Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
[![Tests](https://img.shields.io/badge/tests-5604_passing-brightgreen)](https://github.com/DeusData/codebase-memory-mcp)
[![Languages](https://img.shields.io/badge/languages-158-orange)](https://github.com/DeusData/codebase-memory-mcp)
[![Hybrid LSP](https://img.shields.io/badge/Hybrid_LSP-10_languages-blue)](#hybrid-lsp)
[![Agents](https://img.shields.io/badge/agent_surfaces-43-purple)](https://github.com/DeusData/codebase-memory-mcp)
[![Agents](https://img.shields.io/badge/agent_surfaces-44-purple)](https://github.com/DeusData/codebase-memory-mcp)
[![Pure C](https://img.shields.io/badge/pure_C-zero_dependencies-blue)](https://github.com/DeusData/codebase-memory-mcp)
[![Platform](https://img.shields.io/badge/macOS_%7C_Linux_%7C_Windows-supported-lightgrey)](https://github.com/DeusData/codebase-memory-mcp/releases/latest)
[![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/DeusData/codebase-memory-mcp/badge)](https://scorecard.dev/viewer/?uri=github.com/DeusData/codebase-memory-mcp)
Expand All @@ -16,7 +16,7 @@

**The fastest and most efficient code intelligence engine for AI coding agents.** Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a single static binary for macOS, Linux, and Windows — download, run `install`, done.

High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 158 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. Zero dependencies. Plug and play across 43 supported automatic/conditional client surfaces.
High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 158 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. Zero dependencies. Plug and play across 44 supported automatic/conditional client surfaces.

> **Research** — The design and benchmarks behind this project are described in the preprint [*Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP*](https://arxiv.org/abs/2603.27277) (arXiv:2603.27277). Evaluated across 31 real-world repositories: 83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs. file-by-file exploration.

Expand All @@ -34,7 +34,7 @@ High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-si
- **Plug and play** — single static binary for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (amd64). No Docker, no runtime dependencies, no API keys. Download → `install` → restart agent → done.
- **158 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks.
- **120x fewer tokens** — 5 structural queries: ~3,400 tokens vs ~412,000 via file-by-file search. One graph query replaces dozens of grep/read cycles.
- **43 supported automatic/conditional client surfaces** — `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
- **44 supported automatic/conditional client surfaces** — `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
- **Built-in graph visualization** — 3D interactive UI at `localhost:9749` (optional UI binary variant).
- **Infrastructure-as-code indexing** — Dockerfiles, Kubernetes manifests, and Kustomize overlays indexed as graph nodes with cross-references. `Resource` nodes for K8s kinds, `Module` nodes for Kustomize overlays with `IMPORTS` edges to referenced resources.
- **15 MCP tools** — search, trace, architecture, impact analysis, targeted index-coverage checks, Cypher queries, dead code detection, cross-service HTTP linking, ADR management, and more.
Expand Down Expand Up @@ -370,7 +370,7 @@ Restart your agent. Verify with `/mcp` — you should see `codebase-memory-mcp`

## Multi-Agent Support

`install` configures 43 client surfaces: 37 detected automatically and 6
`install` configures 44 client surfaces: 38 detected automatically and 6
conditional or explicit. “Conditional” means the installer writes only when the
documented platform or an explicit, already-existing config path proves the
target is active. It never flips experimental feature flags, enables plugins,
Expand Down Expand Up @@ -435,6 +435,7 @@ overwrite user-modified agents.
| Pochi | Detected | `~/.pochi/config.jsonc` (`mcp`) | `README.pochi.md`, skill, and three `readFile`-only parent-handoff agents |
| Pi | Detected | — | `~/.pi/agent/AGENTS.md` + skill; MCP/subagents require an explicit reviewed extension |
| IBM Bob IDE | Conditional | Existing `~/.bob/mcp.json` | Shared rule + IDE skill; no invented hook or agent |
| Oh My Pi (omp) | Detected | `~/.omp/agent/mcp.json` | `AGENTS.md`, skill, three direct-MCP graph-tool subagents (Scout/Verify/Auditor) |
| Sourcegraph Cody | Explicit opt-in | Existing `$CBM_CODY_CONFIG_PATH` | MCP only |

