quartermaster Ready for Work?](/blog/qm-ai-agent-harness-review/) 2 Aug 2026
49. [jcode vs Claude Code: Is the Rust Harness Worth Switching To?](/blog/jcode-vs-claude-code-rust-agent-harness/) 2 Aug 2026
50. [Lightpanda Browser for AI Agents: Production Guide](/blog/lightpanda-headless-browser-ai-agents/) 1 Aug 2026
51. [Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?](/blog/graph-engineering-ai-agents/) 1 Aug 2026
52. [Multi-Model AI Coding Agent Stack: A Team Buying Guide](/blog/multi-model-ai-coding-agent-stack-2026/) 1 Aug 2026
53. [Is MCP Stateless Now? Your Server Migration Checklist](/blog/mcp-stateless-server-migration-2026/) 31 Jul 2026
54. [MCP Is Not a Security Boundary: Protect Agent Data](/blog/mcp-security-boundary-data-level-access-control/) 29 Jul 2026
55. [Fine-Tune Gemma 4 Free with Unsloth and Colab](/blog/fine-tune-gemma-4-free-unsloth-colab/) 29 Jul 2026
56. [Can AI Agents Talk to Each Other? A Band Setup Guide](/blog/ai-agents-talk-to-each-other-band/) 29 Jul 2026
57. [Taalas HC1 Review: Is a Hardwired LLM ASIC Worth It?](/blog/taalas-hc1-llm-asic-review/) 28 Jul 2026
58. [LeanCTX Technical Field Report: 64.1% Less Context](/blog/lean-ctx-agency-experience/) 27 Jul 2026
59. [llmfit Guide: Which Local LLM Fits Your Hardware?](/blog/llmfit-local-llm-hardware-guide/) 27 Jul 2026
60. [CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code](/blog/claude-code-gpt-5-6-sol-cliproxyapi/) 26 Jul 2026
61. [Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality](/blog/miso-tts-self-hosted-vs-api/) 26 Jul 2026
62. [Enterprise MCP Authorization Architecture](/blog/enterprise-mcp-authorization-architecture/) 23 Jul 2026
63. [Cut RAG Vector Memory 16x: Is Data-Oblivious Quantization Ready for Production?](/blog/rag-vector-memory-quantization/) 23 Jul 2026
64. [Shared KV Cache Cut LLM Inference Latency 14x, With No New GPUs](/blog/shared-kv-cache-llm-inference-latency/) 23 Jul 2026
65. [Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?](/blog/lossless-llm-weight-compression-production/) 22 Jul 2026
66. [OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent](/blog/ai-agent-eval-sandbox-security-checklist/) 22 Jul 2026
67. [Cisco Antares Review: 1B Local AI for Vulnerability Localization](/blog/cisco-antares-local-vulnerability-localization/) 22 Jul 2026
68. [Meterless Review 2026: Is This AI Agent Context Layer Ready?](/blog/meterless-ai-agent-context-layer-review/) 22 Jul 2026
69. [NVIDIA Nemotron 3.5 ASR: Is Free Self-Hosted STT Ready for Voice Agents?](/blog/nvidia-nemotron-3-5-asr-production-review/) 19 Jul 2026
70. [Claude Code vs OpenCode: Which Costs Less for a Team in 2026?](/blog/claude-code-vs-opencode-team-cost-2026/) 19 Jul 2026
71. [Kimi K3 for EU Companies: API Cost, Data Risk, and a Pilot Plan](/blog/kimi-k3-eu-api-production-review/) 19 Jul 2026
72. [Mesh LLM Review: Can One Large LLM Run Across Multiple Computers?](/blog/mesh-llm-distributed-inference-multiple-computers/) 18 Jul 2026
73. [Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?](/blog/graphify-review-codebase-knowledge-graph/) 16 Jul 2026
74. [Bonsai 27B Review: Can a 27B LLM Really Run on a Phone?](/blog/bonsai-27b-phone-local-ai-review/) 16 Jul 2026
75. [Soofi S: Is Germany's Sovereign LLM Ready for Business?](/blog/soofi-s-european-sovereign-llm/) 16 Jul 2026
76. [AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days](/blog/ai-pilot-kill-or-scale-scorecard/) 16 Jul 2026
77. [T3MP3ST Review 2026: Can It Replace a Penetration Test?](/blog/t3mp3st-ai-red-teaming-review-2026/) 15 Jul 2026
78. [Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.](/blog/colibri-glm-5-2-consumer-hardware/) 14 Jul 2026
79. [Open Knowledge Format (OKF): The Enterprise Guide](/blog/open-knowledge-format-okf/) 12 Jul 2026
80. [AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills](/blog/ai-agent-cost-per-action-2026/) 9 Jul 2026
81. [When Local Models Beat APIs: A Break-Even Calculator for EU Companies](/blog/local-models-vs-apis-break-even-eu-2026/) 8 Jul 2026
