codeembed 0.1.0__tar.gz

codeembed-0.1.0/.claude/settings.local.json

@@ -0,0 +1,6 @@
+{
+  "enabledMcpjsonServers": ["codeembed"],
+  "permissions": {
+    "allow": ["mcp__codeembed__search"]
+  }
+}

codeembed-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,24 @@
+name: CI
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+      - run: uvx ruff check .
+      - run: uvx ruff format --check .
+
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+      - run: uv sync
+      - run: uv pip check
+      - run: uv run pip-audit
+      - run: uv run pytest

codeembed-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,29 @@
+name: Release to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+permissions:
+  contents: read
+  id-token: write
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+
+      - name: Build
+        run: uv build
+
+      - name: Validate
+        run: uvx twine check dist/*
+
+      - name: Publish
+        run: uv publish --trusted-publishing always

codeembed-0.1.0/.gitignore

@@ -0,0 +1,212 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# App
+.codeembed/
+
+temp/

codeembed-0.1.0/.mcp.json

@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "codeembed": {
+      "command": "uv",
+      "args": ["run", "codeembed", "serve"]
+    }
+  }
+}

codeembed-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.15.12
+    hooks:
+      # Run the linter.
+      - id: ruff-check
+        args: [--fix]
+      # Run the formatter.
+      - id: ruff-format

codeembed-0.1.0/.python-version

@@ -0,0 +1 @@
+3.14

codeembed-0.1.0/.vscode/mcp.json

@@ -0,0 +1,8 @@
+{
+  "servers": {
+    "codeembed": {
+      "command": "uv",
+      "args": ["run", "codeembed", "serve"]
+    }
+  }
+}

codeembed-0.1.0/AGENTS.md

@@ -0,0 +1,18 @@
+# Agent Instructions
+
+## Python Coding Standards
+
+- Use `Union` (from `typing`) instead of `|`.
+- Use `Optional[<type>]` instead of `<type> | None`.
+- Strictly use type hints for all functions and methods.
+- Run tests with `uv run --no-sync pytest` (`--no-sync` flag is important).
+
+## General
+
+When asked for a PR review, do a simple git diff against the main branch.
+Do not read PRs from GitHub.
+Do not use PR skill.
+
+## Codebase search
+
+Use the `mcp__codeembed__search` tool as the first step for any question about how this codebase works — how something is implemented, where something is defined, what calls what. Prefer it over grep or file reads for exploratory questions.

codeembed-0.1.0/CHANGELOG.md

@@ -0,0 +1,7 @@
+# Changelog
+
+## Unreleased
+
+## 0.1.0
+
+Initial version.

codeembed-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 robino16/robinoms
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

