{
  "schema_version": "2.1",
  "slug": "pguso-ai-agents-from-scratch",
  "name": "pguso/ai-agents-from-scratch",
  "agent_url": "https://github.com/pguso/ai-agents-from-scratch",
  "repo_url": "https://github.com/pguso/ai-agents-from-scratch",
  "category": "AI Agent",
  "run_id": "run-pguso-ai-agents-from-scratch-repotrack-2026-07-16",
  "run_at": "2026-07-16T13:14:00Z",
  "source": "hlido-repo-track",
  "review_track": "repo-surface",
  "evidence_tier": "repo-surface",
  "methodology_note": "Repo-surface track: this product is distributed as a repository (library/CLI) with no web product surface, so the score derives ONLY from measurable public-repository signals — documentation, licensing, maintenance activity, releases, traction, agent-consumability. Each checklist item carries its evidence. Score ceiling 82/100: VITAL requires hands-on behavioral testing that repo signals cannot provide. Replaces a 2026-06/07 stub that carried a default score with no evidence.",
  "checklist": [
    {
      "id": "repo_reachable",
      "task": "Repository is publicly reachable",
      "required": true,
      "pass": true,
      "evidence": "GH API 200 for pguso/ai-agents-from-scratch"
    },
    {
      "id": "readme_present",
      "task": "README documents the product (≥500 chars)",
      "required": true,
      "pass": true,
      "evidence": "README length 14496"
    },
    {
      "id": "license_present",
      "task": "License declared",
      "required": true,
      "pass": true,
      "evidence": "MIT"
    },
    {
      "id": "install_documented",
      "task": "Install/usage instructions present",
      "required": true,
      "pass": true,
      "evidence": "install/usage section found in README"
    },
    {
      "id": "active_12mo",
      "task": "Maintained: pushed within 12 months and not archived",
      "required": true,
      "pass": true,
      "evidence": "last push 46d ago"
    },
    {
      "id": "releases_present",
      "task": "Tagged releases exist",
      "required": false,
      "pass": false,
      "evidence": "no releases"
    },
    {
      "id": "community_traction",
      "task": "Community traction (≥50 stars)",
      "required": false,
      "pass": true,
      "evidence": "4406 stars"
    },
    {
      "id": "ci_or_tests",
      "task": "CI workflows present",
      "required": false,
      "pass": false,
      "evidence": "no .github/workflows"
    },
    {
      "id": "recent_commit_90d",
      "task": "Actively developed (push within 90 days)",
      "required": false,
      "pass": true,
      "evidence": "last push 46d ago"
    },
    {
      "id": "agent_consumable",
      "task": "Agent-consumable surface documented (MCP config or CLI install)",
      "required": false,
      "pass": false,
      "evidence": "none found"
    }
  ],
  "repo_metrics": {
    "stars": 4406,
    "forks": 639,
    "open_issues": 10,
    "archived": false,
    "pushed_at": "2026-05-31T08:52:06Z",
    "license": "MIT",
    "language": "JavaScript"
  },
  "evidence_urls": [
    "https://github.com/pguso/ai-agents-from-scratch",
    "https://api.github.com/repos/pguso/ai-agents-from-scratch"
  ],
  "laddoo_score": 80,
  "score": 80,
  "tier": "STEADY",
  "confidence": "medium",
  "summary": "pguso/ai-agents-from-scratch — Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.. Repo-surface review: measured from the public repository (4406 stars, MIT, last push 2026-05-31); not hands-on tested.",
  "staleness_after": "2026-10-14",
  "editor": "Hlido Editor",
  "editorial_method": "repo-surface-track+editorial-narrative-v2",
  "hlido_opinion": {
    "headline": "A popular, honest 'build AI agents from scratch' teaching repo — high-value for learning, but a curriculum, not a deployable agent.",
    "body": "With 4.4k stars, an MIT license and a substantial README, this is a well-received educational resource for understanding how agents actually work — function calling, memory and ReAct patterns, on local LLMs with no black boxes. It is important to set expectations from the repository surface: there are no tagged releases and no CI, because this is a learning codebase rather than a maintained product. You read it and rebuild from it; you don't depend on it as a package. Judged on those terms it is strong and does exactly what it promises. Repo-surface read.",
    "voice": "Hlido Editor",
    "as_of": "2026-07-23",
    "editor_signature_pending": true
  },
  "tier_rationale": "STEADY (80). Strong traction, a permissive MIT license, and a substantial, purpose-fit README clear STEADY for an educational resource. It is intentionally not a product — no releases, no CI, no packaged surface — so the higher bands, which assume an operable product, don't apply.",
  "what_it_does_well": [
    "MIT-licensed with strong traction (4.4k stars) for an educational repo",
    "Substantial README (~14.5k chars)",
    "Teaches real, transferable patterns (function calling, memory, ReAct)",
    "Local-LLM, no-black-box approach that builds genuine understanding"
  ],
  "what_it_fails_at": [
    "Not a product or deployable agent — no releases, no CI, no packaged surface",
    "No agent-consumable interface",
    "Value is pedagogical, not operational"
  ],
  "best_for": [
    "Engineers learning how agents work under the hood",
    "Teams wanting a from-scratch reference before adopting a framework"
  ],
  "not_recommended_for": [
    "Production deployment",
    "Anyone needing a supported or packaged agent",
    "Agent pipelines needing a programmatic API"
  ],
  "red_flags": [],
  "compared_to": [],
  "agent_relevance": {
    "has_api": false,
    "has_cli": false,
    "has_mcp": false,
    "has_webhook": false,
    "has_sdk": false,
    "behavioral_testable": false,
    "agent_integration_path": "An educational reference codebase — not intended for agent consumption. No hands-on behavioral test performed.",
    "agent_friendly_score": 2
  },
  "enriched_at": "2026-07-23",
  "enriched_by": "R-publish",
  "marking_signal": {
    "marking_statement": false,
    "detection_tool": false,
    "cop_signatory": null,
    "evidence_url": null,
    "checked_at": "2026-07-25",
    "source": "engine-browser-marking-retrofit"
  },
  "evidence_images": {
    "run_id": "run-5921345201e65402-github-com",
    "base": "https://images.hlido.eu/reviews/pguso-ai-agents-from-scratch/run-5921345201e65402-github-com",
    "files": [
      "home.png"
    ],
    "urls": [
      "https://images.hlido.eu/reviews/pguso-ai-agents-from-scratch/run-5921345201e65402-github-com/home.png"
    ],
    "verified_at": "2026-07-31T09:31:39.713Z",
    "verified_count": 1,
    "note": "Screenshots captured by the Hlido engine during the reviewed run, served from R2. Every URL here was HEAD-verified at the timestamp above. `run_id` is the ENGINE run id — it differs from `scorecard.run_id` and is the only one these keys resolve under."
  }
}