wavescope-mcp
Active·★ 45·Updated 2026-09-02
WaveScope MCP offers wavelet-based multi-resolution context management for Large Language Models, providing a zoomable view of code files. It intelligently identifies structural boundaries and important regions, allowing LLMs to access relevant code sections without loading entire files.
#LLM Context Management#Wavelet Transform#Code Analysis#Multi-resolution#Structural Signal Processing#Developer Tool#Context Window Optimization
01
Features
01Provides a zoomable, multi-resolution code context view for LLMs.
02Analyzes code structure using wavelet transforms to identify important structural boundaries.
03Optimizes LLM context windows by extracting and presenting only relevant code snippets.
04Compares structural changes in code between Git revisions to highlight additions, removals, or shifts.
05Computes multi-scale code complexity heatmaps, useful for review prioritization and context budgeting.
02
Compatibility
Node.js
Runtime
Verified via docs
TypeScript
Language
Verified via docs
Python
Code Language
Verified via docs
TypeScript
Code Language
Verified via docs
JavaScript
Code Language
Verified via docs
Go
Code Language
Verified via docs
03
Quick start
1
$ npm install -g wavescope-mcp
04
Use cases
↳Enhancing Large Language Models' comprehension of extensive codebases by providing structured, relevant context.
↳Assisting developers with intelligent code navigation, review prioritization, and identification of complex or critical regions.
↳Intelligent context budgeting for LLM prompts, focusing on irregular or critical code sections while summarizing boilerplate.
↳Analyzing structural code differences between Git revisions to gain clearer insights into changes and their impact.
05
Alternatives
caura-memclaw★ 504
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
llm-context.py★ 307
Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.
Yggdrasil★ 22
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
sigmap★ 646
~97% token reduction for AI coding sessions — zero deps, 33 languages, MCP server
Comments
Log in to leave a comment
No comments yet. Be the first!