memtomem 0.1.0__tar.gz

memtomem-0.1.0/.gitignore

@@ -0,0 +1,55 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Test / CI artifacts
+.coverage
+coverage.json
+
+# Environment
+.env
+.env.*
+!.env.example
+!.env.*.example
+.mcp.json
+!.mcp.json.example
+
+# Claude Code
+.claude/
+CLAUDE.md
+.claude-plugin/
+
+# macOS
+.DS_Store
+
+# Jupyter checkpoints
+.ipynb_checkpoints/
+notebooks/**/.ipynb_checkpoints/
+
+# Notebooks
+notebooks/__pycache__/
+memories/
+node_modules/
+
+# Internal development artifacts
+docs/testing/
+docs/marketing/
+.claude-memory/
+BUG_REPORT.md
+*.png
+main.py
+
+# Dev repo: root tests excluded, package tests included
+tests/
+!packages/*/tests/
+.playwright-mcp/
+
+# Standalone test sandbox
+/tmp/memtomem-test/

memtomem-0.1.0/LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2025 memtomem contributors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

memtomem-0.1.0/PKG-INFO

@@ -0,0 +1,137 @@
+Metadata-Version: 2.4
+Name: memtomem
+Version: 0.1.0
+Summary: Markdown-first memory infrastructure for AI agents with hybrid search
+Project-URL: Homepage, https://github.com/memtomem/memtomem
+Project-URL: Repository, https://github.com/memtomem/memtomem
+Author: memtomem contributors
+License: Apache-2.0
+License-File: LICENSE
+Keywords: agent,ai,embedding,markdown,mcp,memory,rag,search
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.12
+Requires-Dist: click>=8.1
+Requires-Dist: httpx>=0.28
+Requires-Dist: mcp[cli]>=1.26.0
+Requires-Dist: pydantic-settings>=2.7
+Requires-Dist: pydantic>=2.10
+Requires-Dist: sqlite-vec>=0.1.6
+Requires-Dist: watchdog>=6.0
+Provides-Extra: all
+Requires-Dist: fastapi>=0.115; extra == 'all'
+Requires-Dist: kiwipiepy>=0.18; extra == 'all'
+Requires-Dist: ollama>=0.4; extra == 'all'
+Requires-Dist: openai>=1.60; extra == 'all'
+Requires-Dist: tree-sitter-javascript>=0.23; extra == 'all'
+Requires-Dist: tree-sitter-python>=0.23; extra == 'all'
+Requires-Dist: tree-sitter-typescript>=0.23; extra == 'all'
+Requires-Dist: tree-sitter>=0.25; extra == 'all'
+Requires-Dist: uvicorn[standard]>=0.34; extra == 'all'
+Provides-Extra: code
+Requires-Dist: tree-sitter-javascript>=0.23; extra == 'code'
+Requires-Dist: tree-sitter-python>=0.23; extra == 'code'
+Requires-Dist: tree-sitter-typescript>=0.23; extra == 'code'
+Requires-Dist: tree-sitter>=0.25; extra == 'code'
+Provides-Extra: korean
+Requires-Dist: kiwipiepy>=0.18; extra == 'korean'
+Provides-Extra: ollama
+Requires-Dist: ollama>=0.4; extra == 'ollama'
+Provides-Extra: openai
+Requires-Dist: openai>=1.60; extra == 'openai'
+Provides-Extra: web
+Requires-Dist: fastapi>=0.115; extra == 'web'
+Requires-Dist: uvicorn[standard]>=0.34; extra == 'web'
+Description-Content-Type: text/markdown
+
+# memtomem
+
+Markdown-first long-term memory infrastructure for AI agents. Hybrid keyword + semantic search across your notes, docs, and code via the Model Context Protocol.
+
+**Core philosophy**: `.md` files are the source of truth and the vector database is a derived cache. Manage memories as plain text files — memtomem makes them instantly searchable.
+
+**Built for:**
+- AI agents (Claude Code, Cursor, Windsurf, Claude Desktop) that need to *remember* between sessions
+- Developers who want a searchable knowledge base built from their existing markdown notes — no proprietary database, no vendor lock-in
+- Multilingual content (English, Korean, Japanese, Chinese) via `bge-m3` embeddings
+
+## Installation
+
+```bash
+# As an MCP server (most common — no install needed, uvx handles it)
+ollama pull nomic-embed-text         # one-time embedding model