82. [LLM Cost Calculator 2026: Cost per Task, Not Cost per Token](/blog/llm-cost-calculator-2026/) 8 Jul 2026
83. [Pxpipe Review: Can Images Cut Claude Code Token Costs 60%?](/blog/text-as-image-token-savings/) 3 Jul 2026
84. [Cheaper Per Token. More Expensive Per Answer.](/blog/cost-per-token-vs-cost-per-task/) 2 Jul 2026
85. [How to Use Claude Fable 5 in Claude Code](/blog/coding-with-claude-fable-5/) 2 Jul 2026
86. [Dario Declared War on Open Source. The Real War Is Over Your AI Bill.](/blog/open-source-ai-war-cost-2026/) 1 Jul 2026
87. [What an Internal AI Assistant Actually Costs in the DACH Region (2026)](/blog/internal-ai-assistant-cost-dach/) 29 Jun 2026
88. [LLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM](/blog/llm-gateway-router-comparison-2026/) 27 Jun 2026
89. [Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off](/blog/self-hosting-llms-eu-cost/) 26 Jun 2026
90. [Best Open-Weight LLMs 2026: DeepSeek vs Qwen vs Kimi vs GLM vs Llama](/blog/open-weight-llm-comparison-2026/) 25 Jun 2026
91. [The Bottleneck Was Never Intelligence. It Was Context.](/blog/ai-coding-agents-context-not-intelligence/) 23 Jun 2026
92. [ChatGPT Enterprise vs Copilot vs Custom RAG](/blog/chatgpt-enterprise-vs-copilot-vs-rag/) 22 Jun 2026
93. [MCP vs RAG vs Agent Skills vs Custom GPTs](/blog/mcp-vs-rag-vs-agent-skills-vs-custom-gpts/) 17 Jun 2026
94. [How to Cut LLM Token Costs in 2026](/blog/reduce-llm-token-costs-2026/) 15 Jun 2026
95. [AI Agent Pilot in 30/60/90 Days](/blog/ai-agent-pilot-30-60-90-days/) 14 Jun 2026
96. [Permissions-First RAG over SharePoint, Confluence, Drive](/blog/rag-permissions-sharepoint-confluence-drive/) 11 Jun 2026
97. [RAG Production-Readiness Checklist for EU Companies](/blog/rag-production-readiness-checklist-eu/) 8 Jun 2026
98. [When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge](/blog/llm-evaluation-cost-roi-production/) 1 Jun 2026
99. [Why 40% of AI Agent Projects Die](/blog/why-ai-agent-projects-get-cancelled/) 26 May 2026
100. [RAG vs Fine-Tuning vs Long-Context 2026](/blog/rag-vs-finetune-vs-longcontext-2026/) 26 May 2026
101. [LLM API Costs 2026. Architecture Shift](/blog/llm-api-costs-2026-architecture-shift/) 26 May 2026

## Structured Data

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@id": "https://wavect.io/#organization",
      "@type": [
        "Organization",
        "ProfessionalService",
        "LocalBusiness"
      ],
      "employee": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "founder": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "legalRepresentative": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "name": "Wavect GmbH",
      "subjectOf": {
        "@id": "https://wavect.io/verified-claims.json#dataset",
        "@type": "Dataset",
        "creator": {
          "@id": "https://wavect.io/#organization",
          "@type": [
            "Organization",
            "ProfessionalService",
            "LocalBusiness"
          ]
        },
        "description": "A machine-readable registry of quantitative and qualitative claims published by Wavect, with review dates, localized page appearances and public third-party citations where available.",
        "inLanguage": "en",
        "isAccessibleForFree": true,
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Wavect verified publication claims",
        "url": "https://wavect.io/verified-claims.json"
      },
      "url": "https://wavect.io/"
    },
    {
      "@id": "https://wavect.io/team/kevin-riedl/#person",
      "@type": "Person",
      "jobTitle": "Managing Director",
      "name": "Kevin Riedl",
      "sameAs": [
        "https://www.wikidata.org/wiki/Q139796365",
        "https://www.linkedin.com/in/wsdt",
        "https://github.com/wsdt"
      ],
      "url": "https://wavect.io/team/kevin-riedl/",
      "worksFor": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      }
    },
    {
