Skip to main content

Skill-Orchestrated Context Intelligence Engine for AI coding agents

Project description

V.I.S.O.R. Logo

V.I.S.O.R.

Your AI coding assistant wastes time reading the wrong files. V.I.S.O.R. fixes that.

CI PyPI Open VSX License: MIT Python

Visual Intelligence System for Orchestrated Reasoning

V.I.S.O.R. is a smart helper for your AI coding assistant. It reads your code, understands how files are connected, and gives your AI exactly the right context โ€” so it spends less time searching and more time solving.

It works with Antigravity, VS Code, Cursor, Claude Code, and Windsurf.

V.I.S.O.R HUD โ€” 3D codebase visualization in your IDE

๐ŸŽฌ See it in action

V.I.S.O.R HUD in action

๐Ÿ’ฌ What Can You Do With It?

Just talk to your AI agent like normal. V.I.S.O.R. works behind the scenes to find the right code automatically.

Find a bug

"Find the code related to the login crash"

Without V.I.S.O.R., your AI reads 20+ files blindly. With V.I.S.O.R., it gets the 3โ€“5 most relevant files instantly.

Understand your code

"Explain how authentication works in this project"

V.I.S.O.R. traces the full auth flow across files โ€” showing your AI exactly which functions call which, and in what order.

Refactor safely

"What files would break if I change the database client?"

V.I.S.O.R. runs an impact analysis and shows every file that depends on the one you're changing.

Check for stale context

"Are the files you read earlier still up to date?"

V.I.S.O.R. checks file hashes and warns your AI if something changed since it last looked.


๐Ÿš€ Install (2 minutes)

Step 1: The One-Command Install

You no longer need to manually copy and paste JSON configuration files. V.I.S.O.R. includes an interactive setup wizard that automatically configures your IDE.

# This will auto-detect Cursor, VS Code, or Antigravity and set up the MCP connection
uvx visor-mcp init

Note: Claude Code handles installation natively via claude mcp add visor -- uvx visor-mcp.

Prefer manual installation? Click here for raw configs

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "visor": {
      "command": "uvx",
      "args": ["visor-mcp"]
    }
  }
}

VS Code / Antigravity (.vscode/mcp.json):

{
  "servers": {
    "visor": {
      "command": "uvx",
      "args": ["visor-mcp"]
    }
  }
}

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "visor": {
      "command": "uvx",
      "args": ["visor-mcp"]
    }
  }
}

Prerequisite: You need uv installed. uvx (included with uv) handles virtual environments and dependencies automatically โ€” no manual setup needed.

Step 2 (Optional): Install the 3D HUD Extension

Search for "V.I.S.O.R. HUD" in your editor's extension panel, or install from Open VSX. This gives you a live 3D visualization of your codebase graph right in the sidebar.


๐Ÿค” The Proof: Why You Need V.I.S.O.R.

Every time your AI agent searches for context natively, it relies on brute-force text search (grep or ripgrep). This wastes tokens, misses dependencies, and hallucinates context.

Here is what happens when you ask an AI to "refactor the database client":

AI Without V.I.S.O.R. โŒ AI With V.I.S.O.R. ๐ŸŽฏ
Searches db_client and reads 24 files blindly. Instantly retrieves the db_client.py AST node.
Uses 14,500 tokens filling the context window. Uses 1,800 tokens (an 87% reduction).
Misses src/auth.py because the word "database" wasn't explicitly mentioned in the file. Identifies src/auth.py because it detects a hard dependency graph link.
Result: A broken refactor because it didn't update the authentication service that depended on the database. Result: A perfect refactor because it had complete, surgically precise context.

โœจ Key Features

๐Ÿง  Smart Context Engine

The heart of V.I.S.O.R. When your AI asks "find code related to X", it doesn't just search by text โ€” it thinks:

  • Understands your question โ€” Detects if you're fixing a bug, exploring, or refactoring, and adjusts accordingly
  • Scores code 5 different ways โ€” Combines meaning similarity, name matching, file proximity, code connections, and how recently the file was changed
  • Explains its choices โ€” Every code snippet includes a plain-English reason for why it was picked
  • Saves tokens โ€” Shows you exactly how many tokens it saved vs. a naive approach

โšก Built-in Skills

Pre-built strategies that change how V.I.S.O.R. finds code. Think of them as "modes":

Skill What it does
bug-fixer Focuses on recently changed files and dependency chains
architecture-explainer Casts a wide net to help explain how things connect
refactor-assistant Traces all dependencies so you know what might break
performance-optimizer Finds hotspots by prioritizing recently modified code

You can also create your own custom skills.

๐Ÿ” Code Understanding

V.I.S.O.R. reads your code structure (classes, functions, imports) in 9 languages:

Language File Types
Python .py
TypeScript .ts, .tsx
JavaScript .js, .jsx
Go .go
Rust .rs
Java .java
C .c, .h
C++ .cpp, .cc, .cxx, .hpp

Want more? Adding a new language is ~15 lines of code. See CONTRIBUTING.md.