### Sessions, compaction, and subagents
Expand Down Expand Up @@ -707,7 +708,7 @@ Also supported (not yet benchmarked): Ada, Agda, Apex, Assembly (NASM), Astro, A
src/
main.c Entry point (MCP stdio server + CLI + install/update/config)
mcp/ MCP server (15 tools, JSON-RPC 2.0, session detection, auto-index)
cli/ Install/uninstall/update/config (43 client surfaces, hooks, instructions)
cli/ Install/uninstall/update/config (44 client surfaces, hooks, instructions)
store/ SQLite graph storage (nodes, edges, traversal, search, Louvain)
pipeline/ Multi-pass indexing (structure → definitions → calls → HTTP links → config → tests)
cypher/ Cypher query lexer, parser, planner, executor
Expand Down
12 changes: 6 additions & 6 deletions docs/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>codebase-memory-mcp — Code Intelligence Knowledge Graph for AI Coding Agents</title>
<meta name="description" content="codebase-memory-mcp is an open-source MCP server that indexes any codebase into a persistent knowledge graph so AI coding agents answer structural questions with ~120x fewer tokens. 158 languages, Hybrid LSP type resolution, local semantic vector search, code-clone detection, sub-1ms queries, Linux kernel indexed in 3 minutes. Single static C binary, zero dependencies. One command configures 43 automatic/conditional client surfaces.">
<meta name="description" content="codebase-memory-mcp is an open-source MCP server that indexes any codebase into a persistent knowledge graph so AI coding agents answer structural questions with ~120x fewer tokens. 158 languages, Hybrid LSP type resolution, local semantic vector search, code-clone detection, sub-1ms queries, Linux kernel indexed in 3 minutes. Single static C binary, zero dependencies. One command configures 44 automatic/conditional client surfaces.">
<meta name="keywords" content="MCP server, code intelligence, knowledge graph, tree-sitter, Hybrid LSP, semantic code search, code embeddings, code clone detection, cross-repo analysis, data-flow analysis, Claude Code, Codex CLI, Gemini CLI, Cursor, Zed, code exploration, token reduction, call graph, dead code detection">
<meta name="author" content="DeusData">
<meta name="robots" content="index, follow, max-image-preview:large, max-snippet:-1">
Expand Down Expand Up @@ -68,7 +68,7 @@
"Infrastructure-as-code indexing for Dockerfiles, Kubernetes, and Kustomize",
"Built-in 3D graph visualization UI",
"Auto-sync background watcher for incremental re-indexing",
"One command configures 43 automatic/conditional client surfaces"
"One command configures 44 automatic/conditional client surfaces"
],
"author": {
"@type": "Organization",
Expand Down Expand Up @@ -157,7 +157,7 @@
"name": "Which AI coding agents work with codebase-memory-mcp?",
"acceptedAnswer": {
"@type": "Answer",
"text": "A single install command configures 43 automatic/conditional client surfaces. The 37 detected surfaces are Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi. Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody are conditional or explicit integrations. Qodo, Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI, Plandex, and SWE-agent require manual, UI, cloud, or repository-managed setup and are not counted among the 43."
"text": "A single install command configures 44 automatic/conditional client surfaces. The 38 detected surfaces are Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp). Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody are conditional or explicit integrations. Qodo, Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI, Plandex, and SWE-agent are intentionally not auto-installed."
}
},
{
Expand Down Expand Up @@ -450,7 +450,7 @@ <h1>codebase-memory-mcp</h1>
<div class="stat"><div class="number">~120x</div><div class="label">fewer tokens</div></div>
<div class="stat"><div class="number">158</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">43</div><div class="label">client surfaces</div></div>
<div class="stat"><div class="number">44</div><div class="label">client surfaces</div></div>
</div>
<div class="cta-buttons">
<a href="https://github.com/DeusData/codebase-memory-mcp" class="cta-primary">View on GitHub</a>
Expand Down Expand Up @@ -526,12 +526,12 @@ <h2>How do I install codebase-memory-mcp?</h2>
<span class="cmd">"Index this project"</span>
</div>
<p class="muted">
One command configures 43 automatic/conditional client surfaces. <strong>Detected automatically (37):</strong>
One command configures 44 automatic/conditional client surfaces. <strong>Detected automatically (38):</strong>
Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor,
Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code,
GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI,
GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE,
CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi.
CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp).
</p>
<p class="muted">
<strong>Conditional or explicit (6):</strong> Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE,
Expand Down
2 changes: 1 addition & 1 deletion docs/llms.txt
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
- Semantic & similarity edges: SEMANTICALLY_RELATED (vocabulary-mismatch matches) and SIMILAR_TO (MinHash + LSH near-clone / duplicate detection).
- Cross-repo intelligence: CROSS_* edges link nodes across multiple repos indexed in one store; multi-galaxy 3D layout and cross-repo architecture summary.
- Cross-service linking: HTTP route ↔ call-site matching, plus gRPC/GraphQL/tRPC detection and pub/sub channels (EMITS/LISTENS_ON for Socket.IO, EventEmitter, generic buses).
- Supported agents: 43 automatic/conditional client surfaces (37 automatically detected + 6 conditional/explicit): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Continue / cn, Visual Studio, TRAE, Roo Code, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob IDE, IBM Bob Shell, Pochi, Pi, and Sourcegraph Cody.
- Supported agents: 44 automatic/conditional client surfaces (38 automatically detected + 6 conditional/explicit): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Continue / cn, Visual Studio, TRAE, Roo Code, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob IDE, IBM Bob Shell, Pochi, Pi, Oh My Pi (omp), and Sourcegraph Cody.
- Agent profiles: documented custom-agent formats receive Scout (fast/provisional), Verify (default/task-directed), and Auditor (bounded/full verification) definitions. Every direct tier checks exact path/scope coverage with check_index_coverage and falls back to source for flagged gaps; unsafe child-MCP formats use explicit parent handoff. Kiro and Junie use positive-allowlist Scout/Analysis server profiles (7/11 tools); Qoder combines named-server selection with exact tier-specific MCP tool IDs, while Factory uses exact registered IDs without additive whole-server exposure. Foreign Junie aliases are preserved and force parent handoff.
- Performance: Linux kernel (28M LOC, 75K files) full index in 3 minutes → 4.81M nodes, 7.72M edges; Cypher queries in under 1ms.
- Distribution: single static C binary; also npm, PyPI, Homebrew, Scoop, Winget, Chocolatey, AUR, and `go install`.
Expand Down
6 changes: 3 additions & 3 deletions pkg/npm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@