      "@id": "https://wavect.io/team/christof-jori/#person",
      "@type": "Person",
      "jobTitle": "Managing Director",
      "name": "Christof Jori",
      "sameAs": [
        "https://www.wikidata.org/wiki/Q139796367",
        "https://www.linkedin.com/in/jocr77/",
        "https://github.com/jo-chris"
      ],
      "url": "https://wavect.io/team/christof-jori/",
      "worksFor": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      }
    },
    {
      "@id": "https://wavect.io/#website",
      "@type": "WebSite",
      "inLanguage": [
        "en",
        "de",
        "es",
        "zh"
      ],
      "name": "Wavect",
      "potentialAction": {
        "@type": "SearchAction",
        "query-input": "required name=search_term_string",
        "target": {
          "@type": "EntryPoint",
          "urlTemplate": "https://wavect.io/search/?q={search_term_string}"
        }
      },
      "publisher": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      },
      "url": "https://wavect.io/"
    },
    {
      "@id": "https://wavect.io/blog/topics/ai-agents/#webpage",
      "@type": "WebPage",
      "dateModified": "2026-08-05",
      "inLanguage": "en",
      "isPartOf": {
        "@id": "https://wavect.io/#website",
        "@type": "WebSite"
      },
      "lastReviewed": "2026-08-05",
      "url": "https://wavect.io/blog/topics/ai-agents/"
    }
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {
      "@type": "ListItem",
      "item": "https://wavect.io/",
      "name": "Home",
      "position": 1
    },
    {
      "@type": "ListItem",
      "item": "https://wavect.io/blog/overview/",
      "name": "Blog",
      "position": 2
    },
    {
      "@type": "ListItem",
      "item": "https://wavect.io/blog/topics/ai-agents/",
      "name": "AI and agents",
      "position": 3
    }
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "CollectionPage",
  "about": "AI and agents",
  "description": "Engineering, operating and evaluating AI systems, coding agents and model infrastructure.",
  "mainEntity": {
    "@type": "ItemList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "name": "Ox Alpha Free AI Model: Setup, Privacy and Buyer Guide",
        "position": 1,
        "url": "https://wavect.io/blog/ox-alpha-free-ai-model-guide-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust",
        "position": 2,
        "url": "https://wavect.io/blog/semantic-identity-rust-agent-edits/"
      },
      {
        "@type": "ListItem",
        "name": "LangChain Deep Agents Review: Is the Agent Harness Ready for Production?",
        "position": 3,
        "url": "https://wavect.io/blog/langchain-deep-agents-review/"
      },
      {
        "@type": "ListItem",
        "name": "Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?",
        "position": 4,
        "url": "https://wavect.io/blog/pika-audio-models-api-pricing-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide",
        "position": 5,
        "url": "https://wavect.io/blog/thunder-compute-gpu-virtualization-series-a/"
      },
      {
        "@type": "ListItem",
        "name": "OpenViking Review 2026: Is Filesystem Memory Production-Ready?",
        "position": 6,
        "url": "https://wavect.io/blog/openviking-agent-memory-review/"
      },
      {
        "@type": "ListItem",
        "name": "LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit",
        "position": 7,
        "url": "https://wavect.io/blog/llm-as-a-verifier/"
      },
      {
        "@type": "ListItem",
        "name": "AirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works",
        "position": 8,
        "url": "https://wavect.io/blog/airllm-layer-wise-inference-low-vram/"
      },
      {
        "@type": "ListItem",
        "name": "TrueForge Review: Is the Open-Source Agent Harness Production-Ready?",
        "position": 9,
        "url": "https://wavect.io/blog/trueforge-agent-harness-review/"
      },
      {
        "@type": "ListItem",