+
+# Add to Claude Code
+claude mcp add memtomem -s user -- uvx --from memtomem memtomem-server
+
+# Or add to .mcp.json for Cursor / Windsurf / Claude Desktop
+```
+
+```json
+{
+  "mcpServers": {
+    "memtomem": {
+      "command": "uvx",
+      "args": ["--from", "memtomem", "memtomem-server"],
+      "env": {
+        "MEMTOMEM_INDEXING__MEMORY_DIRS": "/path/to/your/notes"
+      }
+    }
+  }
+}
+```
+
+For terminal use, install the CLI separately:
+
+```bash
+uv tool install memtomem    # or: pipx install memtomem
+mm init                     # 7-step interactive wizard
+```
+
+## Quick Start
+
+In your AI editor, ask:
+
+```
+"Index my notes folder"   →  mem_index(path="~/notes")
+"Search for deployment"   →  mem_search(query="deployment checklist")
+"Remember this insight"   →  mem_add(content="...", tags="ops")
+```
+
+That's it. Your agent now has a long-term memory built from plain markdown files.
+
+## Key Features
+
+- **🔍 Hybrid search** — BM25 (FTS5) + dense vectors (sqlite-vec) merged via Reciprocal Rank Fusion. Exact terms via keyword, meaning via semantic, both at once.
+- **📦 Semantic chunking** — heading-aware Markdown, AST-based Python, tree-sitter JS/TS, structure-aware JSON/YAML/TOML
+- **♻️ Incremental indexing** — chunk-level SHA-256 diff means only changed chunks get re-embedded
+- **🏷️ Namespaces** — scope memories into groups (work / personal / project) with optional auto-derivation from folder names
+- **🧹 Maintenance** — near-duplicate detection with merge, time-based score decay, TTL expiration, auto-tagging
+- **🔄 Export / import** — JSON bundle backup and restore with re-embedding
+- **🌐 Web UI** — full-featured SPA dashboard for search, sources, indexing, tags, sessions, health monitoring
+- **🛠️ 72 MCP tools** — full feature surface as MCP tools, with `mem_do` meta-tool routing 64 actions in `core` mode (default) for minimal context usage
+
+## Documentation
+
+Full documentation lives in the [memtomem GitHub repo](https://github.com/memtomem/memtomem):
+
+| Guide | Topic |
+|-------|-------|
+| [Getting Started](https://github.com/memtomem/memtomem/blob/main/docs/guides/getting-started.md) | **Start here** — install, setup wizard, first use |
+| [Hands-On Tutorial](https://github.com/memtomem/memtomem/blob/main/docs/guides/hands-on-tutorial.md) | Follow-along with example files |
+| [User Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/user-guide.md) | Complete feature walkthrough — all tools and patterns |
+| [Configuration](https://github.com/memtomem/memtomem/blob/main/docs/guides/configuration.md) | All `MEMTOMEM_*` environment variables |
+| [Embeddings](https://github.com/memtomem/memtomem/blob/main/docs/guides/embeddings.md) | Ollama and OpenAI providers, model dimensions, switching models |
+| [MCP Client Setup](https://github.com/memtomem/memtomem/blob/main/docs/guides/mcp-clients.md) | Editor-specific configuration |
+| [Agent Memory Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/agent-memory-guide.md) | Sessions, working memory, procedures, multi-agent |
+| [Web UI Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/web-ui.md) | Visual dashboard reference |
+| [Hooks](https://github.com/memtomem/memtomem/blob/main/docs/guides/hooks.md) | Claude Code hooks for automatic indexing and search |
+| [memtomem-stm](https://github.com/memtomem/memtomem-stm) | Optional STM proxy for proactive memory surfacing (separate package) |
+
+## License
+
+Apache License 2.0 — see [LICENSE](https://github.com/memtomem/memtomem/blob/main/LICENSE) for details.

