From 6c74ae382a98e7083bcae58ff5344ec76943e1e2 Mon Sep 17 00:00:00 2001 From: Martin Vogel Date: Thu, 27 Aug 2026 19:20:03 +0200 Subject: [PATCH] docs: correct the published language count to 161 on every surface Seven surfaces disagreed with reality and with each other: README.md, docs/index.html, docs/llms.txt and pkg/npm/README.md said 158, while server.json, the chocolatey nuspec and scripts/package-release.sh said 159. 161 grammars are vendored. 21 individual claims corrected. The count is now gated by tests/test_language_count_contract.sh, so the next language to land cannot ship a stale figure. Signed-off-by: Martin Vogel --- README.md | 10 +++++----- docs/index.html | 20 ++++++++++---------- docs/llms.txt | 2 +- pkg/chocolatey/codebase-memory-mcp.nuspec | 2 +- pkg/npm/README.md | 4 ++-- scripts/package-release.sh | 2 +- server.json | 2 +- tests/test_language_count_contract.sh | 6 +++--- 8 files changed, 24 insertions(+), 24 deletions(-) diff --git a/README.md b/README.md index b6ffd884b..48ce25615 100644 --- a/README.md +++ b/README.md @@ -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 native executable with a small verified runtime-asset set 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. No language runtime, hosted service, or API key. Plug and play across 44 supported automatic/conditional client surfaces. +High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 161 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. No language runtime, hosted service, or API key. 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. @@ -32,7 +32,7 @@ High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-si - **Extreme indexing speed** — Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline: LZ4 compression, in-memory SQLite, fused Aho-Corasick pattern matching. Memory released after indexing. - **Plug and play** — native executable plus authenticated release-owned assets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (amd64). The native install needs no Docker, language runtime, or API keys. Download → `install` → restart agent → done. -- **158 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks. +- **161 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. - **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`, served from the binary itself. @@ -760,14 +760,14 @@ codebase-memory-mcp ships a **lightweight C implementation of language type-reso **Two-layer architecture:** -1. **Tree-sitter pass** — fast, syntactic, runs for every one of the 158 languages. Extracts definitions, calls, imports. +1. **Tree-sitter pass** — fast, syntactic, runs for every one of the 161 languages. Extracts definitions, calls, imports. 2. **Hybrid LSP pass** — type-aware, runs above the tree-sitter pass per-language. Refines call edges using the import graph plus a per-file or pre-built cross-file definition registry. Languages without a Hybrid LSP pass yet fall back to textual resolution, so you always get *some* answer. The result is a knowledge graph accurate enough to drive `trace_path` across packages, inheritance hierarchies, and stdlib calls — without paying for a language server process per project. ## Language Support -158 languages, all parsed via vendored tree-sitter grammars compiled into the binary. Benchmarked against 64 real open-source repositories (78 to 49K nodes): +161 languages, all parsed via vendored tree-sitter grammars compiled into the binary. Benchmarked against 64 real open-source repositories (78 to 49K nodes): | Tier | Score | Languages | |------|-------|-----------| @@ -793,7 +793,7 @@ src/ traces/ Runtime trace ingestion ui/ Local HTTP server + verified external 3D-UI asset pack foundation/ Platform abstractions (threads, filesystem, logging, memory) -internal/cbm/ Vendored tree-sitter grammars (158 languages) + AST extraction engine +internal/cbm/ Vendored tree-sitter grammars (161 languages) + AST extraction engine ``` ## Security diff --git a/docs/index.html b/docs/index.html index 7e4a1c7aa..514456e7f 100644 --- a/docs/index.html +++ b/docs/index.html @@ -4,7 +4,7 @@ codebase-memory-mcp — Code Intelligence Knowledge Graph for AI Coding Agents - + @@ -12,7 +12,7 @@ - + @@ -24,7 +24,7 @@ - + @@ -41,7 +41,7 @@ "applicationSubCategory": "Model Context Protocol (MCP) server", "operatingSystem": "macOS, Linux, Windows", "softwareVersion": "0.8.1", - "description": "An open-source MCP server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links, so AI coding agents answer structural questions with roughly 120x fewer tokens than file-by-file search. Parses 158 languages via tree-sitter with Hybrid LSP semantic type resolution for 9 language families. Ships as a native executable with authenticated release-owned assets; the native install needs no language runtime.", + "description": "An open-source MCP server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links, so AI coding agents answer structural questions with roughly 120x fewer tokens than file-by-file search. Parses 161 languages via tree-sitter with Hybrid LSP semantic type resolution for 9 language families. Ships as a native executable with authenticated release-owned assets; the native install needs no language runtime.", "url": "https://deusdata.github.io/codebase-memory-mcp/", "downloadUrl": "https://github.com/DeusData/codebase-memory-mcp/releases/latest", "codeRepository": "https://github.com/DeusData/codebase-memory-mcp", @@ -125,7 +125,7 @@ "name": "What is codebase-memory-mcp?", "acceptedAnswer": { "@type": "Answer", - "text": "codebase-memory-mcp is an open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query that graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens. It parses 158 languages and ships as a native executable with authenticated release-owned assets; the native install needs no language runtime." + "text": "codebase-memory-mcp is an open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query that graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens. It parses 161 languages and ships as a native executable with authenticated release-owned assets; the native install needs no language runtime." } }, { @@ -141,7 +141,7 @@ "name": "Which programming languages does codebase-memory-mcp support?", "acceptedAnswer": { "@type": "Answer", - "text": "It supports 158 languages through vendored tree-sitter grammars compiled into the binary, including Python, Go, JavaScript, TypeScript, Rust, Java, C, C++, C#, PHP, Ruby, Kotlin, Swift, and many more. Nine language families — Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust — additionally get Hybrid LSP semantic type resolution." + "text": "It supports 161 languages through vendored tree-sitter grammars compiled into the binary, including Python, Go, JavaScript, TypeScript, Rust, Java, C, C++, C#, PHP, Ruby, Kotlin, Swift, and many more. Nine language families — Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust — additionally get Hybrid LSP semantic type resolution." } }, { @@ -444,7 +444,7 @@ The fastest, most efficient code intelligence engine for AI coding agents. It indexes any repository into a persistent knowledge graph — full-indexing an average repo in seconds and the Linux kernel in 3 minutes — so your agent answers structural questions with ~120x fewer tokens. - Tree-sitter parsing across 158 languages, Hybrid LSP type resolution, native executable with verified assets. + Tree-sitter parsing across 161 languages, Hybrid LSP type resolution, native executable with verified assets.