        "name": "Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks",
        "position": 10,
        "url": "https://wavect.io/blog/agent-readable-website-llms-txt-markdown-mirrors/"
      },
      {
        "@type": "ListItem",
        "name": "Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting Screenshots",
        "position": 11,
        "url": "https://wavect.io/blog/qwen3-8-27b-self-hosted-computer-use-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Localized URLs Break hreflang: Keep One English Slug",
        "position": 12,
        "url": "https://wavect.io/blog/english-slugs-vs-localized-urls-hreflang/"
      },
      {
        "@type": "ListItem",
        "name": "Can an AI Agent Use Your Product, or Only Read About It?",
        "position": 13,
        "url": "https://wavect.io/blog/can-an-ai-agent-use-your-product/"
      },
      {
        "@type": "ListItem",
        "name": "Graft Review 2026: Do Agent Repo Maps Belong in Git?",
        "position": 14,
        "url": "https://wavect.io/blog/graft-review-agent-repo-map/"
      },
      {
        "@type": "ListItem",
        "name": "How Coding Agents Keep Token Bills in Check with Output Compression",
        "position": 15,
        "url": "https://wavect.io/blog/codag-cost-control/"
      },
      {
        "@type": "ListItem",
        "name": "Smarter Token Usage with Your AI Coding Agent",
        "position": 16,
        "url": "https://wavect.io/blog/smarter-token-usage-with-your-ai-coding-agent/"
      },
      {
        "@type": "ListItem",
        "name": "DeepSeek Harness Review: Is the Plugin Stack Production-Ready?",
        "position": 17,
        "url": "https://wavect.io/blog/deepseek-harness-enterprise-review/"
      },
      {
        "@type": "ListItem",
        "name": "Netflix's vLLM and Triton Stack: 7 Production Lessons",
        "position": 18,
        "url": "https://wavect.io/blog/netflix-vllm-triton-inference-stack/"
      },
      {
        "@type": "ListItem",
        "name": "OpenSandbox Review: Is Self-Hosting Worth It?",
        "position": 19,
        "url": "https://wavect.io/blog/opensandbox-ai-agent-sandbox-review/"
      },
      {
        "@type": "ListItem",
        "name": "Transformers.js Browser AI: When Local Inference Belongs in Your Product",
        "position": 20,
        "url": "https://wavect.io/blog/transformers-js-browser-ai-guide/"
      },
      {
        "@type": "ListItem",
        "name": "Cloudflare Kitesurf Review: Cost, Limits and Production Fit",
        "position": 21,
        "url": "https://wavect.io/blog/cloudflare-kitesurf-browser-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "GitHub Spec Kit Review: Is It Worth the Process?",
        "position": 22,
        "url": "https://wavect.io/blog/github-spec-kit-production-guide/"
      },
      {
        "@type": "ListItem",
        "name": "Internal AI Agent Marketplace: A 2026 Enterprise Build Guide",
        "position": 23,
        "url": "https://wavect.io/blog/internal-ai-agent-marketplace/"
      },
      {
        "@type": "ListItem",
        "name": "How to Self-Host LiteLLM in Production: 2026 Guide",
        "position": 24,
        "url": "https://wavect.io/blog/self-host-litellm-production-2026/"
      },
      {
        "@type": "ListItem",
        "name": "AI-Ready Company Wiki: Architecture and Build Guide",
        "position": 25,
        "url": "https://wavect.io/blog/ai-ready-company-wiki/"
      },
      {
        "@type": "ListItem",
        "name": "Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide",
        "position": 26,
        "url": "https://wavect.io/blog/linux-for-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Does Claude Watermark Text? The 2026 API Answer",
        "position": 27,
        "url": "https://wavect.io/blog/claude-text-watermark-api-2026/"
      },
      {
        "@type": "ListItem",
        "name": "OpenKB Review: Knowledge Compiler vs RAG",
        "position": 28,
