{
  "schema_version": "2.0",
  "slug": "muvon-octocode",
  "name": "Octocode (muvon)",
  "agent_url": "https://octomind.run/product/octocode/",
  "category": "Coding",
  "run_id": "run-r-publish-v2-muvon-octocode-2026-08-26",
  "run_at": "2026-08-26T09:00:00Z",
  "editor": "Hlido Editor",
  "editorial_method": "public-surface-tier-1+editorial-narrative-v2",
  "methodology_version": "2026.05",
  "methodology_url": "/methodology/public-surface-tier-1/",
  "score": 78,
  "tier": "STEADY",
  "laddoo_score": 78,
  "confidence": "high",
  "hlido_opinion": {
    "headline": "A Rust, local-first semantic code-search and knowledge-graph tool that turns a codebase into a queryable graph and exposes it to AI assistants over MCP — sub-2-second indexing, 12+ languages, Apache-2.0.",
    "body": "This Octocode (by muvon, distinct from the octocode.ai tool of the same name) builds a cross-file knowledge graph from your codebase using tree-sitter AST parsing and vector embeddings, then lets you query it in natural language — 'how does authentication work?' returns relevant code across files, and dependency queries return callers, callees and related types. It is local-first, Apache-2.0, claims sub-2-second indexing and 12+ language support, and ships an MCP server exposing three clear tools to Claude, Cursor and Windsurf: `semantic_search`, `view_signatures` (signatures without full implementations — a real token-saver for agents) and `graphrag` (relationship/dependency queries). The framing is honest about the problem it targets — grep fails on conceptual queries, and AI assistants lack structural awareness — and the GitHub star signal (a few hundred) is a modest but real adoption marker. The ceiling on the score is that the differentiators (indexing speed, semantic quality, the '200M free tokens/mo' figure) are vendor claims on the marketing surface rather than measured here, and the embeddings approach means quality depends on the embedding model and repo shape. Note the name collision: an unrelated evidence-first research tool also called 'Octocode' exists — pick by mechanism (this one is embeddings + knowledge graph; the other is cited tool-based retrieval).",
    "voice": "Hlido Editor",
    "as_of": "2026-08-26",
    "editor_signature_pending": true
  },
  "tier_rationale": "STEADY (78) because it is genuinely agent-native (MCP with semantic_search/view_signatures/graphrag), local-first, Apache-2.0, multi-language, and solves a real gap grep cannot. Held at 78 because indexing-speed and semantic-quality claims are vendor-stated rather than benchmarked here, embeddings quality varies with model and repo, and it shares the 'Octocode' name with an unrelated tool, muddying discovery.",
  "what_it_does_well": [
    "Semantic search understands meaning, not keywords — conceptual queries return relevant code even without matching terms",
    "Builds a cross-file knowledge graph via tree-sitter AST parsing — callers, callees, imports and type references",
    "MCP server exposes semantic_search, view_signatures and graphrag to Claude, Cursor and Windsurf",
    "`view_signatures` returns signatures without full implementations — token-efficient context for agents",
    "Local-first and Apache-2.0, brew-installable, 12+ languages, claimed sub-2-second indexing",
    "Honest positioning about where grep and unaided assistants fall short"
  ],
  "what_it_fails_at": [
    "Indexing-speed, language-count and '200M free tokens/mo' figures are vendor claims on the marketing surface, not measured in this review",
    "Semantic-search quality depends on the embedding model and codebase shape",
    "Shares the name 'Octocode' with an unrelated evidence-first research tool — discovery ambiguity",
    "Modest public adoption signal (a few hundred GitHub stars) — young tool"
  ],
  "best_for": [
    "Developers onboarding to an unfamiliar codebase who want natural-language answers spanning files",
    "AI pair-programming setups that need semantic context and dependency graphs handed to the assistant over MCP",
    "Teams that want local-first, Apache-2.0 code intelligence with no hosted index"
  ],
  "not_recommended_for": [
    "Teams that need a commercially supported, SLA-backed product",
    "Workflows that prefer cited, tool-driven retrieval over embeddings-based ranking"
  ],
  "red_flags": [
    "Name collision: an unrelated 'Octocode' (octocode.ai, evidence-first cited research) exists from a different author — confirm you are installing muvon/tap/octocode if this is the tool you want."
