ce) — a local code graph for you and your AI agent
AI agents see files, not architecture. CodeExplorer (ce) gives your AI coding agents (Claude Code, Cursor, GitHub Copilot, Windsurf, Cline) and engineering teams a live cross-service map of every API, queue, and database in VS Code & MCP—plus hard architectural guardrails in CI.
✓ Live Architecture Map in VS Code • ✓ Graph Context for Agents (CLI + MCP) • ✓ CI Architecture Gates • ✓ 100% Local SQLite Graph
It indexes polyglot source files, project manifests, HTTP/gRPC/GraphQL endpoints, message broker topologies, and SQL schemas into a single local SQLite graph (.codeexplorer/graph.db) powered by an embedded OpenCypher-to-SQL compiler. It ships as a single native binary: no .NET runtime, JVM, Docker, or graph database server required, and nothing leaves your machine.
Live Architecture Map in VS Code: Interactive C1/C2/C3 service topologies, concentric architectural tiers, async broker flows, and database lineage with click-to-source navigation.
Surgical MCP Context for AI Agents: Gives coding agents instant access to call chains, cross-service dependencies, data lineage, and blast-radius impact analysis without burning millions of tokens on blind grep searches.
CI Architecture Gates (Semantic Invariant Gates): Enforces architectural boundaries in the IDE and CI (ce gate check) using declarative OpenCypher rules and SHA-256 ratchet baselines.
(We run two distinct types of benchmarks: 1. End-to-End AI Agent Workflows (measuring how much time, tokens, and missed dependencies a graph saves an LLM on real tasks) and 2. Deterministic Graph Engine Head-to-Head (cold indexing speed, RAM, MCP latency, and extraction recall across 371 verified items without an LLM). Full catalog: benchmarks/README.md and code-explorer.app/benchmarks.html.)
Metric |
| 324-Service Multi-Repo ( |
|
Time to Answer |
|
|
|
Cumulative Input Tokens |
|
|
|
Agent Effort |
|
|
|
Recall & Context Health |
|
|
|
immich & twenty)(Evaluated on immich-app/immich (3,205 files, 461k LOC) and twentyhq/twenty (24,527 files, 2.49M LOC) against a frozen seed-42 ground-truth dataset (371 items across C1–C11: 130 Group A Basic Code + 241 Group B Architecture, DB & Queues). Full reproducible reports and scripts: Case Study 03 (ce vs. codebase-memory-mcp) and Case Study 04 (ce vs. graphify).)
Dimension |
|
|
|
Cold Index ( |
|
|
|
Cold Index ( |
|
|
|
Part 1 Recall ( |
|
|
|
Part 2 Recall ( |
| Not modeled | Not modeled |
Structured Query & CI Governance | OpenCypher ( | Cypher subset ( | Keyword BFS/DFS ( |
CodeExplorer is distributed as a self-contained single-file binary (ce / ce.exe) with embedded Tree-sitter grammars and SQLite (no .NET runtime required), and as a VS Code extension that finds an installed ce or downloads the native binary for your platform on first run.
brew install vmikhailov/tap/ceInstall from the Visual Studio Marketplace or Open VSX Registry:
code --install-extension vmikhailov.code-explorer-vscodemacOS & Linux:
curl -fsSL https://raw.githubusercontent.com/vmikhailov/code-explorer/main/cli/scripts/install.sh | bashWindows (PowerShell):
irm https://raw.githubusercontent.com/vmikhailov/code-explorer/main/cli/scripts/install.ps1 | iexdotnet tool install -g CodeExplorer.CliStandalone archives are available on GitHub Releases:
OS | Architecture | Asset |
macOS | Apple Silicon ( |
|
macOS | Intel ( |
|
Linux |
|
|
Linux |
|
|
Windows |
|
|
Windows |
|
|
The .NET global tool (dotnet tool install -g CodeExplorer.Cli) is an alternative if you already have the .NET 10 SDK.