        "url": "https://wavect.io/blog/openkb-review-vs-rag/"
      },
      {
        "@type": "ListItem",
        "name": "Unsloth Desktop Review: A Private Local AI Workstation?",
        "position": 29,
        "url": "https://wavect.io/blog/unsloth-desktop-local-ai-workstation-review/"
      },
      {
        "@type": "ListItem",
        "name": "NeMo Switchyard 0.2: Agent Model Routing Without Training?",
        "position": 30,
        "url": "https://wavect.io/blog/nemo-switchyard-model-router/"
      },
      {
        "@type": "ListItem",
        "name": "Firecrawl AnyDoc Review: 14 Formats to Markdown",
        "position": 31,
        "url": "https://wavect.io/blog/firecrawl-anydoc-review/"
      },
      {
        "@type": "ListItem",
        "name": "MCP Cloud vs Manufact Cloud: MCP Hosting Guide",
        "position": 32,
        "url": "https://wavect.io/blog/mcp-cloud-vs-manufact-cloud/"
      },
      {
        "@type": "ListItem",
        "name": "Muse Glimmer 30B: Is Meta's Local Agent Model Production-Ready?",
        "position": 33,
        "url": "https://wavect.io/blog/muse-glimmer-30b-local-agent-guide/"
      },
      {
        "@type": "ListItem",
        "name": "How to Make AI Writing Sound Human with Agent Skills",
        "position": 34,
        "url": "https://wavect.io/blog/ai-writing-agent-skills/"
      },
      {
        "@type": "ListItem",
        "name": "NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?",
        "position": 35,
        "url": "https://wavect.io/blog/nvidia-nooa-object-oriented-agents-review/"
      },
      {
        "@type": "ListItem",
        "name": "OmniRoute AI Routing: Setup and Production Checklist",
        "position": 36,
        "url": "https://wavect.io/blog/omniroute-ai-routing-setup/"
      },
      {
        "@type": "ListItem",
        "name": "Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026",
        "position": 37,
        "url": "https://wavect.io/blog/strix-ai-pentesting-pilot-guide-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Hyperagent Review: Cloud AI Agents Without a Server",
        "position": 38,
        "url": "https://wavect.io/blog/hyperagent-review-cloud-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Gemini Robotics 2: Whole-Body Control and the Pilot Decision",
        "position": 39,
        "url": "https://wavect.io/blog/gemini-robotics-2-whole-body-control/"
      },
      {
        "@type": "ListItem",
        "name": "Hark Handoff Review: The Agent That Actually Clicks",
        "position": 40,
        "url": "https://wavect.io/blog/hark-handoff-computer-use-agent-review/"
      },
      {
        "@type": "ListItem",
        "name": "Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?",
        "position": 41,
        "url": "https://wavect.io/blog/meta-muse-code-pricing-contributor-tier/"
      },
      {
        "@type": "ListItem",
        "name": "pdf-inspector Review: Route PDFs Before OCR",
        "position": 42,
        "url": "https://wavect.io/blog/pdf-inspector-ocr-routing/"
      },
      {
        "@type": "ListItem",
        "name": "PII Redaction Before LLM Prompts: A Practical Pipeline",
        "position": 43,
        "url": "https://wavect.io/blog/pii-redaction-before-llm-prompts/"
      },
      {
        "@type": "ListItem",
        "name": "Agent Reach Review: Costs, Security and Real Limits",
        "position": 44,
        "url": "https://wavect.io/blog/agent-reach-open-source-review/"
      },
      {
        "@type": "ListItem",
        "name": "Cloudflare Wallets for AI Agents: What Is Live?",
        "position": 45,
        "url": "https://wavect.io/blog/cloudflare-wallets-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Local Multimodal AI Coding Assistant: Voice, OCR and Privacy",
        "position": 46,
        "url": "https://wavect.io/blog/local-multimodal-ai-coding-assistant/"
      },
      {
        "@type": "ListItem",
        "name": "DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?",
