indxr
Active·★ 66·MIT·Updated 2026-04-07
★ Trending★ API Integration
A fast codebase indexer and MCP server for AI coding agents.
indxr gives AI coding agents a structural map of codebases, reducing token costs by ~5x compared to reading full files. It supports 27 languages, provides a 22-tool MCP server for live queries, and features incremental caching, git structural diffing, and dependency graphs. Setup is one-command with `indxr init` for popular AI coding agents.
#ai#ai-agents#claude-code#mcp-server#mcp-servers#openai#tokens
01
Features
0127 languages support (tree-sitter for 8, regex for 19)
0222-tool MCP server for live codebase queries
03Token-aware truncation with ~5x reduction
04Git structural diffing at declaration level
05Dependency graphs (DOT, Mermaid, JSON)
02
Compatibility
Claude Code
Claude Code
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
03
Quick start
1
$ cargo install indxr
04
Use cases
↳AI coding agents understanding a codebase without full file reads
↳Debugging and exploring dependencies between files and symbols
↳Automated codebase health reporting and complexity analysis
05
Alternatives
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
context-mode★ 16.0k
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
Related searches
Comments
Log in to leave a comment
- CCameron MartinezMay 5, 2026
Fast codebase indexing for AI coding agents significantly improves context quality
- OOakley ThompsonMar 24, 2026
Used to speed up code navigation in large monorepos, indexing is fast even on big codebases
- KKai ZhangMar 5, 2026
The MCP server integration means indexed knowledge is immediately available in agent workflows