Related MCP server: trace-mcp
# 1. Initialize .codeexplorer/ in your repository
ce init
# 2. Parse ASTs, project references, endpoints, and cross-service links
ce scan
# 3. Inspect workspace summary and node/edge counts
ce status
# 4. Run a built-in or ad-hoc OpenCypher query
ce query -n get_architecture_map_workspace
ce query "MATCH (a:Project)-[:DEPENDS_ON]->(b:Project) RETURN a.name, b.name"
# 5. Evaluate architectural gates
ce gate check
# 6. Start the MCP server (stdio)
ce mcpText search (grep, ripgrep) works well for finding literals, but it cannot reliably trace interface implementations, cross-service HTTP/gRPC calls, message queue publishers/consumers, or SQL table usage across projects. Reading dozens of files to reconstruct call graphs consumes context window budget and degrades agent accuracy.
Running ce mcp exposes the indexed SQLite graph over the Model Context Protocol:
Architecture & Entry Points: Query projects, dependencies, HTTP/gRPC/GraphQL endpoints, and message consumers via get_architecture_map and get_project_entry_points.
Low-Token File Outlines: Inspect classes, methods, and line ranges in a file via get_file_outline before reading full source text.
Impact & Lineage Analysis: Trace downstream callers of a symbol (analyze_code_impact) or all SQL/ORM readers and writers of a database table (inspect_data_lineage).
OpenCypher Queries: Execute read-only Cypher queries (execute_custom_read_cypher) and save reusable project queries in .codeexplorer/queries/.
Add ce to your MCP client configuration (.cursor/mcp.json, claude_desktop_config.json, or VS Code MCP settings):
{
"mcpServers": {
"code-explorer": {
"command": "ce",
"args": ["mcp"]
}
}
}Or auto-provision your workspace MCP configuration with a single command:
ce mcp configureAGENTS.md / CLAUDE.md Snippet## CodeExplorer (`ce`) MCP Guidelines
- Start architectural exploration with `get_architecture_map` and `get_project_dependencies` instead of broad file searches.
- Use `find_symbol` and `get_file_outline` to locate declarations and line ranges before reading large files.
- Run `analyze_code_impact` or `get_call_chain` before changing shared interfaces or methods.
- Run `inspect_data_lineage` before modifying database tables or ORM entities.
- Use `execute_custom_read_cypher` for multi-hop structural queries.Linters validate syntax and style within single files. Semantic Invariant Gates (SIG) validate structural and architectural rules across the entire repository by executing OpenCypher queries against the graph.
Every gate follows a Zero-Match Contract:
0 rows returned: Gate passes.
1 or more rows returned: Each returned row is a violation with file:line:column coordinates, offending symbol, target, and remediation message.
FAIL: SIG-P-B-001 [Clean Architecture Layer Isolation]
src/Core/Services/OrderService.cs:42:15: OrderService -> SqliteConnection
Domain Core module directly references Infrastructure driver..codeexplorer/gates/*.yaml)id: SIG-P-B-001
name: Clean Architecture Layer Isolation
category: Architectural
platform: agnostic
scope: Module
dimension: Boundaries
severity: Error
description: Domain Core projects must not reference Infrastructure or UI projects.
remediation: Invert the dependency by introducing an interface in Core and implementing it in Infrastructure.
query: |
MATCH (source:Project)-[:DEPENDS_ON]->(target:Project)
WHERE source.name CONTAINS "Core" AND target.name CONTAINS "Infrastructure"
RETURN
coalesce(source.path, "workspace") AS file,
1 AS line,
1 AS column,
source.name AS symbol,
target.name AS target,
"Core project '" + source.name + "' cannot depend on '" + target.name + "'" AS messageTo introduce strict rules into an existing repository without fixing every legacy violation upfront, gates support ratchet baselines (.codeexplorer/baselines/*.json):
Baseline Existing Debt: ce gate ratchet --update records SHA-256 fingerprints of current violations as tolerated baseline debt.
Block Regressions: ce gate check passes if only baselined violations exist, and fails immediately if any new violation is introduced.
Ratchet Down: When legacy violations are fixed, running ce gate ratchet --update tightens the baseline so debt cannot be reintroduced.
