mirror of
https://github.com/DeusData/codebase-memory-mcp.git
synced 2026-10-21 05:59:35 +08:00
437 lines
18 KiB
HTML
437 lines
18 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>codebase-memory-mcp — High-Performance Code Intelligence for AI Agents</title>
|
|
<meta name="description" content="MCP server that indexes codebases into a persistent knowledge graph. 66 languages, 120x fewer tokens, 3-minute Linux kernel indexing. Single static binary. Works with Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode.">
|
|
<meta name="keywords" content="MCP server, code analysis, knowledge graph, tree-sitter, Claude Code, Codex, Cursor, Windsurf, Gemini CLI, VS Code, Zed, OpenCode, KiloCode, developer tools, code exploration, token reduction, code intelligence">
|
|
|
|
<!-- Open Graph -->
|
|
<meta property="og:title" content="codebase-memory-mcp — High-Performance Code Intelligence for AI Agents">
|
|
<meta property="og:description" content="120x fewer tokens for AI code exploration. 66 languages, sub-ms queries, 3-min Linux kernel indexing. Single static binary.">
|
|
<meta property="og:type" content="website">
|
|
<meta property="og:url" content="https://deusdata.github.io/codebase-memory-mcp">
|
|
<meta property="og:image" content="https://deusdata.github.io/codebase-memory-mcp/graph-ui-screenshot.png">
|
|
|
|
<!-- Twitter Card -->
|
|
<meta name="twitter:card" content="summary_large_image">
|
|
<meta name="twitter:title" content="codebase-memory-mcp — High-Performance Code Intelligence for AI Agents">
|
|
<meta name="twitter:description" content="120x fewer tokens for AI code exploration. 66 languages, sub-ms queries, 3-min Linux kernel indexing.">
|
|
<meta name="twitter:image" content="https://deusdata.github.io/codebase-memory-mcp/graph-ui-screenshot.png">
|
|
|
|
<link rel="canonical" href="https://deusdata.github.io/codebase-memory-mcp">
|
|
|
|
<style>
|
|
:root {
|
|
--bg: #0d1117;
|
|
--surface: #161b22;
|
|
--border: #30363d;
|
|
--text: #e6edf3;
|
|
--text-secondary: #8b949e;
|
|
--accent: #58a6ff;
|
|
--accent-hover: #79c0ff;
|
|
--green: #3fb950;
|
|
--red: #f85149;
|
|
}
|
|
* { margin: 0; padding: 0; box-sizing: border-box; }
|
|
body {
|
|
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif;
|
|
background: var(--bg);
|
|
color: var(--text);
|
|
line-height: 1.6;
|
|
}
|
|
.container { max-width: 960px; margin: 0 auto; padding: 0 24px; }
|
|
|
|
/* Hero */
|
|
.hero {
|
|
padding: 80px 0 40px;
|
|
text-align: center;
|
|
}
|
|
.hero h1 {
|
|
font-size: 2.5rem;
|
|
font-weight: 700;
|
|
margin-bottom: 16px;
|
|
}
|
|
.hero .tagline {
|
|
font-size: 1.25rem;
|
|
color: var(--text-secondary);
|
|
margin-bottom: 32px;
|
|
max-width: 700px;
|
|
margin-left: auto;
|
|
margin-right: auto;
|
|
}
|
|
.hero .stat {
|
|
display: inline-block;
|
|
background: var(--surface);
|
|
border: 1px solid var(--border);
|
|
border-radius: 8px;
|
|
padding: 16px 24px;
|
|
margin: 8px;
|
|
}
|
|
.hero .stat .number {
|
|
font-size: 2rem;
|
|
font-weight: 700;
|
|
color: var(--accent);
|
|
}
|
|
.hero .stat .label {
|
|
font-size: 0.875rem;
|
|
color: var(--text-secondary);
|
|
}
|
|
.cta-buttons {
|
|
margin-top: 32px;
|
|
}
|
|
.cta-buttons a {
|
|
display: inline-block;
|
|
padding: 12px 24px;
|
|
border-radius: 6px;
|
|
text-decoration: none;
|
|
font-weight: 600;
|
|
margin: 4px;
|
|
}
|