  ],
  "compared_to": [
    {
      "slug": "oraios-serena",
      "verdict_diff": "Serena uses LSP for exact symbol operations; this Octocode uses tree-sitter + embeddings for semantic search and a knowledge graph. Serena for precise language-server-grade navigation, Octocode for meaning-based cross-file queries.",
      "preferred_for_axis": "semantic-embeddings-vs-lsp-precision"
    },
    {
      "slug": "deusdata-codebase-memory-mcp",
      "verdict_diff": "Both give an agent codebase awareness over MCP; codebase-memory-mcp persists memory, while Octocode indexes into a semantic knowledge graph queried live. Memory for recall, Octocode for structural/semantic search.",
      "preferred_for_axis": "semantic-graph-vs-persistent-memory"
    }
  ],
  "evidence_urls": [
    {
      "claim": "Semantic code search + cross-file knowledge graph via tree-sitter AST and vector embeddings",
      "source": "octomind.run/product/octocode ('Transform your codebase into a queryable semantic knowledge graph'; 'Builds cross-file dependency maps using tree-sitter AST parsing')",
      "tested_at": "2026-08-26",
      "verified": true
    },
    {
      "claim": "MCP server exposes semantic_search, view_signatures and graphrag to AI assistants",
      "source": "octomind.run/product/octocode ('MCP Tools ... semantic_search ... view_signatures ... graphrag')",
      "tested_at": "2026-08-26",
      "verified": true
    },
    {
      "claim": "Local-first, Apache-2.0, 12+ languages, brew-installable",
      "source": "octomind.run/product/octocode ('Tree-sitter AST · Vector Embeddings · Local-First · Apache 2.0'; 'brew install muvon/tap/octocode'; '12+ LANGUAGES')",
      "tested_at": "2026-08-26",
      "verified": true
    }
  ],
  "agent_relevance": {
    "has_api": false,
    "has_cli": true,
    "has_mcp": true,
    "has_webhook": false,
    "has_sdk": false,
    "behavioral_testable": true,
    "agent_integration_path": "Runs as an MCP server exposing semantic_search, view_signatures and graphrag to Claude, Cursor, Windsurf and any MCP client, giving the assistant meaning-based search and dependency-graph queries over a locally indexed codebase. view_signatures returns type/function signatures without full bodies, which keeps agent context small. Also usable directly as a local CLI.",
    "agent_friendly_score": 8
  },
  "checklist": [
    {
      "id": "homepage_loads",
      "pass": true,
      "required": true,
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "primary_value_prop",
      "pass": true,
      "required": true,
      "evidence": "Semantic code search + knowledge graph exposed to AI assistants over MCP",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "cta_present",
      "pass": true,
      "required": true,
      "evidence": "Install / brew install muvon/tap/octocode / GitHub",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "pricing_or_access",
      "pass": true,
      "required": false,
      "evidence": "Apache-2.0, local-first; brew-installable; 200M free tokens/mo claimed",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "evidence_or_demo",
      "pass": true,
      "required": false,
      "evidence": "MCP tool list, feature descriptions, use-case walkthroughs",
      "tested_at": "2026-08-26T09:00:00Z"
    }
  ],
  "summary": "A Rust, local-first semantic code-search and knowledge-graph tool that turns a codebase into a queryable graph and exposes it to AI assistants over MCP — sub-2-second indexing, 12+ languages, Apache-2.0.",
  "_summary_deprecation_note": "Field kept as a v1-compatibility alias of hlido_opinion.headline. New consumers should read hlido_opinion.{headline,body,voice,as_of}.",
  "staleness_after": "2026-11-24",
  "review_age_days_at_publish": 0,
  "next_review_due_at": "2026-11-24",
  "attestation_url": "/data/attestations/muvon-octocode.json",
  "signature_pending": true,
  "source": "r-publish-editorial-v2",
  "marking_signal": {
    "checked_at": "2026-08-26",
    "source": "r-publish-editorial-enrich",
    "not_applicable": true,
    "note": "Octocode (muvon) produces code-search results and graph queries, not synthetic media for publication. Article-50 marking obligations do not apply. Recorded as not applicable."
  },
  "evidence_images": {
    "run_id": "run-31adba7018e90b1f-octomind-run",
    "base": "https://images.hlido.eu/reviews/muvon-octocode/run-31adba7018e90b1f-octomind-run",
    "files": [
      "home.png"
    ],
    "urls": [
      "https://images.hlido.eu/reviews/muvon-octocode/run-31adba7018e90b1f-octomind-run/home.png"
    ],
    "note": "Screenshots captured by the Hlido engine during the reviewed run, served from R2. `run_id` is the ENGINE run id — it differs from `scorecard.run_id` and is the only one these keys resolve under."
  },
  "pricing_facts": {
    "schema": "pricing-facts/1",
    "model": [
      "open-source"
    ],
    "free_tier": true,
    "pricing_disclosed": {
      "pass": true,
      "evidence": "Apache-2.0, local-first; brew-installable; 200M free tokens/mo claimed",
      "tested_at": "2026-08-26"
    },
    "last_verified": "2026-08-26",
    "basis": "Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page.",
    "derived_at": "2026-08-27"
  }
}