- name: Run Architectural Gates
run: |
ce scan
ce gate check --format markdown >> $GITHUB_STEP_SUMMARYThe VS Code extension provides an interactive workspace for exploring the graph, inspecting dependencies, and managing architectural gates.
Multiple Views:
Domain Microservice Map: Interactive graph with Concentric Orbits, Swimlanes, Domain Islands, Hive Plot, Grid, and Dependency Matrix modes.
Architecture Tiers: Layered view across Presentation, Application, Domain, and Infrastructure tiers.
Project Flow: Upstream/downstream dependency columns for a selected project, showing endpoints, database tables, and message topics.
Bounded Context Map: Visualizes domain groupings, capabilities, and domain entities.
Transitive Broker Contraction: When message broker nodes (Kafka, RabbitMQ, SQS) are hidden, the graph automatically synthesizes dashed producer-to-consumer edges (PUBLISHES_TO (via Topic)) so asynchronous flows remain visible.
Unified Right-Hand Dock Panel:
Info: Displays inbound/outbound calls, database dependencies, topics, and source links for the selected node or edge.
Orbits: Reorders concentric tiers and toggles tier visibility.
Hidden: Lists filtered nodes with search and one-click restore.
Gates: Evaluates Semantic Invariant Gates, displays new vs. tolerated violations, ratchets baselines, and jumps directly to offending lines of code.
Sidebar TreeView: Browse Architecture Diagrams, Ontology Layers (Layers 1–5), Domains & Bounded Contexts, Semantic Invariant Gates, and Server/Graph status from the VS Code activity bar.
CodeExplorer combines Tree-sitter parsers, SQL parsers, and 250 framework analyzers across 8 languages. Maturity reflects how much real-world code each analyzer has been validated against: Stable means validated on large open-source and production repositories, Beta means coverage is still growing. If the graph looks wrong on your repository, please open an issue.
Language | Maturity | Files & Manifests | Extracted Framework Semantics (250 Library Parsers) |
C# | Stable |
| ASP.NET Core Controllers & Minimal APIs, FastEndpoints, Carter, YARP, gRPC, HttpClient, EF Core, Dapper, Marten, Linq2Db, NHibernate, MassTransit (incl. Sagas), Wolverine, NServiceBus, Rebus, Hangfire, Quartz.NET, CAP, MediatR, Dapr, Azure/AWS SDKs, Semantic Kernel |
TypeScript / JS | Stable |
| NestJS (REST, GraphQL |
SQL | Stable |
| T-SQL, PostgreSQL, MySQL, SQLite, ClickHouse, BigQuery DDL & CRUD lineage ( |
Go | Stable |
| Gin, Fiber, Echo, Fasthttp, Beego, Gorilla Mux, Go-Zero, Go-Kit/Kratos, |
Java | Stable |
| Spring Boot/Cloud/Batch/Integration/Gateway, Quarkus (RESTEasy, Panache, SmallRye), Micronaut, Dropwizard/Jersey, Vert.x, Akka/Pekko, Netty, Apache Dubbo, Camel, Pulsar, Axon, JPA/Hibernate, MyBatis (Annotations & XML), jOOQ, JDBI, R2DBC, OpenFeign/Retrofit, Temporal, LangChain4j/Spring AI |
Kotlin & Android | Stable |
| Spring Web/Data, Ktor Server & Client DSL, Micronaut, http4k, gRPC-Kotlin, Apollo GraphQL, Exposed, Ktorm, Room DAO/Entities, SQLDelight, Coroutines Channels/SharedFlow, Retrofit/OkHttp, Hilt/Dagger/Koin/Kodein DI, Jetpack Compose, Voyager/Decompose, Kotest/MockK |
Python | Stable |
| FastAPI, Litestar, Flask, Django, Sanic/Tornado/Falcon, Strawberry GraphQL, SQLAlchemy, SQLModel, Tortoise ORM, |
Rust | Stable |
| Axum, Actix Web, Warp, Rocket, Tonic gRPC, Reqwest, SQLx, SeaORM, Diesel, Tokio, Lapin/rdkafka |
ColdFusion | Beta |
| Components, functions, |
The graph schema is organized into five decoupled layers (see docs/ontology.md for the full node and relationship specification):
Layer 1 — Physical: Workspace, Folder, File, ConfigurationFile, Document, Script.