        "position": 47,
        "url": "https://wavect.io/blog/deepseek-v4-flash-0731-local-ai-pc/"
      },
      {
        "@type": "ListItem",
        "name": "YC QM Agent Review: Is Quartermaster Ready for Work?",
        "position": 48,
        "url": "https://wavect.io/blog/qm-ai-agent-harness-review/"
      },
      {
        "@type": "ListItem",
        "name": "jcode vs Claude Code: Is the Rust Harness Worth Switching To?",
        "position": 49,
        "url": "https://wavect.io/blog/jcode-vs-claude-code-rust-agent-harness/"
      },
      {
        "@type": "ListItem",
        "name": "Lightpanda Browser for AI Agents: Production Guide",
        "position": 50,
        "url": "https://wavect.io/blog/lightpanda-headless-browser-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?",
        "position": 51,
        "url": "https://wavect.io/blog/graph-engineering-ai-agents/"
      },
      {
        "@type": "ListItem",
        "name": "Multi-Model AI Coding Agent Stack: A Team Buying Guide",
        "position": 52,
        "url": "https://wavect.io/blog/multi-model-ai-coding-agent-stack-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Is MCP Stateless Now? Your Server Migration Checklist",
        "position": 53,
        "url": "https://wavect.io/blog/mcp-stateless-server-migration-2026/"
      },
      {
        "@type": "ListItem",
        "name": "MCP Is Not a Security Boundary: Protect Agent Data",
        "position": 54,
        "url": "https://wavect.io/blog/mcp-security-boundary-data-level-access-control/"
      },
      {
        "@type": "ListItem",
        "name": "Fine-Tune Gemma 4 Free with Unsloth and Colab",
        "position": 55,
        "url": "https://wavect.io/blog/fine-tune-gemma-4-free-unsloth-colab/"
      },
      {
        "@type": "ListItem",
        "name": "Can AI Agents Talk to Each Other? A Band Setup Guide",
        "position": 56,
        "url": "https://wavect.io/blog/ai-agents-talk-to-each-other-band/"
      },
      {
        "@type": "ListItem",
        "name": "Taalas HC1 Review: Is a Hardwired LLM ASIC Worth It?",
        "position": 57,
        "url": "https://wavect.io/blog/taalas-hc1-llm-asic-review/"
      },
      {
        "@type": "ListItem",
        "name": "LeanCTX Technical Field Report: 64.1% Less Context",
        "position": 58,
        "url": "https://wavect.io/blog/lean-ctx-agency-experience/"
      },
      {
        "@type": "ListItem",
        "name": "llmfit Guide: Which Local LLM Fits Your Hardware?",
        "position": 59,
        "url": "https://wavect.io/blog/llmfit-local-llm-hardware-guide/"
      },
      {
        "@type": "ListItem",
        "name": "CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code",
        "position": 60,
        "url": "https://wavect.io/blog/claude-code-gpt-5-6-sol-cliproxyapi/"
      },
      {
        "@type": "ListItem",
        "name": "Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality",
        "position": 61,
        "url": "https://wavect.io/blog/miso-tts-self-hosted-vs-api/"
      },
      {
        "@type": "ListItem",
        "name": "Enterprise MCP Authorization Architecture",
        "position": 62,
        "url": "https://wavect.io/blog/enterprise-mcp-authorization-architecture/"
      },
      {
        "@type": "ListItem",
        "name": "Cut RAG Vector Memory 16x: Is Data-Oblivious Quantization Ready for Production?",
        "position": 63,
        "url": "https://wavect.io/blog/rag-vector-memory-quantization/"
      },
      {
        "@type": "ListItem",
        "name": "Shared KV Cache Cut LLM Inference Latency 14x, With No New GPUs",
        "position": 64,
        "url": "https://wavect.io/blog/shared-kv-cache-llm-inference-latency/"
      },
      {
        "@type": "ListItem",
        "name": "Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?",
        "position": 65,
        "url": "https://wavect.io/blog/lossless-llm-weight-compression-production/"
