Back to browse
GitHub Repository

Zero-config grammar-free structural codebase indexer and MCP server. ~0.16s builds, sub-ms queries, 4.7MB binary.

5 starsRust

I built a codebase analysis MCP: Stria

by microbass·Jun 1, 2026·3 points·1 comment

AI Analysis

●●●BangerWizardryShip ItSolve My Problem

Indexes the Linux kernel in 80 seconds without AST parsers, where tree-sitter tools fail.

Strengths
  • Grammar-free phrase extraction eliminates maintenance burden of language-specific tree-sitter grammars.
  • Bundled SQLite and static binary mean zero configuration and easy deployment anywhere.
  • Lazy context expansion saves tokens by loading function bodies only when agents request.
Weaknesses
  • Grammar-free approach may lack semantic precision compared to full AST parsing for refactors.
  • MCP server ecosystem is still nascent, limiting utility outside specific agent frameworks.
Target Audience

Backend developers, AI agent builders, teams with large polyglot repositories

Similar To

Sourcegraph Cody · Cursor · Continue

Similar Projects

AI/ML●●Solid

CocoIndex-Code open source embedded AST-based code MCP

AST-based code indexing saves tokens but Cursor and Continue already do this.

Solve My ProblemNiche Gem
georgehe9
213mo ago
Developer Tools●●●Banger

Srclight – Deep code indexing MCP server (FTS5 and Tree-sitter)

Tree-sitter + FTS5 + MCP = tokens saved for AI agents to actually code, not search.

WizardryBig BrainZero to One
srclight
103mo ago