Layer 2 — Project: Project, Service, App, Worker, Library, Package, ExternalDependencies.
Layer 3 — Syntactic: Namespace, Type (class, interface, struct, record, enum), Function (method, constructor), Variable, Field, CallLiteral.
Layer 4 — Semantic: Endpoint (REST, gRPC, GraphQL, WebSocket), ExternalService, Database, Table, Query, Topic, Queue.
Layer 5 — Cross-Project & Analytical: Late-bound cross-project CALLS, IMPLEMENTS, USES_TYPE, PUBLISHES_TO, SUBSCRIBES_TO, READS_FROM, WRITES_TO, and optional LLM-distilled Domain / BoundedContext classifications.
CodeExplorer sits between code-intelligence indexers and architecture-testing libraries. It is not a replacement for most of the tools below, and several of them are complementary.
Tool | What it does best | How CodeExplorer differs |
Sourcegraph (code search, SCIP) | Compiler-accurate code navigation and search across many repositories, run as a server. | Runs locally as a single binary. Models system-level architecture (services, endpoints, topics, tables) and enforces rules on it. Its symbol resolution is less precise than SCIP indexers. |
GitHub CodeQL | Deep semantic and security dataflow queries over per-language databases, built from the compiler for compiled languages. | No build required. One graph across all languages, with cross-service HTTP/gRPC/queue edges and architecture gates with ratchet baselines. Not a security dataflow engine. |
Joern | Open-source Code Property Graph for vulnerability research, queried with a Scala DSL. | Architecture-level ontology instead of a low-level CPG, standard OpenCypher, and MCP / VS Code / CI integration out of the box. |
Serena and other LSP-based MCP servers | Precise symbol lookup and editing for agents through language servers. | Gives agents the system view (cross-service calls, data lineage, blast radius) rather than symbol-level edits. Works well alongside an LSP-based server. |
| Fast Go/C Tree-sitter structural & call-graph indexing ( | Adds Layer 4–5 architectural ontology (ORM/SQL database tables, |
| Unsupervised Leiden community clustering, cross-community bridge detection ( | Scales to 24.5k-file monorepos ( |
Aider repo map | Compact Tree-sitter summary of important symbols, placed directly into the prompt. | A persistent graph the agent can query on demand with multi-hop questions, instead of a static summary. |
ArchUnit, NetArchTest, dependency-cruiser | Architecture rules written as tests inside one language ecosystem. ArchUnit can also freeze existing violations. | One rule language (OpenCypher) across languages and services, and the same graph also powers visualization and agent context. |
Structurizr, C4 diagrams-as-code | Carefully authored architecture models and diagrams. | The model is derived from code, so it does not drift. Diagrams can be exported to Mermaid or C4 ( |
Static analysis only. Reflection, runtime-configured DI, and URLs or topic names assembled at runtime can be missed. Common constant patterns (string constants and simple concatenation) are resolved.
Not a type checker. Calls are resolved from Tree-sitter syntax plus imports, DI bindings, and interface implementations. This is fast and polyglot, but less precise than compiler-based indexers for heavy overloading or dynamic dispatch.
Language maturity varies. See the Maturity column in Supported Languages.
One workspace at a time. Cross-service links are resolved within one indexed workspace (for example, a monorepo).
Parsing, indexing, queries, gates, and the MCP server run locally, and the graph is stored in .codeexplorer/graph.db inside your repository. There is no telemetry. The CLI only uses the network when you explicitly run ce model download (fetches the optional local GGUF model) or configure ce intent with an OpenAI-compatible API. The VS Code extension downloads the ce binary from GitHub Releases if it is not already installed.