~120x
fewer tokens
@@ -483,7 +483,7 @@ Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. Instead of reading files one at a time, an AI coding agent queries the graph — answering structural questions with roughly 120x fewer - tokens. It parses 158 languages and ships as a native executable with authenticated release-owned assets; + tokens. It parses 161 languages and ships as a native executable with authenticated release-owned assets; the native install needs no language runtime.

@@ -606,7 +606,7 @@

- The two-layer pipeline runs a fast syntactic tree-sitter pass for every one of the 158 languages, + The two-layer pipeline runs a fast syntactic tree-sitter pass for every one of the 161 languages, then a type-aware Hybrid LSP pass on top for the families above. Languages without a Hybrid LSP pass yet fall back to textual resolution, so you always get an answer.

@@ -699,7 +699,7 @@

Features

-

158 languages

+

161 languages

Python, Go, JS, TS, TSX, Rust, Java, C++, C#, C, PHP, Ruby, Kotlin, Scala, Zig, Elixir, Haskell, OCaml, Swift, Dart, Lean 4, and many more via vendored tree-sitter grammars compiled into the binary.

diff --git a/docs/llms.txt b/docs/llms.txt index ce927ad91..4a18a3ac4 100644 --- a/docs/llms.txt +++ b/docs/llms.txt @@ -1,6 +1,6 @@ # codebase-memory-mcp -> An open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query the graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens (~3,400 vs ~412,000 across five structural queries). Parses 158 languages via vendored tree-sitter grammars, with Hybrid LSP semantic type resolution for Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust. It also generates semantic graph edges (SEMANTICALLY_RELATED for vocabulary-mismatch matches, SIMILAR_TO for near-clone detection) and supports semantic vector search via bundled nomic-embed-code embeddings compiled into the native executable — no API key, no Ollama, no Docker. Ships a native executable with an authenticated integration asset; the UI variant adds one content-addressed frontend pack. All processing is local — the embeddings run on-device; there is no embedded LLM and no API key. +> An open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query the graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens (~3,400 vs ~412,000 across five structural queries). Parses 161 languages via vendored tree-sitter grammars, with Hybrid LSP semantic type resolution for Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust. It also generates semantic graph edges (SEMANTICALLY_RELATED for vocabulary-mismatch matches, SIMILAR_TO for near-clone detection) and supports semantic vector search via bundled nomic-embed-code embeddings compiled into the native executable — no API key, no Ollama, no Docker. Ships a native executable with an authenticated integration asset; the UI variant adds one content-addressed frontend pack. All processing is local — the embeddings run on-device; there is no embedded LLM and no API key. ## Key facts diff --git a/pkg/chocolatey/codebase-memory-mcp.nuspec b/pkg/chocolatey/codebase-memory-mcp.nuspec index 0c8f3f177..d0509ecf1 100644 --- a/pkg/chocolatey/codebase-memory-mcp.nuspec +++ b/pkg/chocolatey/codebase-memory-mcp.nuspec @@ -18,7 +18,7 @@ release-owned runtime assets. Chocolatey retains the complete extracted runtime set and exposes its executable through a PATH shim. Full indexes an average repository in milliseconds, the Linux kernel (28M LOC) in -3 minutes. Answers structural queries in under 1ms. Supports 159 languages via +3 minutes. Answers structural queries in under 1ms. Supports 161 languages via vendored tree-sitter grammars. No hosted service or API key. Plug and play across 11 coding agents including Claude Code, Codex CLI, Gemini CLI, and Zed. diff --git a/pkg/npm/README.md b/pkg/npm/README.md index 