|
.cta-primary {
|
|
background: var(--accent);
|
|
color: #0d1117;
|
|
}
|
|
.cta-primary:hover { background: var(--accent-hover); }
|
|
.cta-secondary {
|
|
border: 1px solid var(--border);
|
|
color: var(--text);
|
|
}
|
|
.cta-secondary:hover { border-color: var(--text-secondary); }
|
|
|
|
/* Screenshot */
|
|
.screenshot {
|
|
margin: 40px 0;
|
|
text-align: center;
|
|
}
|
|
.screenshot img {
|
|
max-width: 100%;
|
|
border-radius: 12px;
|
|
border: 1px solid var(--border);
|
|
box-shadow: 0 8px 32px rgba(0,0,0,0.4);
|
|
}
|
|
.screenshot .caption {
|
|
margin-top: 12px;
|
|
font-size: 0.875rem;
|
|
color: var(--text-secondary);
|
|
}
|
|
|
|
/* Sections */
|
|
section { padding: 60px 0; }
|
|
section h2 {
|
|
font-size: 1.75rem;
|
|
margin-bottom: 24px;
|
|
}
|
|
|
|
/* Install */
|
|
.install-block {
|
|
background: var(--surface);
|
|
border: 1px solid var(--border);
|
|
border-radius: 8px;
|
|
padding: 20px 24px;
|
|
font-family: 'SF Mono', 'Fira Code', monospace;
|
|
font-size: 0.9rem;
|
|
overflow-x: auto;
|
|
margin: 16px 0;
|
|
}
|
|
.install-block .comment { color: var(--text-secondary); }
|
|
.install-block .cmd { color: var(--green); }
|
|
|
|
/* Comparison table */
|
|
table {
|
|
width: 100%;
|
|
border-collapse: collapse;
|
|
margin: 16px 0;
|
|
}
|
|
th, td {
|
|
padding: 10px 16px;
|
|
text-align: left;
|
|
border-bottom: 1px solid var(--border);
|
|
}
|
|
th {
|
|
background: var(--surface);
|
|
font-weight: 600;
|
|
font-size: 0.875rem;
|
|
color: var(--text-secondary);
|
|
text-transform: uppercase;
|
|
letter-spacing: 0.5px;
|
|
}
|
|
td { font-size: 0.9rem; }
|
|
.win { color: var(--green); font-weight: 600; }
|
|
.lose { color: var(--text-secondary); }
|
|
|
|
/* Features grid */
|
|
.features {
|
|
display: grid;
|
|
grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
|
|
gap: 20px;
|
|
margin-top: 24px;
|
|
}
|
|
.feature {
|
|
background: var(--surface);
|
|
border: 1px solid var(--border);
|
|
border-radius: 8px;
|
|
padding: 24px;
|
|
}
|
|
.feature h3 {
|
|
font-size: 1rem;
|
|
margin-bottom: 8px;
|
|
}
|
|
.feature p {
|
|
font-size: 0.875rem;
|
|
color: var(--text-secondary);
|
|
}
|
|
|
|
/* Benchmark */
|
|
.benchmark-table td:nth-child(2),
|
|
.benchmark-table td:nth-child(3),
|
|
.benchmark-table td:nth-child(4) {
|
|
text-align: right;
|
|
font-family: 'SF Mono', monospace;
|
|
font-size: 0.85rem;
|
|
}
|
|
.benchmark-table th:nth-child(2),
|
|
.benchmark-table th:nth-child(3),
|
|
.benchmark-table th:nth-child(4) {
|
|
text-align: right;
|
|
}
|
|
|
|
/* Footer */
|
|
footer {
|
|
padding: 40px 0;
|
|
text-align: center;
|
|
color: var(--text-secondary);
|
|
font-size: 0.875rem;
|
|
border-top: 1px solid var(--border);
|
|
}
|
|
footer a { color: var(--accent); text-decoration: none; }
|
|
|
|
/* Responsive */
|
|
@media (max-width: 640px) {
|
|
.hero h1 { font-size: 1.75rem; }
|
|
.hero .stat { display: block; margin: 8px 0; }
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
|
|
<div class="container">
|
|
<section class="hero">
|
|
<h1>codebase-memory-mcp</h1>
|
|
<p class="tagline">
|
|
The fastest and most efficient code intelligence engine for AI coding agents. Full-indexes an average repo in seconds,
|
|
the Linux kernel in 3 minutes. Tree-sitter + LSP hybrid parsing (Go, C, C++ — more coming). Single static binary — download, install, done.