Command | Description |
| Initialize |
| Parse source files, build AST and semantic layers, and resolve cross-project edges ( |
| Show workspace statistics, database size, project counts by language, and node/edge totals ( |
| Run an ad-hoc OpenCypher query ( |
| List built-in and workspace-saved OpenCypher queries. |
| Evaluate Semantic Invariant Gates ( |
| Create or tighten violation baseline files in |
| Generate a starter gate template in |
| Export architecture, C4, data lineage, or event pipeline diagrams (`--format mermaid |
| Start the local MCP server over |
| Classify files into business domains and bounded contexts (supports local GGUF via |
| Check or download the optional local GGUF model for offline intent classification. |
| Clear indexed graph data for a path or reset the workspace graph ( |
Tool | Description |
| High-level workspace architecture: projects, services, databases, ingress endpoints, and egress calls. |
| Direct and transitive project/package dependencies ( |
| HTTP endpoints, gRPC methods, GraphQL resolvers, CLI commands, and message consumers for a project. |
| Locate types, interfaces, methods, or functions by name pattern. |
| Return classes, methods, fields, and line ranges for a file without reading the full file. |
| Trace invocation paths between two functions up to |
| Resolve concrete class implementations of an interface or abstract method. |
| Compute downstream callers and files affected by changing a symbol. |
| Find all SQL queries, ORM entities, methods, and services reading from or writing to a table. |
| Identify unreferenced symbols, dead code, or high-coupling types. |
| Execute a read-only OpenCypher ( |
| List saved parameterized queries in |
| Validate and save a reusable OpenCypher query to |
| Run a saved or built-in query by name with parameter binding. |
| Export Mermaid or C4 diagrams for architecture, data lineage, or CQRS flows. |
| Read source snippets by file and line range from graph node results. |
| Return active node labels, relationship types, and counts in the workspace graph. |
| Return schema documentation for a specific ontology node kind. |
| Initialize or re-index the workspace graph from an MCP client. |
| Return index health, schema version, and node/edge counts. |
├── cli/
│ ├── src/
│ │ ├── Core/CodeExplorer.Core/ # Graph storage (SQLite), 5-layer indexer, SIG engine, MCP tools
│ │ ├── Cypher/CodeExplorer.Cypher/ # OpenCypher parser, AST, and SQLite SQL compiler
│ │ ├── Parsers/ # Language parsers (C#, TS/JS, Java, Kotlin, Android, Go, Python, SQL, CF)
│ │ ├── Tools/CodeExplorer.OntologyGen/# Generates docs/ontology.md from C# node/edge attributes
│ │ └── UI/CodeExplorer/ # 'ce' CLI, WebSocket/HTTP server, and MCP host
│ ├── tests/
│ │ ├── CodeExplorer.Cypher.Tests/ # OpenCypher parser & SQL compiler test suite
│ │ └── CodeExplorer.Tests/ # Indexing, cross-service, gate, and MCP integration tests
│ └── CodeExplorer.slnx
├── vscode-extension/ # VS Code extension (TreeView, Webview UI, bundled binary manager)
├── proto/ # Shared WebSocket & REST protocol contracts
└── docs/ # Auto-generated ontology reference and diagramsBlast-radius impact analysis: all callers, dependents, and references affected by modifying a symbol (Class, Interface, Function, Service, Table). Prioritize over grep.
Inputs: symbolName (required), workspacePath.
Evaluate Semantic Invariant Gates (SIG) across the workspace or against specific changed files. Returns zero-match status, new vs tolerated violations, and remediation guidance.
Inputs: limit, scope, gateId, groupBy, +6 more.
Clear indexed data from the workspace database.
Inputs: path, workspacePath.
Execute custom read-only Cypher query (MATCH only) against the code graph.
Inputs: query (required), workspacePath.
Execute a saved project-specific Cypher query by name with parameters.
Inputs: name (required), parameters, workspacePath.
Export Mermaid or C4 system architecture diagrams from the knowledge graph.
Inputs: type, format, project, workspacePath, +1 more.
Fetch source code snippets for given graph nodes.
Inputs: nodes (required), workspacePath.
Find code health anomalies: dead code (0 incoming edges) and god objects.
Inputs: projectName (required), metricType, workspacePath.
Search graph for code symbols (Class, Interface, Function, Variable).
Inputs: name (required), limit, symbolType, workspacePath.