๐Ÿ“Š 3D HUD (VS Code / Antigravity)

A real-time interactive graph of your codebase โ€” right in your editor sidebar. Shows:

  • Your code as connected nodes you can explore
  • Live stats: how many tokens your AI is using, how many files are indexed
  • Drift alerts when files change under your AI

โš ๏ธ Drift Detection

Knows when your AI is looking at outdated code. Compares file hashes and warns before your AI makes decisions on stale information.


๐Ÿ“ฆ Example: Finding a Bug

$ visor fix "authentication crash"
============================================================
  V.I.S.O.R. Context Intelligence Engine
============================================================
  Query:  authentication crash
  Intent: BUG_FIX
  Skill:  bug-fixer
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
  Tokens without V.I.S.O.R.: 11,400
  Tokens with V.I.S.O.R.:    2,180
  Reduction:                  80.9%
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
  Selected 4 nodes (truncated=False):

  [2.85]  src/auth/jwt.py:verify_token
          โ†’ Matched query token in symbol name
          โ†’ Co-located in same file as top semantic hit
          โ†’ Recently modified file (boosted)

  [2.12]  src/auth/middleware.py:auth_guard
          โ†’ Reachable via dependency chain
          โ†’ Semantic similarity (score: 0.375)

============================================================

What happened: Instead of your AI reading every file in the project, V.I.S.O.R. found the 4 most relevant functions and saved 80% of the tokens.


๐Ÿ› ๏ธ CLI Commands

You can also use V.I.S.O.R. from the terminal:

visor fix "login crash on null user"         # Find bug-related code
visor explain "database client"              # Understand how a module works
visor context "how is auth handled"          # General code search
visor trace src/auth.py src/db/client.py     # Show how two files are connected
visor drift                                  # Check for changed files

๐Ÿ› ๏ธ MCP Tools (for AI Agents)

V.I.S.O.R. gives your AI agent 17 tools across 5 categories. Your AI uses these automatically โ€” you don't need to call them manually.

Category Tools
๐Ÿง  Intelligence build_context โ€” the main tool that finds and ranks relevant code
๐Ÿ” Search search_codebase, get_symbol_context, get_file_context
๐Ÿ—บ๏ธ Graph get_dependency_chain, impact_analysis, trace_route, dead_code_detection
โš ๏ธ Drift get_drift_report
๐Ÿงฉ Memory & Skills store_memory, add_custom_skill, list_custom_skills, delete_custom_skill
๐Ÿ“Š HUD get_architecture_map, get_telemetry, set_hud_focus

See docs/MCP_TOOLS.md for the full API reference.


๐Ÿ“š Documentation

Document What's Inside
docs/ARCHITECTURE.md How V.I.S.O.R. works under the hood
docs/MCP_TOOLS.md Complete reference for all 17 tools
docs/FAQ.md Common questions answered
docs/TROUBLESHOOTING.md Fixing common problems
CONTRIBUTING.md How to add languages, tools, and skills
CHANGELOG.md What changed in each version

๐Ÿค Contributing

V.I.S.O.R. welcomes contributions! The easiest way to start is by adding a new language โ€” it's ~15 lines and a great first issue.

git clone https://github.com/dibun75/visor.git
cd visor && uv sync --dev
uv run pytest tests/ -v

See CONTRIBUTING.md for the full guide.


๐ŸŒ Works With

IDE Support How to Set Up
Claude Code โœ… Full claude mcp add visor -- uvx visor-mcp
Cursor โœ… Full ~/.cursor/mcp.json
Claude Desktop โœ… Full claude_desktop_config.json
VS Code โœ… Full .vscode/mcp.json + HUD Extension
Antigravity โœ… Full .vscode/mcp.json + HUD Extension
Windsurf โœ… Full Plugin raw config

License

MIT ยฉ Arunav Mandal

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

visor_mcp-1.1.0.tar.gz (796.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

visor_mcp-1.1.0-py3-none-any.whl (806.3 kB view details)

Uploaded Python 3

File details

Details for the file visor_mcp-1.1.0.tar.gz.

File metadata

  • Download URL: visor_mcp-1.1.0.tar.gz
  • Upload date:
  • Size: 796.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for visor_mcp-1.1.0.tar.gz
Algorithm Hash digest
SHA256 263aa518c70da9c26ddafea5e9d8108ff9316fc04d7a9436685e65f69b61fd2b
MD5 1eb0dacaad153d153bafc017d141a1cc
BLAKE2b-256 b29a5eba6facbaa0791c9dd01afec96c0faa3f88c2b7d1e3c049b2833489336c

See more details on using hashes here.

Provenance

The following attestation bundles were made for visor_mcp-1.1.0.tar.gz:

Publisher: publish.yml on dibun75/visor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file visor_mcp-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: visor_mcp-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 806.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for visor_mcp-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 84e4722aa5d1540988b56a4b8ee2d84aed4e2c7ef2705cc32729fa4f76bf6f3f
MD5 1ab9ead83a80a082fc94e25289d25c89
BLAKE2b-256 8849e0511429f537902db48fe57224bcf3731d15d2458e9b9708ccc24f25258f

See more details on using hashes here.

Provenance

The following attestation bundles were made for visor_mcp-1.1.0-py3-none-any.whl:

Publisher: publish.yml on dibun75/visor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page