      },
      {
        "@type": "ListItem",
        "name": "OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent",
        "position": 66,
        "url": "https://wavect.io/blog/ai-agent-eval-sandbox-security-checklist/"
      },
      {
        "@type": "ListItem",
        "name": "Cisco Antares Review: 1B Local AI for Vulnerability Localization",
        "position": 67,
        "url": "https://wavect.io/blog/cisco-antares-local-vulnerability-localization/"
      },
      {
        "@type": "ListItem",
        "name": "Meterless Review 2026: Is This AI Agent Context Layer Ready?",
        "position": 68,
        "url": "https://wavect.io/blog/meterless-ai-agent-context-layer-review/"
      },
      {
        "@type": "ListItem",
        "name": "NVIDIA Nemotron 3.5 ASR: Is Free Self-Hosted STT Ready for Voice Agents?",
        "position": 69,
        "url": "https://wavect.io/blog/nvidia-nemotron-3-5-asr-production-review/"
      },
      {
        "@type": "ListItem",
        "name": "Claude Code vs OpenCode: Which Costs Less for a Team in 2026?",
        "position": 70,
        "url": "https://wavect.io/blog/claude-code-vs-opencode-team-cost-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Kimi K3 for EU Companies: API Cost, Data Risk, and a Pilot Plan",
        "position": 71,
        "url": "https://wavect.io/blog/kimi-k3-eu-api-production-review/"
      },
      {
        "@type": "ListItem",
        "name": "Mesh LLM Review: Can One Large LLM Run Across Multiple Computers?",
        "position": 72,
        "url": "https://wavect.io/blog/mesh-llm-distributed-inference-multiple-computers/"
      },
      {
        "@type": "ListItem",
        "name": "Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?",
        "position": 73,
        "url": "https://wavect.io/blog/graphify-review-codebase-knowledge-graph/"
      },
      {
        "@type": "ListItem",
        "name": "Bonsai 27B Review: Can a 27B LLM Really Run on a Phone?",
        "position": 74,
        "url": "https://wavect.io/blog/bonsai-27b-phone-local-ai-review/"
      },
      {
        "@type": "ListItem",
        "name": "Soofi S: Is Germany's Sovereign LLM Ready for Business?",
        "position": 75,
        "url": "https://wavect.io/blog/soofi-s-european-sovereign-llm/"
      },
      {
        "@type": "ListItem",
        "name": "AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days",
        "position": 76,
        "url": "https://wavect.io/blog/ai-pilot-kill-or-scale-scorecard/"
      },
      {
        "@type": "ListItem",
        "name": "T3MP3ST Review 2026: Can It Replace a Penetration Test?",
        "position": 77,
        "url": "https://wavect.io/blog/t3mp3st-ai-red-teaming-review-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.",
        "position": 78,
        "url": "https://wavect.io/blog/colibri-glm-5-2-consumer-hardware/"
      },
      {
        "@type": "ListItem",
        "name": "Open Knowledge Format (OKF): The Enterprise Guide",
        "position": 79,
        "url": "https://wavect.io/blog/open-knowledge-format-okf/"
      },
      {
        "@type": "ListItem",
        "name": "AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills",
        "position": 80,
        "url": "https://wavect.io/blog/ai-agent-cost-per-action-2026/"
      },
      {
        "@type": "ListItem",
        "name": "When Local Models Beat APIs: A Break-Even Calculator for EU Companies",
        "position": 81,
        "url": "https://wavect.io/blog/local-models-vs-apis-break-even-eu-2026/"
      },
      {
        "@type": "ListItem",
        "name": "LLM Cost Calculator 2026: Cost per Task, Not Cost per Token",
        "position": 82,
        "url": "https://wavect.io/blog/llm-cost-calculator-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Pxpipe Review: Can Images Cut Claude Code Token Costs 60%?",
        "position": 83,
        "url": "https://wavect.io/blog/text-as-image-token-savings/"