Test Impact Analysis (TIA): finds tests affected by changed files, git diff, or symbols.
Inputs: gitDiff, filePath, filePaths, symbolName, +1 more.
Infrastructure map: workspace folders, projects, internal folders, and databases.
Inputs: projectName, workspacePath.
High-level architecture overview grouped by semantic layers (Core, Services, UI, Infra, Tests).
Inputs: workspacePath.
Architecture view of workspace structure ('c1', 'c2', 'c3', 'project-map', 'tiers').
Inputs: level, scope, workspacePath, includeLibraries.
Trace sequential call graph between start and end functions.
Inputs: endFunction (required), startFunction (required), maxDepth, workspacePath.
Find all callers, inbound references, service consumers, or table/topic accessors for a target (functions, microservices, database tables, messaging topics). Prioritize this tool over grep for discovering callers.
Inputs: target (required), includeTests, workspacePath.
Extract file structural outline without reading source text.
Inputs: filePath (required), workspacePath.
Get schema and documentation for a specific ontological Node Kind.
Inputs: kind (required).
Project dependency graph with runtime vs build filtering.
Inputs: type, limit, projectFilter, workspacePath.
Find entry points (controllers, handlers, endpoints) inside a project.
Inputs: projectName (required), workspacePath.
Ingress and egress contracts for a service (endpoints, RPC, publishers, subscribers).
Inputs: serviceName (required), direction, workspacePath.
Retrieve active graph schema (node kinds, relationship types, properties).
Inputs: workspacePath.
Static test reachability coverage: covered/uncovered classes and methods.
Inputs: limit, status, pathPrefix, projectName, +1 more.
Get workspace health, DB size, indexed project languages, node and edge counts.
Inputs: workspacePath.
Batch ingest custom nodes and relationships into the graph database.
Inputs: nodes (required), relationships, workspacePath.
Initialize a new '.codeexplorer' workspace in the target directory.
Inputs: name, force, workspacePath.
Data lineage: trace SQL/ORM queries, source files, and functions accessing a database table.
Inputs: tableName (required), workspacePath.
List saved project-specific Cypher queries in .codeexplorer/queries/.
Inputs: workspacePath.
List all available Semantic Invariant Gates (both built-in and workspace-specific) with FOIM coordinates and debt status.
Inputs: category, platform, workspacePath.
Find concrete implementations of an interface method (DI resolution).
Inputs: methodName (required), interfaceName (required), workspacePath.
Save a reusable Cypher query with metadata into .codeexplorer/queries/.
Inputs: name (required), cypher (required), description (required), tags, +3 more.
Scan and index source files, projects, ASTs, and dependencies into graph DB.
Inputs: path, clear, workspacePath.
Fast hybrid vector and trigram search across code identifiers, routes, tables, and topics. Finds exact or fuzzy matches with sub-millisecond ranking.
Inputs: query (required), kind, limit, workspacePath.
Trace distributed flow across microservices starting from an endpoint or topic.
Inputs: startService (required), maxDepth, entryPoint, workspacePath.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 33 tools
Most tools have distinct graph-analysis purposes, but several clusters overlap heavily: get_architecture_view, get_architecture_map, and get_architecture_overview are easy to confuse, as are get_call_chain, get_callers, analyze_code_impact, and trace_cross_service_flow. The descriptions provide useful distinctions, but an agent still has to reason carefully to choose the right architecture or call-analysis tool.
All tool names use consistent snake_case verb_noun conventions such as get_callers, find_symbol, scan_workspace, and execute_project_query. The pattern is predictable throughout, even across the large surface.
33 tools is heavy for a code graph explorer and includes many closely related architecture, call-analysis, and semantic-gate tools. While the domain is complex, several tools could likely be consolidated or exposed through a smaller, clearer set.
The surface covers workspace lifecycle, indexing, schema inspection, symbol search, call graphs, impact analysis, test coverage, architecture views, service contracts, data lineage, and semantic gates. Minor gaps exist around updating or deleting custom graph data and managing saved queries beyond save/list/execute, but core exploration workflows are well covered.
Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents.
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
