Skip to main content

VibeTrace: The Code Intelligence & Execution Trace MCP

CI PyPI License: MIT Python 3.10+

Philosophy: Structural Truth > Statistical Guessing

VibeTrace is an intelligent code analysis and navigation engine that treats your codebase as a living execution nervous system. Instead of relying solely on probabilistic embedding models that miss call hierarchies or hallucinate links, VibeTrace builds a deterministic relational graph of your code using Tree-sitter AST extraction, SQLite FTS5 lexical ranking, and bidirectional BFS pathfinding with exact 1-indexed call-site line numbers.

Designed from the ground up for AI Coding Agents (Antigravity, Claude, Cursor, Cline) and developers working across massive codebases.


⚡ Key Capabilities

  • 🚀 1-Click Workspace Setup (vibetrace init): Configures local .gitignore rules, bundles and installs the vibetrace-navigator agent skill, sets up an isolated project database, and performs initial indexing.
  • 🗺️ Bidirectional BFS Tracepaths (vibetrace trace): Finds the shortest and alternative call chains between any two functions, classes, or HTTP endpoints with exact file.py:L<line> coordinates.
  • 🔍 4-Stream Hybrid Search (vibetrace search): Reciprocal Rank Fusion (RRF) combining deterministic AST symbol matching, SQLite FTS5 BM25 lexical ranking, PageRank centrality, and optional 256d Matryoshka vectors (EmbeddingGemma 2).
  • ✂️ Surgical Source Slicing (vibetrace slice): Returns only the exact lines of a symbol and its outgoing callee signatures, saving 85–95% of LLM context window tokens.
  • 🌳 Top-Down Recursive Call Hierarchy (vibetrace call-tree): Generates an ASCII call tree from an entry point down to leaf database or system primitives with cycle detection.
  • 💥 Transitive Blast Radius (vibetrace impact): 3-level caller impact analysis (Direct, Secondary, Deep) to evaluate the ripple effect before refactoring.
  • 🤖 Native Model Context Protocol (vibetrace mcp): 10 purpose-built MCP tools that empower AI coding agents to navigate, trace, and inspect code surgically.
  • 🌐 Map Room 2.0 Visualizer (vibetrace serve): Interactive @xyflow/react + ELK.js web graph visualizer with live agent radar tracking.

💻 Supported Languages

VibeTrace provides first-class multi-language AST extraction:

Language Extensions Support Level Features
Python .py 🔥 Full Classes, Functions, Imports, Wildcards, Decorators, Visibility, Type hints
JavaScript / TypeScript .js, .jsx, .ts, .tsx 💎 High ES Imports, CommonJS require() destructuring, Dynamic import(), Interfaces, Classes, JSX elements
Go .go ✅ Solid Packages, Structs, Interfaces, Receivers, Constructor types, var specs
Rust .rs ✅ Solid Crates, mod item; submodules, mod.rs barrel resolution, Traits, Impls
Java .java ✅ Solid Packages, Classes, Interfaces, Method-local variable types, Call hierarchies
C / C++ .c, .cpp, .h, .hpp 🛠️ Solid Functions, Classes, Structs, Preprocessor includes
C# / Ruby / PHP .cs, .rb, .php 🛠️ Generic Structural symbol extraction

🚀 Quick Start

Installation

uv tool install vibetrace

Via pip

pip install vibetrace

Optional: Local Vector Embeddings (EmbeddingGemma 2 + sqlite-vec)

uv tool install "vibetrace[embeddings]"

Initializing Any Project

Navigate to any codebase and run:

cd /path/to/my-project

# 1-click onboarding: updates .gitignore, installs agent skill, indexes codebase
vibetrace init

That's it! vibetrace.db is created locally inside that project and never shared across projects.


Core CLI Usage

# 1. 4-Stream Hybrid Search
vibetrace search "authentication flow"

# 2. Bidirectional Execution Trace
vibetrace trace "handleLogin" "verifyPassword"

# Trace web route to backend service handler
vibetrace trace "GET /api/users" "queryUsersFromDB"

# Bookmark and re-run saved traces
vibetrace trace "handleLogin" "verifyPassword" --save-as "AuthFlow"
vibetrace trace --saved "AuthFlow"

# 3. Surgical Code Slicing (token-efficient)
vibetrace slice "AuthService.login"

# 4. Top-Down Recursive Call Tree
vibetrace call-tree "main" --depth 3

# 5. Blast Radius Impact Analysis
vibetrace impact src/auth/service.py

# 6. Launch Map Room Web Visualizer (http://localhost:8000)
vibetrace serve

🤖 Configuring AI Agents (Claude Desktop, Cursor, Antigravity, Cline)

Add VibeTrace to your agent's MCP configuration (claude_desktop_config.json, antigravity.json, or Cursor MCP settings):

{
  "mcpServers": {
    "vibetrace": {
      "command": "vibetrace",
      "args": ["mcp", "--path", "/path/to/your/project"]
    }
  }
}

The agent will automatically gain access to:

  • vibetrace_semantic_search
  • vibetrace_trace_path
  • vibetrace_get_code_slice
  • vibetrace_impact_analysis
  • vibetrace_find_references
  • vibetrace_get_call_tree

🛠️ Development & Contributing

git clone https://github.com/serguei9090/VibeTrace.git
cd VibeTrace

# Install dependencies
uv sync

# Run the full test suite (164 tests)
uv run pytest

# Lint and format
uv run ruff check .
uv run ruff format .
uv run pyright

📜 License

MIT License. Copyright (c) 2026 Serguei.

Metadata

Release files for vibetrace 0.1.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for vibetrace 0.1.4
File Size Uploaded Provenance Actions
vibetrace-0.1.4.tar.gz 953.7 kB With provenance Details for vibetrace-0.1.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for vibetrace 0.1.4
File Interpreter ABI Platform Actions
vibetrace-0.1.4-py3-none-any.whl Python 3 none any Details for vibetrace-0.1.4-py3-none-any.whl

Total release size: 1.0 MB

Release files / vibetrace-0.1.4.tar.gz

Download URL vibetrace-0.1.4.tar.gz
Size 953.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d7dceca7b3304305feb4b7764010959890ff2f7ce540bf4eae2661a15c58159a
BLAKE2b-256 checksum
How to use checksums
29a79d1b5f2cf4c0a480c2d5ea5841c7121dc3fb3830432e42b8965ebbc9567e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2026.

Transparency log

Release files / vibetrace-0.1.4-py3-none-any.whl

Download URL vibetrace-0.1.4-py3-none-any.whl
Size 91.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3c3bb47d9fd9576de4938bf3a7a562a1fd305efa3d72f4ed91258d1a2304d6b7
BLAKE2b-256 checksum
How to use checksums
5a18074be9947577b4262f6e68a27ef0a56ef6cca70308b599bf160ad6835d67
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2026.

Transparency log

Security for vibetrace 0.1.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for vibetrace-0.1.4.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page