Stellarion
Cross-language code intelligence for AI agents and developers.
Stellarion builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 47 tools, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files. EDA mode adds Quartus / Qsys / SDC analysis for hardware design teams.
Quick Start
MCP Server (Claude Code, Cursor, any MCP client)
Add to ~/.claude.json (or your MCP client config):
{
"mcpServers": {
"stellarion": {
"command": "/path/to/stellarion-server",
"args": ["--mcp"]
}
}
}
The server indexes the current working directory automatically.
VS Code Extension
Install the VSIX:
code --install-extension stellarion-2.0.4.vsix
The extension starts the server automatically and registers all tools as Language Model Tools for Copilot.
Configuration
MCP Server flags
| Flag |
Default |
Description |
--workspace <path> |
current dir |
Directories to index (repeatable for multi-project) |
--exclude <dir> |
— |
Directories to skip (repeatable) |
--embedding-model <model> |
bge-small |
bge-small (384d, fast) or jina-code-v2 (768d, 6x slower) |
--max-files <n> |
5000 |
Maximum files to index |
VS Code settings
{
"stellarion.indexOnStartup": true,
"stellarion.indexPaths": ["/path/to/project-a", "/path/to/project-b"],
"stellarion.excludePatterns": ["**/cmake-build-debug/**", "**/generated/**"],
"stellarion.embeddingModel": "bge-small",
"stellarion.maxFileSizeKB": 1024,
"stellarion.maxFiles": 5000,
"stellarion.debug": false
}
| Setting |
Default |
Description |
indexOnStartup |
false |
Index workspace on startup. When false, use the Stellarion: Index Directory command on demand. |
indexPaths |
[] |
Specific directories to index. Empty = all workspace folders. List multiple paths for cross-project navigation. |
excludePatterns |
(defaults) |
Glob patterns to skip during indexing |
embeddingModel |
bge-small |
bge-small (384d, fast) or jina-code-v2 (768d, 6x slower) |
maxFileSizeKB |
1024 |
Maximum file size to index, in KB |
maxFiles |
5000 |
Maximum number of files to index per workspace. Increase for large repos (impacts memory and indexing time). |
Index multiple projects by listing paths in indexPaths. All paths are merged into a single graph, enabling cross-file navigation and impact analysis across project boundaries.
Full-body embeddings are enabled by default. Function body text is captured at parse time with zero I/O overhead.
Built-in exclusions (always skipped): node_modules, target, dist, build, out, .git, __pycache__, vendor, DerivedData, tmp, coverage, logs.
License Activation
A 180-day free trial of all 47 tools (community + Pro + EDA) starts automatically — no signup, no credit card.
To activate a Pro license:
- Command palette (
Cmd/Ctrl+Shift+P): Stellarion: Activate Pro License, then paste the key
- Manual: save the key to
~/.stellarion/license.key and reload VS Code
Check status anytime with Stellarion: Show License Status.
Get a Pro license at stellarion.ai/pro.
All community tools are free to use. No license required.
Code Analysis (5)
| Tool |
What it does |
get_ai_context |
Primary context tool. Intent-aware (explain/modify/debug/test) with token budgeting. Returns source, related symbols, imports, siblings, debug hints. |
get_edit_context |
Everything needed before editing: source + callers + tests + memories + git history |
get_curated_context |
Cross-codebase context for a natural language query ("how does auth work?") |
analyze_impact |
Blast radius prediction — what breaks if you modify, delete, or rename |
analyze_complexity |
Cyclomatic complexity with breakdown (branches, loops, nesting, exceptions, early returns) |
Code Navigation (13)
| Tool |
What it does |
symbol_search |
Find symbols by name or natural language (hybrid BM25 + semantic search) |
get_callers / get_callees |
Who calls this? What does it call? (with transitive depth) |
get_detailed_symbol |
Full symbol info: source, callers, callees, complexity |
get_symbol_info |
Quick metadata: signature, visibility, kind |
get_dependency_graph |
File/module import relationships with depth control |
get_call_graph |
Function call chains (callers and callees) |
find_by_imports |
Find files importing a module |
find_by_signature |
Search by param count, return type, modifiers |
find_entry_points |
Main functions, HTTP handlers, CLI commands, event handlers |
find_implementors |
Find all functions registered as ops struct callbacks |
find_related_tests |
Tests that exercise a given function |
traverse_graph |
Custom graph traversal with edge/node type filters |
Indexing (3)
| Tool |
What it does |
reindex_workspace |
Full or incremental workspace reindex |
index_files |
Add/update specific files without full reindex |
index_directory |
Add directory to graph alongside existing data |
Memory (7)
Persistent AI context across sessions — debugging insights, architectural decisions, known issues.
| Tool |
What it does |
memory_store / memory_get / memory_search |
Store, retrieve, search memories (BM25 + semantic) |
memory_context |
Get memories relevant to a file/function |
memory_list / memory_invalidate / memory_stats |
Browse, retire, monitor |
All tool names are prefixed with stellarion_ (e.g. stellarion_get_ai_context). Tools that target a specific symbol accept uri + line or nodeId from symbol_search results.
Stellarion Pro adds 16 advanced tools for architecture analysis, security scanning, code similarity, and git history mining. All Pro tools are visible in the tool list and marked with [Pro] — they require a Stellarion Pro license to invoke.
A 180-day free trial starts automatically when you first use the Pro server. No signup required.