**The fastest and most efficient code intelligence engine for AI coding agents.** Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a single static binary — this package downloads and runs it automatically.

High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across 159 languages — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 14 MCP tools. Zero dependencies. Plug and play across 43 automatic/conditional client surfaces.
High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across 159 languages — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 14 MCP tools. Zero dependencies. Plug and play across 44 automatic/conditional client surfaces.

## Installation

Expand All @@ -29,8 +29,8 @@ Restart your agent. Say **"Index this project"** — done.
- **Plug and play** — single static binary for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (amd64). No Docker, no runtime dependencies, no API keys.
- **159 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks.
- **120x fewer tokens** — 5 structural queries: ~3,400 tokens vs ~412,000 via file-by-file search.
- **43 supported automatic/conditional client surfaces** — `install` configures the appropriate MCP, durable-context, and documented hook surfaces without widening client permissions.
- **Detected automatically (37)** — Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi.
- **44 supported automatic/conditional client surfaces** — `install` configures the appropriate MCP, durable-context, and documented hook surfaces without widening client permissions.
- **Detected automatically (38)** — Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp).
- **Conditional or explicit (6)** — Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody. Bob IDE is touched only when `~/.bob/mcp.json` already exists.
- **New documented adapters** — CodeBuddy uses `~/.codebuddy/.mcp.json` while preserving active older files; Bob Shell uses `~/.bob/mcp_settings.json`; Pochi uses the `mcp` section in `~/.pochi/config.jsonc`; Amazon Q Developer IDE defaults to `~/.aws/amazonq/default.json` while preserving either documented alternative.
- **Lifecycle hooks stay conservative** — Kimi uses `UserPromptSubmit`; on macOS/Linux, GitLab Duo gets a fail-open user `SessionStart`, while Devin gets `UserPromptSubmit`, `PostCompaction`, and a deduplicated `SessionStart` when Claude does not already provide it. Qoder, GitLab Duo, Devin, and Factory hooks are withheld on Windows without a documented shell/executor contract. Cline's auto-activating file hooks are withheld because their context output is not reliably consumed, CodeBuddy beta hooks are not auto-installed, and Cursor context hooks remain withheld.
Expand Down
Loading
Loading