2fed116ab..d46191594 100644 --- a/pkg/npm/README.md +++ b/pkg/npm/README.md @@ -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. This npm wrapper downloads, verifies, and caches the selected native runtime set: the executable, its authenticated integration asset, and—when requested—the content-addressed UI pack. -High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across 158 languages — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. No hosted service or API key; this package requires Node.js to manage and launch the cached native runtime set. Plug and play across 44 automatic/conditional client surfaces. +High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across 161 languages — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. No hosted service or API key; this package requires Node.js to manage and launch the cached native runtime set. Plug and play across 44 automatic/conditional client surfaces. ## Installation @@ -29,7 +29,7 @@ Restart your agent. Say **"Index this project"** — done. - **Extreme indexing speed** — Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline with LZ4 compression and in-memory SQLite. - **Plug and play** — verified native runtime sets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (arm64/amd64). No Docker or API keys; Node.js owns package download, cache repair, and launch. -- **158 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks. +- **161 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. - **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, Grok Build, 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. diff --git a/scripts/package-release.sh b/scripts/package-release.sh index 0aa00d4d2..1ee35c539 100755 --- a/scripts/package-release.sh +++ b/scripts/package-release.sh @@ -293,7 +293,7 @@ build_mcpb_bundle() { "name": "codebase-memory-mcp", "display_name": "Codebase Memory", "version": "$mcpb_version", - "description": "Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.", + "description": "Codebase knowledge graph for AI agents — 161 languages, sub-ms queries, 99% fewer tokens.", "author": { "name": "DeusData", "url": "https://github.com/DeusData" }, "repository": { "type": "git", "url": "https://github.com/DeusData/codebase-memory-mcp" }, "homepage": "https://deusdata.github.io/codebase-memory-mcp/", diff --git a/server.json b/server.json index dc49e586e..93bcccc3b 100644 --- a/server.json +++ b/server.json @@ -2,7 +2,7 @@ "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json", "name": "io.github.DeusData/codebase-memory-mcp", "title": "Codebase Memory", - "description": "Codebase knowledge graph for AI agents \u2014 159 languages, sub-ms queries, 99% fewer tokens.", + "description": "Codebase knowledge graph for AI agents \u2014 161 languages, sub-ms queries, 99% fewer tokens.", "repository": { "url": "https://github.com/DeusData/codebase-memory-mcp", "source": "github" diff --git a/tests/test_language_count_contract.sh b/tests/test_language_count_contract.sh index 7093e41d4..1b664c0d1 100644 --- a/tests/test_language_count_contract.sh +++ b/tests/test_language_count_contract.sh @@ -73,7 +73,7 @@ EXEMPT=( ) failures=0 -claims=0 +distinct=0 for path in "${SURFACES[@]}"; do if [[ ! -f "$path" ]]; then @@ -90,7 +90,7 @@ for path in "${SURFACES[@]}"; do continue fi while IFS= read -r n; do - claims=$((claims + 1)) + distinct=$((distinct + 1)) if [[ "$n" != "$expected" ]]; then echo "FAIL: $path claims $n languages, $expected grammars are vendored" >&2 failures=$((failures + 1)) @@ -120,4 +120,4 @@ if ((failures > 0)); then exit 1 fi -echo "Language-count contract passed ($claims claims across ${#SURFACES[@]} surfaces, registry = $expected)" +echo "Language-count contract passed (${#SURFACES[@]} surfaces, $distinct distinct value(s) checked, $expected grammars vendored)"