codeix
About
Fast semantic code search for AI agents — find symbols, references, and callers across any codebase. Pre-built index committed to git, instant queries via MCP.
Details
- Author
- montanetech
- Categories
- Developer Tools, Search, Other
Jump to
Setup
Install codeix in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/montanetech/codeix
Follow the installation instructions in the repository README, then restart your MCP client.
codeix.dev· Fast semantic code search for AI agents — find symbols, references, and callers across any codebase.
codeix # start MCP server, watch for changes codeix build # parse source files, write .codeindex codeix -r ~/project build # build from a specific directory
AI coding agents spend most of their token budgetfindingcode before they canwork onit. They grep, read files, grep again, backtrack. On a large codebase the agent might burn thousands of tokens just locating the right function — or worse, miss it entirely and hallucinate.
Codeix gives the agent a pre-built map of your codebase.One structured query returns the symbol name, file, line range, signature, and parent — no scanning, no guessing.
- Committed to git— the index is a.codeindexdirectory you commit with your code. Clone the repo, the index is already there. No re-indexing.
- Shareable— library authors can ship.codeindexin their npm/PyPI/crates.io package. Consumers get instant navigation of dependencies.
- Composable— the MCP server auto-discovers dependency indexes and mounts them. Query your code and your dependencies in one place.
- Structured for LLMs— symbols have kinds, signatures, parent relationships, and line ranges. The agent gets exactly what it needs in one tool call instead of piecing it together from raw text.
- Prose search—search --scope texttargets comments, docstrings, and string literals specifically. Find TODOs, find the error message a user reported, find what a function's docstring says — without noise from code.
- Fast— builds in seconds, queries in milliseconds. Rust + tree-sitter + in-memory SQLite FTS5 under the hood.
An open, portable format for structured code indexing. Plain JSONL files you commit alongside your code — git-friendly diffs, human-readable withgrepandjq, no binary blobs.
.codeindex/ index.json # manifest: version, name, languages files.jsonl # one line per source file (path, lang, hash, line count) symbols.jsonl # one line per symbol (functions, classes, imports, with signatures) texts.jsonl # one line per comment, docstring, string literal
Any tool that can parse JSON can consume a.codeindex. Codeix builds it usingtree-sitter, and AI agents query it throughMCP(Model Context Protocol).
{"file":"src/main.py","name":"os","kind":"import","line":[1,1]} {"file":"src/main.py","name":"Config","kind":"class","line":[22,45]} {"file":"src/main.py","name":"Config.__init__","kind":"method","line":[23,30],"parent":"Config","sig":"def __init__(self, path: str, debug: bool = False)"} {"file":"src/main.py","name":"main","kind":"function","line":[48,60],"sig":"def main(args: list[str]) -> int"}
Include.codeindexin your package and every developer who depends on you gets instant navigation of your API — no setup, no re-indexing.
Works with Git repos, npm, PyPI, and crates.io.
Seven tools, zero setup. The agent queries immediately — no init, no config, no refresh.
Launchcodeixfrom any directory. It walks downward and treats every directory containing.git/as a separate project — each gets its own.codeindex.
Works uniformly for single repos, monorepos, sibling repos, and git submodules. No config needed.
Tree-sitter grammars, feature-gated at compile time:
Markdown files are parsed forheadings(both ATX#and Setext underline styles) which are indexed assectionsymbols with hierarchical parent-child relationships — enabling TOC extraction and document structure navigation.
Fenced code blocks are extracted ascodetext entries, parented to their containing section.
HTML, Vue, Svelte, and Astro files are preprocessed to extract embedded<script>blocks, which are then parsed with the JavaScript or TypeScript grammar:
Line numbers in the index point to the original file, not the extracted script block.
# npm / npx — run without installing npx codeix # pip / uvx — run without installing uvx codeix # Rust cargo install codeix # Homebrew brew install codeix # Or build from source git clone https://github.com/montanetech/codeix.git cd codeix cargo build --release
All channels install the same single binary. No runtime dependencies.
# Build the index for the current project codeix build # Build from a specific directory (discovers all git repos below) codeix -r ~/projects build # Start MCP server (default command, watches for changes) codeix # Or explicitly codeix serve codeix serve --no-watch # Serve from a specific directory codeix -r ~/projects serve
Add to your MCP client config (e.g. Claude Desktop, Cursor):
{ "mcpServers": { "codeix": { "command": "codeix" } } }
- Local only— no network, no API keys, works offline and air-gapped
- Deterministic— same source always produces the same index (clean diffs)
- Composable— dependency indexes are auto-discovered and mounted at query time
- Minimal surface— 7 query tools, zero management plumbing
Seedocs/architecture.mdfor the full set of architecture decision records.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Persistent code index using Tree-sitter for fast, precise code search. Replaces grep with ~50 token responses instead of 2000+.
A platform-agnostic code analysis library with semantic search capabilities and MCP server support.
A server for code indexing, searching, and analysis, enabling LLMs to interact with code repositories.
Advanced code search and transformation powered by ugrep and ast-grep for modern development workflows.
Structural codebase indexer with 17 query tools. 87% token reduction. Zero dependencies.
Local-first code intelligence MCP server. Hybrid BM25 + ONNX vector search, symbol-level impact analysis, diff-aware PR review with risk scoring, and persistent memory tied to git state. 20 tools, MIT licensed.
AI-to-AI code review platform — Claude, Codex, and Gemini cross-check each other via MCP, REST API, and CLI for consensus-based results.
A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.
Orchestrates a dual-AI engineering loop where a Primary AI plans and implements, while a Review AI validates and reviews, with continuous feedback for optimal code quality. Supports custom AI pairing (Claude, Codex, Gemini, etc.)
Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