      },
      {
        "@type": "ListItem",
        "name": "Cheaper Per Token. More Expensive Per Answer.",
        "position": 84,
        "url": "https://wavect.io/blog/cost-per-token-vs-cost-per-task/"
      },
      {
        "@type": "ListItem",
        "name": "How to Use Claude Fable 5 in Claude Code",
        "position": 85,
        "url": "https://wavect.io/blog/coding-with-claude-fable-5/"
      },
      {
        "@type": "ListItem",
        "name": "Dario Declared War on Open Source. The Real War Is Over Your AI Bill.",
        "position": 86,
        "url": "https://wavect.io/blog/open-source-ai-war-cost-2026/"
      },
      {
        "@type": "ListItem",
        "name": "What an Internal AI Assistant Actually Costs in the DACH Region (2026)",
        "position": 87,
        "url": "https://wavect.io/blog/internal-ai-assistant-cost-dach/"
      },
      {
        "@type": "ListItem",
        "name": "LLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM",
        "position": 88,
        "url": "https://wavect.io/blog/llm-gateway-router-comparison-2026/"
      },
      {
        "@type": "ListItem",
        "name": "Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off",
        "position": 89,
        "url": "https://wavect.io/blog/self-hosting-llms-eu-cost/"
      },
      {
        "@type": "ListItem",
        "name": "Best Open-Weight LLMs 2026: DeepSeek vs Qwen vs Kimi vs GLM vs Llama",
        "position": 90,
        "url": "https://wavect.io/blog/open-weight-llm-comparison-2026/"
      },
      {
        "@type": "ListItem",
        "name": "The Bottleneck Was Never Intelligence. It Was Context.",
        "position": 91,
        "url": "https://wavect.io/blog/ai-coding-agents-context-not-intelligence/"
      },
      {
        "@type": "ListItem",
        "name": "ChatGPT Enterprise vs Copilot vs Custom RAG",
        "position": 92,
        "url": "https://wavect.io/blog/chatgpt-enterprise-vs-copilot-vs-rag/"
      },
      {
        "@type": "ListItem",
        "name": "MCP vs RAG vs Agent Skills vs Custom GPTs",
        "position": 93,
        "url": "https://wavect.io/blog/mcp-vs-rag-vs-agent-skills-vs-custom-gpts/"
      },
      {
        "@type": "ListItem",
        "name": "How to Cut LLM Token Costs in 2026",
        "position": 94,
        "url": "https://wavect.io/blog/reduce-llm-token-costs-2026/"
      },
      {
        "@type": "ListItem",
        "name": "AI Agent Pilot in 30/60/90 Days",
        "position": 95,
        "url": "https://wavect.io/blog/ai-agent-pilot-30-60-90-days/"
      },
      {
        "@type": "ListItem",
        "name": "Permissions-First RAG over SharePoint, Confluence, Drive",
        "position": 96,
        "url": "https://wavect.io/blog/rag-permissions-sharepoint-confluence-drive/"
      },
      {
        "@type": "ListItem",
        "name": "RAG Production-Readiness Checklist for EU Companies",
        "position": 97,
        "url": "https://wavect.io/blog/rag-production-readiness-checklist-eu/"
      },
      {
        "@type": "ListItem",
        "name": "When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge",
        "position": 98,
        "url": "https://wavect.io/blog/llm-evaluation-cost-roi-production/"
      },
      {
        "@type": "ListItem",
        "name": "Why 40% of AI Agent Projects Die",
        "position": 99,
        "url": "https://wavect.io/blog/why-ai-agent-projects-get-cancelled/"
      },
      {
        "@type": "ListItem",
        "name": "RAG vs Fine-Tuning vs Long-Context 2026",
        "position": 100,
        "url": "https://wavect.io/blog/rag-vs-finetune-vs-longcontext-2026/"
      },
      {
        "@type": "ListItem",
        "name": "LLM API Costs 2026. Architecture Shift",
        "position": 101,
        "url": "https://wavect.io/blog/llm-api-costs-2026-architecture-shift/"
      }
    ],
    "numberOfItems": 101
  },
  "name": "AI and agents",
  "url": "https://wavect.io/blog/topics/ai-agents/"
}
```