Houseofmvps/codesight

Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.

What it solves

AI assistants often waste thousands of tokens during a conversation because they must manually explore a codebase to understand its structure, routes, and schema. codesight reduces this overhead by pre-compiling a codebase into a compact, high-precision context map that AI tools can read instantly.

How it works

The tool uses a combination of Abstract Syntax Tree (AST) precision for TypeScript and battle-tested regex detection for other languages. It scans the project root to detect routes, schema models, UI components, and environment variables across 30+ frameworks and 14 ORM parsers.

It provides three layers of token reduction:

  1. Base Scan: Replaces manual file exploration with a single compiled map.
  2. Wiki Knowledge Base: Compiles a persistent, narrative layer of markdown files (e.g., auth.md, database.md) so the AI can read only the specific article relevant to a question rather than the full map.
  3. Knowledge Mode: Maps non-code context, such as ADRs, meeting notes, and Obsidian vaults, into a KNOWLEDGE.md primer.

Who it’s for

Developers using AI coding assistants like Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, or Aider who want to reduce token usage, lower costs, and speed up AI responses.

Highlights

  • Zero Dependencies: Runs via a single npx call with no configuration or API keys required.
  • Broad Language Support: Works with TypeScript, JavaScript, Python, Go, Ruby, Elixir, Java, Kotlin, Rust, PHP, Dart, Swift, and C#.
  • MCP Integration: Includes 14 Model Context Protocol (MCP) tools to allow AI assistants to interact with the codebase map and wiki directly.
  • High Efficiency: Claims up to 91x total token reduction by combining base scans with targeted wiki access.

Related

  • Project
    cocoindex-io/cocoindex-code

    cocoindex‑code is a real, open‑source tool that builds an AST‑based semantic index of a codebase and lets you search it with natural‑language queries. Install via pipx (full or slim variant), run `ccc init` and `ccc index`, then use `ccc search` or integrate the provided `ccc` skill/MCP server with Claude, Grok, Oh My Pi, Codex, etc. Docker images are also available for reproducible deployments.

  • Project
    tirth8205/code-review-graph

    code‑review‑graph is a Python package that parses a repository with Tree‑sitter, stores the AST‑derived nodes/edges in a SQLite graph, and serves a minimal, blast‑radius slice of that graph to any MCP‑compatible AI coding assistant. It reduces per‑question token usage by ~63×, supports 30+ languages (including notebooks), offers incremental updates, framework‑aware edges for PHP/Laravel and Java/Spring, a GitHub Action for CI risk‑scored reviews, and optional semantic embeddings. Benchmarks show large token savings and an average F1 of 0.69 for impact analysis. The tool is aimed at developers and teams using LLM‑based code reviewers who need precise, low‑overhead context.

  • Project
    alexgreensh/token-optimizer

    Token Optimizer is a zero‑dependency Python tool that plugs into AI coding assistants (Claude Code, Copilot, etc.) to automatically compress command output, search results, JSON, file diffs and other “structural” data, saving tokens and money. It adds smart checkpoints so savings survive model compaction, scores context quality live, stores a local SQLite audit trail, and provides slash‑commands (e.g., `/token‑optimizer`, `/token‑coach`) for reports and dashboards. Installation is a one‑time plugin add, after which it runs silently in the background.

  • Project
    elara-labs/code-context-engine

    A local codebase indexing engine that reduces AI coding assistant costs by replacing full-file reads with targeted semantic search and retrieval.

  • Project
    giancarloerra/SocratiCode

    A local, zero-config codebase intelligence engine that provides AI assistants with deep semantic understanding, dependency graphs, and symbol-level impact analysis for large repositories.