codeembed-0.1.0/PKG-INFO

@@ -0,0 +1,292 @@
+Metadata-Version: 2.4
+Name: codeembed
+Version: 0.1.0
+Summary: Embeds your codebase and makes it available for quick LLM lookups via MCP.
+Project-URL: Homepage, https://github.com/robino16/codeembed
+Project-URL: Repository, https://github.com/robino16/codeembed
+Project-URL: Issues, https://github.com/robino16/codeembed/issues
+Author-email: robino16 <robinoms.dev@proton.me>
+License: MIT License
+        
+        Copyright (c) 2026 robino16/robinoms
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: codebase,embeddings,llm,mcp,rag,vector-search
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.11
+Requires-Dist: chromadb<2,>=1.5
+Requires-Dist: mcp<2,>=1.26
+Requires-Dist: ollama<1,>=0.6
+Requires-Dist: pydantic<3,>=2.13
+Requires-Dist: python-dotenv<2,>=1.2.2
+Requires-Dist: tiktoken<1,>=0.12
+Provides-Extra: openai
+Requires-Dist: azure-identity<2,>=1.25; extra == 'openai'
+Requires-Dist: openai<3,>=2.33; extra == 'openai'
+Description-Content-Type: text/markdown
+
+# CodeEmbed
+
+Embeds your codebase into a local vector database and exposes it as an MCP tool, giving AI assistants like Claude Code fast semantic search over your code.
+
+Particularly useful for questions like:
+
+- How is X implemented in this repo?
+- Where is X defined or used?
+- Does this repo already have X?
+
+For other questions, the agent will fall back to normal lookups.
+CodeEmbed can improve lookup speed and accuracy, especially for finding existing implementations before writing new ones.
+Note that the biggest bottleneck in coding agents is LLM thinking and token generation — solid prompts and follow-up questions still matter.
+
+Uses [ChromaDB](https://github.com/chroma-core/chroma) for local vector storage and either [Ollama](https://github.com/ollama/ollama) or OpenAI (including OpenAI models via Azure AI Foundry) for LLM analysis.
+
+## Prerequisites
+
+- [Python](https://python.org) 3.11+
+- [uv](https://github.com/astral-sh/uv)
+- One of:
+  - [Ollama](https://ollama.com) running locally, **or**
+  - An OpenAI API key or Azure OpenAI endpoint
+
+## Installation
+
+**With Ollama:**
+
+```bash
+uv tool install codeembed
+```
+
+**With OpenAI / Azure OpenAI:**
+
+```bash
+uv tool install 'codeembed[openai]'
+```
+
+> **Supply chain safety:** To reduce the risk of newly-published malicious packages, consider adding `exclude-newer = "7 days"` to your global [`uv.toml`](https://docs.astral.sh/uv/reference/settings/#exclude-newer). This prevents `uv` from installing packages published in the last 7 days.
+
+### Manual installation (from source)
+
+If CodeEmbed is not published to PyPI, install it directly from source:
+
+```bash
+git clone https://github.com/robino16/codeembed
+cd codeembed
+
+# With Ollama
+uv tool install .
+
+# With OpenAI support
+uv tool install '.[openai]'
+```
+
+Then run `codeembed init` inside of your target repository.
+
+## Upgrading
+
+```bash
+uv tool upgrade codeembed
+```
+
+## Usage
+
+CodeEmbed is intended to be used within a single project — run all commands from your project root. Each project gets its own local vector database stored in `.codeembed/`.
+
+Supported file types: `.py`, `.md`, `.ts`, `.tsx`, `.js`, `.jsx`.
+
+**1. Initialize** (run once in your project root):
+
+```bash
+codeembed init
+```
+
+Creates a `codeembed.toml` config and configures your `.gitignore`. You'll be prompted to select a provider (Ollama or OpenAI) and a model. You'll also be offered the option to automatically configure Claude Code and/or GitHub Copilot.
+
+**2. Pre-populate the index:**
+
+```bash
+codeembed embed
+```
+
+Run this before starting the server to pre-populate the index. Searches will return empty results until the first file has been embedded.
+
+CodeEmbed respects your project's `.gitignore` and also excludes typical environment directories and files (`.env`, `venv`, `node_modules`, etc.) by default.
+
+**3. Start the MCP server:**
+
+```bash
+codeembed serve
+```
+
+Starts the MCP server.
+If the MCP server is added to Claude or GitHub Copilot, you do not need to do this.
+
+The `serve` command will embed your codebase in the background - by default it will scan for changes every 60 seconds.
+
+## Configuring OpenAI
+
+If you use the OpenAI provider, credentials are read from environment variables. The recommended approach is a `.env` file. `codeembed init` will ask for the path, and it will be stored in `codeembed.toml` so `codeembed serve` and `codeembed embed` loads the `.env` file automatically.
+
+### Standard OpenAI
+
+```env
+OPENAI_API_KEY=...
+```
+
+Optionally override the endpoint (for compatible APIs like vLLM, LM Studio, OpenRouter):
+
+```env
+OPENAI_API_KEY=...
+OPENAI_BASE_URL=...
+```
+
+### Azure OpenAI — API key
+
+```env
+AZURE_OPENAI_ENDPOINT=https://<your-resource>.openai.azure.com/openai/v1/
+AZURE_OPENAI_API_KEY=...
+```
+
+### Azure OpenAI — RBAC / Entra ID (keyless)
+
+Set only the endpoint; CodeEmbed will use `DefaultAzureCredential`, which automatically tries multiple credential sources in order — service principals (via env vars), workload identity, managed identity, VS Code Azure sign-in, `az login`, Azure PowerShell, and `azd auth login` — falling back to an interactive browser window if none are found automatically:
+
+```env
+AZURE_OPENAI_ENDPOINT=https://<your-resource>.openai.azure.com/openai/v1/
+```
+
+## Add to Claude Code or GitHub Copilot
+
+`codeembed init` will offer to configure these automatically. If you prefer to do it manually:
+
+**Claude Code** — add to `.mcp.json` in your project root:
+
+```json
+{
+  "mcpServers": {
+    "codeembed": {
+      "command": "codeembed",
+      "args": ["serve"]
+    }
+  }
+}
+```
+
+And add to `.claude/settings.local.json` to enable and pre-approve the tool:
+
+```json
+{
+  "enabledMcpjsonServers": ["codeembed"],
+  "permissions": {
+    "allow": ["mcp__codeembed__search"]
+  }
+}
+```
+
+**GitHub Copilot** — add to `.vscode/mcp.json`:
+
+```json
+{
+  "servers": {
+    "codeembed": {
+      "command": "codeembed",
+      "args": ["serve"]
+    }
+  }
+}
+```
+
+The MCP server exposes a single `search(query)` tool for semantic search over your codebase.
+
+## Contributing
+
+Clone this repo with:
+
+```bash
+git clone git@github.com:robino16/codeembed.git
+```
+
+```bash
+cd codeembed
+uv sync
+```
+
+Check for dependency conflicts with:
+
+```bash
+uv pip check
+```
+
+Check for package vulnerabilities with:
+
+```bash
+uv run pip-audit
+```
+
+(Optional) Add Ruff pre-commit with:
+
+```bash
+pre-commit install
+```
+
+Update init files:
+
+```bash
+uv run --no-sync scripts/generate_init_files.py
+```
+
+Run linter:
+
+```bash
+ruff check . --fix
+```
+
+Run formatter:
+
+```bash
+ruff format .
+```
+
+Run tests:
+
+```bash
+uv run --no-sync pytest
+```
+
+Build with:
+
+```bash
+uv build
+```
+
+Validate build with:
+
+```bash
+uv run twine check dist/*
+```
+
+> `--no-sync` is required for local dev commands when the MCP server is running, as uv holds a lock that blocks sync operations.