memtomem-0.1.0/README.md

@@ -0,0 +1,87 @@
+# memtomem
+
+Markdown-first long-term memory infrastructure for AI agents. Hybrid keyword + semantic search across your notes, docs, and code via the Model Context Protocol.
+
+**Core philosophy**: `.md` files are the source of truth and the vector database is a derived cache. Manage memories as plain text files — memtomem makes them instantly searchable.
+
+**Built for:**
+- AI agents (Claude Code, Cursor, Windsurf, Claude Desktop) that need to *remember* between sessions
+- Developers who want a searchable knowledge base built from their existing markdown notes — no proprietary database, no vendor lock-in
+- Multilingual content (English, Korean, Japanese, Chinese) via `bge-m3` embeddings
+
+## Installation
+
+```bash
+# As an MCP server (most common — no install needed, uvx handles it)
+ollama pull nomic-embed-text         # one-time embedding model
+
+# Add to Claude Code
+claude mcp add memtomem -s user -- uvx --from memtomem memtomem-server
+
+# Or add to .mcp.json for Cursor / Windsurf / Claude Desktop
+```
+
+```json
+{
+  "mcpServers": {
+    "memtomem": {
+      "command": "uvx",
+      "args": ["--from", "memtomem", "memtomem-server"],
+      "env": {
+        "MEMTOMEM_INDEXING__MEMORY_DIRS": "/path/to/your/notes"
+      }
+    }
+  }
+}
+```
+
+For terminal use, install the CLI separately:
+
+```bash
+uv tool install memtomem    # or: pipx install memtomem
+mm init                     # 7-step interactive wizard
+```
+
+## Quick Start
+
+In your AI editor, ask:
+
+```
+"Index my notes folder"   →  mem_index(path="~/notes")
+"Search for deployment"   →  mem_search(query="deployment checklist")
+"Remember this insight"   →  mem_add(content="...", tags="ops")
+```
+
+That's it. Your agent now has a long-term memory built from plain markdown files.
+
+## Key Features
+
+- **🔍 Hybrid search** — BM25 (FTS5) + dense vectors (sqlite-vec) merged via Reciprocal Rank Fusion. Exact terms via keyword, meaning via semantic, both at once.
+- **📦 Semantic chunking** — heading-aware Markdown, AST-based Python, tree-sitter JS/TS, structure-aware JSON/YAML/TOML
+- **♻️ Incremental indexing** — chunk-level SHA-256 diff means only changed chunks get re-embedded
+- **🏷️ Namespaces** — scope memories into groups (work / personal / project) with optional auto-derivation from folder names
+- **🧹 Maintenance** — near-duplicate detection with merge, time-based score decay, TTL expiration, auto-tagging
+- **🔄 Export / import** — JSON bundle backup and restore with re-embedding
+- **🌐 Web UI** — full-featured SPA dashboard for search, sources, indexing, tags, sessions, health monitoring
+- **🛠️ 72 MCP tools** — full feature surface as MCP tools, with `mem_do` meta-tool routing 64 actions in `core` mode (default) for minimal context usage
+
+## Documentation
+
+Full documentation lives in the [memtomem GitHub repo](https://github.com/memtomem/memtomem):
+
+| Guide | Topic |
+|-------|-------|
+| [Getting Started](https://github.com/memtomem/memtomem/blob/main/docs/guides/getting-started.md) | **Start here** — install, setup wizard, first use |
+| [Hands-On Tutorial](https://github.com/memtomem/memtomem/blob/main/docs/guides/hands-on-tutorial.md) | Follow-along with example files |
+| [User Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/user-guide.md) | Complete feature walkthrough — all tools and patterns |
+| [Configuration](https://github.com/memtomem/memtomem/blob/main/docs/guides/configuration.md) | All `MEMTOMEM_*` environment variables |
+| [Embeddings](https://github.com/memtomem/memtomem/blob/main/docs/guides/embeddings.md) | Ollama and OpenAI providers, model dimensions, switching models |
+| [MCP Client Setup](https://github.com/memtomem/memtomem/blob/main/docs/guides/mcp-clients.md) | Editor-specific configuration |
+| [Agent Memory Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/agent-memory-guide.md) | Sessions, working memory, procedures, multi-agent |
+| [Web UI Guide](https://github.com/memtomem/memtomem/blob/main/docs/guides/web-ui.md) | Visual dashboard reference |
+| [Hooks](https://github.com/memtomem/memtomem/blob/main/docs/guides/hooks.md) | Claude Code hooks for automatic indexing and search |
+| [memtomem-stm](https://github.com/memtomem/memtomem-stm) | Optional STM proxy for proactive memory surfacing (separate package) |
+
+## License
+
+Apache License 2.0 — see [LICENSE](https://github.com/memtomem/memtomem/blob/main/LICENSE) for details.

memtomem-0.1.0/pyproject.toml

@@ -0,0 +1,59 @@
+[project]
+name = "memtomem"
+version = "0.1.0"
+description = "Markdown-first memory infrastructure for AI agents with hybrid search"
+authors = [{name = "memtomem contributors"}]
+license = {text = "Apache-2.0"}
+keywords = ["memory", "ai", "mcp", "agent", "rag", "embedding", "search", "markdown"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "mcp[cli]>=1.26.0",
+    "pydantic>=2.10",
+    "pydantic-settings>=2.7",
+    "sqlite-vec>=0.1.6",
+    "httpx>=0.28",
+    "watchdog>=6.0",
+    "click>=8.1",
+]
+
+[project.optional-dependencies]
+ollama = ["ollama>=0.4"]
+openai = ["openai>=1.60"]
+korean = ["kiwipiepy>=0.18"]
+code = [
+    "tree-sitter>=0.25",
+    "tree-sitter-python>=0.23",
+    "tree-sitter-javascript>=0.23",
+    "tree-sitter-typescript>=0.23",
+]
+web = [
+    "fastapi>=0.115",
+    "uvicorn[standard]>=0.34",
+]
+all = ["memtomem[ollama,openai,korean,code,web]"]
+
+[project.scripts]
+memtomem = "memtomem.cli:cli"
+mm = "memtomem.cli:cli"
+memtomem-server = "memtomem.server:main"
+memtomem-web = "memtomem.web.app:main"
+
+[project.urls]
+Homepage = "https://github.com/memtomem/memtomem"
+Repository = "https://github.com/memtomem/memtomem"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/memtomem"]