Architecture & Quality (5)
| Tool |
What it does |
codebase_health |
Single-call health dashboard with score (0-100), grade (A-F), complexity histograms, test coverage, dependency health |
tech_debt_report |
Prioritized debt assessment with severity and remediation effort estimates |
assess_change_risk |
Predict risk of file changes (blast radius, complexity, tests, coupling) for PR review |
dependency_drift |
Detect new dependencies, fan-out changes, circular dep regressions |
api_surface |
Catalog public exports, find unused API surface |
Security & Coupling (3)
| Tool |
What it does |
scan_security |
Scan for vulnerabilities: dangerous calls, weak crypto, hardcoded secrets, unsafe patterns, architectural layer violations. 40+ rules across 13 languages. |
analyze_coupling |
Module coupling metrics: afferent/efferent coupling, instability scores, dependency graph |
find_unused_code |
Dead code detection with confidence scoring and framework-aware heuristics |
Code Similarity (4)
Powered by semantic code embeddings — works across languages.
| Tool |
What it does |
find_duplicates |
Detect duplicate/near-duplicate functions across the codebase |
find_similar |
Find functions most similar to a given function |
cluster_symbols |
Group functions into semantic clusters by purpose |
compare_symbols |
Deep comparison of two functions: similarity score, structural diff, shared callers |
Cross-Project Search (1)
| Tool |
What it does |
cross_project_search |
Search for symbols across all other indexed projects in the shared graph database |
Git History Mining (3)
| Tool |
What it does |
mine_git_history |
Mine commit history to bootstrap project knowledge |
mine_git_history_for_file |
Mine git history for a specific file |
search_git_history |
Semantic + keyword search over git commit history |
EDA — Quartus / Qsys / SDC (3)
For hardware design teams. Activated by --mode eda (Pro / trial only).
The TCL/SDC/UPF parser classifies commands into 40+ stage-aware
categories (quartus_assignment, qsys_module, qsys_interface,
qsys_instantiation, quartus_timing, query_clock, read_sdc, …).
| Tool |
What it does |
find_eda_calls |
Aggregate EDA call sites by category / category prefix / file pattern. Surfaces Quartus assignment locations, Qsys component declarations, SDC reads, etc. |
get_flow_graph |
Build EDA flow graph: project_setup → ip_composition → configuration → synthesis → placement → routing → timing → reporting. Each stage's procs, category breakdown, and stage-to-stage transitions (callers spanning ≥2 stages → directed edges). |
find_duplicate_constraints |
Detect duplicate (category, key) groups — multiple set_global_assignment -name FAMILY with conflicting values, repeated set_module_property NAME declarations across _hw.tcl files, AXI parameter drift across IP components. onlyTrueConflicts filter keeps only real config drift (some values repeat AND others differ). |
EDA mode is additive only — it surfaces the three EDA-native
tools above without hiding any general tools. EDA codebases are
multi-language (HDL + Tcl + Python build scripts + C testbenches),
so the generic tools (security scan, related tests, etc.) still
apply on the non-HDL portions.
| Feature |
Community |
Pro |
| Tools |
28 |
47 (28 + 19 Pro, incl. 3 EDA) |
| Languages |
17 |
17 |
| Multi-project indexing |
Yes |
Yes |
| Persistent memory |
Yes |
Yes |
| Security scanning |
— |
40+ rules, 13 languages |
| Code similarity |
— |
Embedding-based, cross-language |
| Dead code detection |
— |
Confidence-scored, framework-aware |
| Cross-project search |
— |
Shared graph database |
| Git history mining |
— |
Semantic commit search |
| License |
Free |
stellarion.ai/pro |
Community edition is fully functional for single and multi-project code intelligence. Pro adds advanced analysis tools. A 180-day trial of all Pro features starts automatically — no signup, no credit card.
Languages
17 languages parsed via tree-sitter — functions, imports, call graph, complexity metrics, dependency graphs, symbol search, and impact analysis:
TypeScript/JS, Python, Rust, Go, C, C++, Java, Kotlin, C#, PHP, Ruby, Swift, Tcl, Verilog/SystemVerilog, COBOL, Fortran
Architecture
MCP Client (Claude, Cursor, ...) VS Code Extension
| |
MCP (stdio) LSP Protocol
| |
└───────────┐ ┌───────────┘
▼ ▼
┌─────────────────────────────┐
│ stellarion-server │
├─────────────────────────────┤
│ 17 tree-sitter parsers │
│ Semantic graph engine │
│ AI query engine (BM25) │
│ Memory layer (RocksDB) │
│ Full-body embeddings (BGE) │
│ HNSW vector index │
└─────────────────────────────┘
A single Rust binary serves both MCP and LSP protocols.
- Indexing: ~60 files/sec. Incremental re-indexing on file changes.
- Queries: Sub-100ms. Cross-file import and call resolution at index time.
- Embeddings: Full-body (function bodies captured at parse time, zero disk I/O). Auto-downloads model on first run.
Examples & Issue Tracker
Configuration templates and 14 architect-level slash commands (Claude
Code + VS Code Copilot Chat) live at
github.com/stellarion-repos/stellarion-ai.
That's also the public bug tracker — open issues there for the
extension, the MCP server, EDA classification, slash commands, or
documentation.
For security disclosures: security@stellarion.ai (do not open a
public issue).
License
Proprietary. See stellarion.ai/pro for Pro licensing.