|
|
</p>
|
|
<div>
|
|
<div class="stat">
|
|
<div class="number">120x</div>
|
|
<div class="label">fewer tokens</div>
|
|
</div>
|
|
<div class="stat">
|
|
<div class="number">66</div>
|
|
<div class="label">languages</div>
|
|
</div>
|
|
<div class="stat">
|
|
<div class="number">3 min</div>
|
|
<div class="label">Linux kernel index</div>
|
|
</div>
|
|
<div class="stat">
|
|
<div class="number">8</div>
|
|
<div class="label">agents supported</div>
|
|
</div>
|
|
</div>
|
|
<div class="cta-buttons">
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp" class="cta-primary">View on GitHub</a>
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp/releases/latest" class="cta-secondary">Download Latest Release</a>
|
|
</div>
|
|
</section>
|
|
|
|
<div class="screenshot">
|
|
<img src="graph-ui-screenshot.png" alt="3D graph visualization of the codebase-memory-mcp knowledge graph showing 23,827 nodes and 51,526 edges">
|
|
<p class="caption">Built-in 3D graph visualization (UI variant) — explore your knowledge graph at localhost:9749</p>
|
|
</div>
|
|
|
|
<section>
|
|
<h2>Install in 3 steps</h2>
|
|
<div class="install-block">
|
|
<span class="comment"># 1. Download for your platform (standard or ui variant)</span><br>
|
|
<span class="cmd">tar xzf codebase-memory-mcp-*.tar.gz</span><br>
|
|
<span class="cmd">mv codebase-memory-mcp ~/.local/bin/</span><br><br>
|
|
<span class="comment"># 2. Auto-configure all detected agents</span><br>
|
|
<span class="cmd">codebase-memory-mcp install</span><br><br>
|
|
<span class="comment"># 3. Restart your agent, then say:</span><br>
|
|
<span class="cmd">"Index this project"</span>
|
|
</div>
|
|
<p style="color: var(--text-secondary); font-size: 0.9rem;">
|
|
Static binary for macOS, Linux, and Windows — no Docker, no runtime dependencies. One install command
|
|
configures all 8 agents: Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode.
|
|
</p>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>The problem</h2>
|
|
<p style="margin-bottom: 16px;">
|
|
AI coding agents explore codebases by reading files one at a time. Every structural question
|
|
triggers a cascade of grep → read file → grep again → read more files.
|
|
</p>
|
|
<p style="margin-bottom: 16px;">
|
|
Five structural questions about a real codebase:
|
|
<strong style="color: var(--red);">~412,000 tokens</strong> via file-by-file search.
|
|
<strong style="color: var(--green);">~3,400 tokens</strong> via knowledge graph queries.
|
|
</p>
|
|
<p style="color: var(--text-secondary);">
|
|
The 120x reduction isn't about fitting in the context window. It's about cost ($3-15/M tokens adds up),
|
|
latency (<1ms vs seconds), and accuracy (less noise = better answers, no "lost in the middle" problem).
|
|
</p>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Benchmark results</h2>
|
|
<table class="benchmark-table">
|
|
<thead>
|
|
<tr>
|
|
<th>Question Type</th>
|
|
<th>Graph</th>
|
|
<th>File-by-file</th>
|
|
<th>Savings</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr>
|
|
<td>Find function by pattern</td>
|
|
<td>~200</td>
|
|
<td>~45,000</td>
|
|
<td class="win">225x</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Trace call chain (depth 3)</td>
|
|
<td>~800</td>
|
|
<td>~120,000</td>
|
|
<td class="win">150x</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Dead code detection</td>
|
|
<td>~500</td>
|
|
<td>~85,000</td>
|
|
<td class="win">170x</td>
|
|
</tr>
|
|
<tr>
|
|
<td>List all routes</td>
|
|
<td>~400</td>
|
|
<td>~62,000</td>
|
|
<td class="win">155x</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Architecture overview</td>
|
|
<td>~1,500</td>
|
|
<td>~100,000</td>
|
|
<td class="win">67x</td>
|
|
</tr>
|
|
<tr style="font-weight: 700;">
|
|
<td>Total</td>
|
|
<td>~3,400</td>
|
|
<td>~412,000</td>
|
|
<td class="win">121x</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
<p style="color: var(--text-secondary); font-size: 0.875rem; margin-top: 8px;">
|
|
Tested across 31 languages with agent-vs-agent methodology (372 questions).