memtomem-0.1.0/src/memtomem/__init__.py

@@ -0,0 +1,3 @@
+"""memtomem: Markdown-first memory infrastructure for AI agents."""
+
+__version__ = "0.1.0"

memtomem-0.1.0/src/memtomem/chunking/base.py

@@ -0,0 +1,13 @@
+"""Chunker protocol."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Protocol
+
+from memtomem.models import Chunk
+
+
+class Chunker(Protocol):
+    def supported_extensions(self) -> frozenset[str]: ...
+    def chunk_file(self, file_path: Path, content: str) -> list[Chunk]: ...

memtomem-0.1.0/src/memtomem/chunking/javascript.py

@@ -0,0 +1,119 @@
+"""JavaScript/TypeScript chunker using tree-sitter AST (optional dependency)."""
+
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+
+from memtomem.models import Chunk, ChunkMetadata, ChunkType
+
+logger = logging.getLogger(__name__)
+
+_TOP_LEVEL_TYPES = frozenset(
+    {
+        "function_declaration",
+        "class_declaration",
+        "generator_function_declaration",
+        "export_statement",
+        "lexical_declaration",  # const foo = () => {}
+        "variable_declaration",  # var/let foo = function() {}
+    }
+)
+
+
+class JavaScriptChunker:
+    """Chunks JS/TS files by top-level declarations.
+
+    Falls back to a single whole-file chunk if tree-sitter-javascript /
+    tree-sitter-typescript is not installed or parsing fails.
+    """
+
+    def supported_extensions(self) -> frozenset[str]:
+        return frozenset({".js", ".ts", ".jsx", ".tsx", ".mjs"})
+
+    def chunk_file(self, file_path: Path, content: str) -> list[Chunk]:
+        if not content.strip():
+            return []
+        try:
+            return self._ast_chunk(file_path, content)
+        except Exception:
+            logger.debug(
+                "JS/TS AST parsing failed for %s, using fallback", file_path, exc_info=True
+            )
+            return self._fallback(file_path, content)
+
+    def _ast_chunk(self, file_path: Path, content: str) -> list[Chunk]:
+        from tree_sitter import Language, Parser  # type: ignore[import]
+
+        if file_path.suffix in {".ts", ".tsx"}:
+            import tree_sitter_typescript as tsts  # type: ignore[import]
+
+            lang = Language(tsts.language_typescript())
+            lang_name = "typescript"
+        else:
+            import tree_sitter_javascript as tsjs  # type: ignore[import]
+
+            lang = Language(tsjs.language())
+            lang_name = "javascript"
+
+        parser = Parser(lang)
+        tree = parser.parse(content.encode())
+
+        lines = content.splitlines()
+        module_stem = file_path.stem
+        chunks: list[Chunk] = []
+
+        for node in tree.root_node.children:
+            if node.type not in _TOP_LEVEL_TYPES:
+                continue
+
+            name = self._extract_name(node, content)
+            start_line = node.start_point[0] + 1
+            end_line = node.end_point[0] + 1
+            body = "\n".join(lines[start_line - 1 : end_line])
+
+            chunks.append(
+                Chunk(
+                    content=body,
+                    metadata=ChunkMetadata(
+                        source_file=file_path,
+                        heading_hierarchy=(module_stem, name) if name else (module_stem,),
+                        chunk_type=ChunkType.JS_FUNCTION,
+                        start_line=start_line,
+                        end_line=end_line,
+                        language=lang_name,
+                    ),
+                )
+            )
+
+        return chunks if chunks else self._fallback(file_path, content)
+
+    @classmethod
+    def _extract_name(cls, node, content: str) -> str:
+        for child in node.children:
+            if child.type in ("function_declaration", "class_declaration", "lexical_declaration"):
+                return cls._extract_name(child, content)
+            if child.type == "identifier":
+                return content[child.start_byte : child.end_byte]
+            if child.type == "variable_declarator":
+                for grandchild in child.children:
+                    if grandchild.type == "identifier":
+                        return content[grandchild.start_byte : grandchild.end_byte]
+        return ""
+
+    def _fallback(self, file_path: Path, content: str) -> list[Chunk]:
+        lang = "typescript" if file_path.suffix in {".ts", ".tsx"} else "javascript"
+        lines = content.splitlines()
+        return [
+            Chunk(
+                content=content,
+                metadata=ChunkMetadata(
+                    source_file=file_path,
+                    heading_hierarchy=(file_path.stem,),
+                    chunk_type=ChunkType.RAW_TEXT,
+                    start_line=1,
+                    end_line=len(lines),
+                    language=lang,
+                ),
+            )
+        ]