Conducks
CONDUCKSPROTOCOL

Structural code intelligence · No embeddings

Exact answers
about your code.

Conducks parses your repo into a structural graph with Tree-sitter, so AI agents and developers get graph-verified facts, not fuzzy embedding guesses.

Embedding search
“getUserById is somewhere in services…”
Conducks · example output
getUserById · src/services/user.ts:42
called by 7 places · risk 0.31
Mirror, a map of your project
View

Demo

See it work

Mirror: hover a folder, click inside, read what uses what

Terminal: status, query, impact, audit

Structural Intelligence

Structural
Intelligence

Conducks turns your source into a graph of symbols and the edges between them, calls, imports, inheritance, that you can query exactly.

Tree-sitter
DuckDB

Resilient extraction

When a grammar query fails to compile, Conducks falls back to a regex extractor, so a broken parse still yields file and symbol structure instead of nothing.

Weighted pathfinding

Finds the call and import paths between any two symbols using weighted edges, surfacing critical paths and blast radius across the dependency graph.

Impact analysis

See everything that depends on a symbol before you change it.

Mirror, folder and file view
View

Map Detail

Graph
Detail

Mirror opens on one picture of your project: folders as boxes, links as arrows, six health checks across the top. Click a folder to go inside it, down to single files. Hover to see what a change can reach.

Granular Mapping

Decompose complex inheritance chains and import graphs into actionable structural intelligence.

Side panel

A side panel lists who uses the folder from outside, what it uses, and the files other code leans on most.

Workspace

Unified
Workspace

Conducks keeps the graph in sync with your editor as you work, so structural drift shows up the moment it happens.

Real-Time Sync

conducks watch re-indexes files as they change on disk, so the graph follows your edits.

Drift Detection

conducks audit reports violations of the custom rules you define for your repository.

Engineering Workspace
View

Taxonomy

9-Layer
Taxonomy

Conducks maps every construct across all languages to a universal structural hierarchy, from ecosystems to atomic data points.

Universal Taxonomy Map
View
L0
Ecosystem
Cross-Repo
L1
Repository
Services
L2
Namespace
Modules
L3
Unit
Files
L4
Infra
Routes
L5
Structure
Classes
L6
Behavior
Methods
L7
Atom
Variables
L8
Data
Records

Language Support

Language
Support

13 language grammars. The matrix shows the feature coverage for the five main languages.

FeatureTypeScriptPythonRustGoJava
Imports✓✓✓✓✓
Named Bindings✓✓✓✓✓
Exports✓✓✓✓·
Heritage✓✓✓✓✓
Type Annotations✓✓✓✓✓
Constructor Inference✓✓✓✓✓
Config✓✓✓✓·
Frameworks✓✓✓✓✓
Entry Points✓✓✓✓✓

AlsoThe other grammars: JavaScript · TSX · C# · C · C++ · PHP · Ruby · Swift.

Governance

Agentic
Governance

The Conducks MCP server gives agents a 6-signal risk breakdown for any symbol, so your AI can weigh a change before making it.

Risk Decomposition

Gravity, Complexity, Entropy, Churn, FanOut, and Debt are distilled into a single actionable risk score.

Execution Tracing

Agents can trace execution paths to understand exactly how data flows through your system.

Agent Governance Hub
View

Architecture

Three-Layer
Architecture

Intelligence Layer

30 CLI commands and 12 MCP tools providing analysis, metrics, and governance.

Reflection Layer

Language-specific lenses powered by 13 Tree-sitter grammars and a regex fallback extractor.

Core Layer

Atomic DuckDB storage, weighted graph pathfinding, and the structural registry hub.

Intelligence
Reflection
Core Graph

Roadmap

What's Next

Our roadmap to the ultimate agentic governance platform.

Completed

TS / Python / Rust / Go / Java extraction
Real-time Mirror dashboard
12 MCP tools
Regex fallback extractor

In Progress

Query templates (query --mode template)
Filter Builder for conducks_query
DAAC Community Clustering UI

Planned

import type Edge Detection (GVR gap)
Dynamic Dispatch Resolver
Deep Traversal Precompute

Get Started

Initialization

Two commands. Then your agent can use the tools.

01

Install

Node.js 20+ and Git. Local process, no cloud, no account.

$ npm i -g conducks
02

Set up your project

In your project, conducks setup registers the MCP server in every agent found on the machine, installs the skills, and builds the first graph. Restart your agent and it can use the tools.

$ conducks setup
$ conducks analyze
# after code changes

Another MCP client? Add {"command": "conducks", "args": ["mcp"]} to its config.

FAQ

Common
Questions

What is Conducks?

Conducks parses your source code with Tree-sitter into a structural graph stored in a local DuckDB vault. AI agents and developers can then ask exact questions about a codebase, where a symbol lives, what calls it, what breaks if it changes, and get graph-verified answers.

How is it different from embedding or RAG code search?

Embedding search returns approximate matches and can point to the wrong file or a symbol that does not exist. Conducks answers from a deterministic AST graph instead: exact symbol locations, real call and import paths, and no guessing.

Which languages does Conducks support?

Conducks ships 13 language grammars: C, C++, C#, Go, Java, JavaScript, PHP, Python, Ruby, Rust, Swift, TSX, and TypeScript.

Does my code leave my machine?

No. Conducks runs locally and stores the graph in a .conducks/ folder inside your project. There is no cloud, no account, and no embeddings sent anywhere.

How do AI agents use Conducks?

Through a Model Context Protocol (MCP) server that exposes 12 tools, including query, trace, impact, explain, and audit, so an agent can navigate and reason about your codebase over JSON-RPC.

Build
Better

GitHub Source