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/BENCHMARK_REPORT.md">Full benchmark report →</a>
|
|
</p>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Features</h2>
|
|
<div class="features">
|
|
<div class="feature">
|
|
<h3>64 Languages</h3>
|
|
<p>Python, Go, JS, TS, TSX, Rust, Java, C++, C#, C, PHP, Ruby, Kotlin, Scala, Zig, Elixir, Haskell, OCaml, Swift, Dart, MATLAB, Lean 4, Wolfram, and 41 more via vendored tree-sitter grammars.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Extreme Performance</h3>
|
|
<p>RAM-first pipeline: LZ4 compression, in-memory SQLite, fused Aho-Corasick pattern matching. Linux kernel (28M LOC) indexed in 3 minutes.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Graph Visualization</h3>
|
|
<p>Built-in 3D graph UI (optional). Explore nodes, edges, and clusters visually at localhost:9749. Ships as a separate binary variant.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Call Graph Tracing</h3>
|
|
<p>Trace callers and callees across files and packages. Import-aware, type-inferred resolution. BFS traversal up to depth 5.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>8-Agent Install</h3>
|
|
<p>One command configures Claude Code, Codex, Gemini CLI, Zed, OpenCode, Antigravity, Aider, and KiloCode with MCP configs, instructions, and hooks.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Dead Code Detection</h3>
|
|
<p>Find functions with zero callers, with smart filtering that excludes entry points (route handlers, main(), framework decorators).</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Cross-Service HTTP Linking</h3>
|
|
<p>Discovers REST routes and matches them to HTTP call sites across services with confidence scoring.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>Auto-Sync + Auto-Index</h3>
|
|
<p>Background watcher detects git changes. Optional auto-indexing on session start. No manual reindex needed.</p>
|
|
</div>
|
|
<div class="feature">
|
|
<h3>14 MCP Tools</h3>
|
|
<p>search_graph, trace_call_path, detect_changes, query_graph, get_architecture, manage_adr, get_code_snippet, and 7 more.</p>
|
|
</div>
|
|
</div>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>How it compares</h2>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Feature</th>
|
|
<th>codebase-memory-mcp</th>
|
|
<th>GitNexus</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr><td>Languages</td><td class="win">64</td><td>8-11</td></tr>
|
|
<tr><td>Runtime</td><td class="win">Single static binary</td><td>Node.js (npx)</td></tr>
|
|
<tr><td>Runtime dependency</td><td class="win">None</td><td>Node.js</td></tr>
|
|
<tr><td>Stress test</td><td class="win">Linux kernel (2.1M nodes, 3 min)</td><td>Not published</td></tr>
|
|
<tr><td>Embedded LLM</td><td class="win">No (uses your MCP client)</td><td>Yes (extra API key + cost)</td></tr>
|
|
<tr><td>Published benchmarks</td><td class="win">Yes (31 langs, 372 questions)</td><td>No</td></tr>
|
|
<tr><td>Auto-sync</td><td class="win">Yes</td><td>No</td></tr>
|
|
<tr><td>MCP tools</td><td class="win">14</td><td>7</td></tr>
|
|
<tr><td>Agents supported</td><td class="win">8</td><td>1-2</td></tr>
|
|
<tr><td>Cross-service HTTP linking</td><td class="win">Yes</td><td>No</td></tr>
|
|
<tr><td>Cypher queries</td><td class="win">Yes</td><td>No</td></tr>
|
|
<tr><td>Incremental reindex</td><td class="win">Yes (<1ms no-op)</td><td>No</td></tr>
|
|
<tr><td>Pre-tool hooks</td><td class="win">Yes (agents prefer graph tools)</td><td>No</td></tr>
|
|
<tr><td>Visual web UI</td><td class="win">Yes (3D graph)</td><td class="win">Yes</td></tr>
|
|
<tr><td>Graph RAG / embeddings</td><td>Not needed*</td><td>Yes</td></tr>
|
|
</tbody>
|
|
</table>
|
|
<p style="color: var(--text-secondary); font-size: 0.875rem; margin-top: 12px;">
|
|
*Graph RAG and semantic embeddings solve a human problem — fuzzy "find something similar" queries.
|
|
MCP agents don't need this: they make precise structural queries via tool calls and synthesize results themselves.
|
|
codebase-memory-mcp is purpose-built for agents — exact patterns, call chain tracing, and structural search
|
|
at machine speed.
|
|
</p>
|
|
</section>
|
|
</div>
|
|
|
|
<footer>
|
|
<div class="container">
|
|
<p>
|
|
Open source, MIT licensed.
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp">GitHub</a> ·
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp/releases/latest">Releases</a> ·
|
|
<a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/BENCHMARK_REPORT.md">Benchmarks</a>
|
|
</p>
|
|
</div>
|
|
</footer>
|
|
|
|
</body>
|
|
</html>
|