Dendron Mesh
Hierarchical Git-Native Knowledge Base & Agent Memory (CLI & Stdio MCP Server)
dendron-mesh liberates the hierarchical dot-notation knowledge paradigm of Dendron from VS Code extension lock-in into a zero-dependency, standalone Python engine built for both humans and autonomous AI agents.
✨ Key Features
- Dot-Notation Hierarchy: Organize notes cleanly as flat Markdown files (
root.md,cloud.aws.iam.md,agents.memory.decisions.md) that form a dynamic knowledge tree. - Native Wiki-Links & Backlink Graph: Automatic extraction of
[[target.note]]links and bidirectional backlink indexing. - Full-Text Search: Fast local search across all notes in your vault.
- Zero-Dependency: Pure Python 3.9+ standard library. No Node.js, no VS Code, no external database required.
- Dual Interface: Use it directly as a Standalone CLI (
dendron-mesh) or as a Stdio MCP Server (dendron-mcp) for Claude Desktop, Cursor, Antigravity, LangGraph, and CrewAI.
🚀 Installation
pip install dendron-mesh
Or run directly from source:
git clone https://github.com/tastenkasperle/dendron_mesh.git
cd dendron_mesh
pip install -e .
🛠️ CLI Usage
# Create a hierarchical note
dendron-mesh create cloud.aws.iam --title "AWS IAM Best Practices" --body "Use least-privilege roles. See [[security.zero-trust]]."
# Read a note
dendron-mesh read cloud.aws.iam
# Visualize the knowledge tree
dendron-mesh tree
# Inspect backlinks for a note
dendron-mesh backlinks security.zero-trust
# Search across the vault
dendron-mesh search "least-privilege"
🤖 MCP Server Integration
Add dendron-mesh to your MCP client configuration (e.g., claude_desktop_config.json or mcp_config.json):
{
"mcpServers": {
"dendron-mesh": {
"command": "dendron-mcp",
"args": []
}
}
}
Exposed MCP Tools
dendron_create_note— Create or update a hierarchical note with optional frontmatter & bodydendron_read_note— Read a note's metadata and markdown contentdendron_get_tree— Return the hierarchical dot-notation knowledge treedendron_get_backlinks— List all notes referencing a target note via[[wiki-links]]dendron_search— Full-text search across the vault
🧪 Testing
python -m pytest -v
📄 License
MIT © 2026 THE HIVE // BSO
Metadata
Release files for dendron-mesh 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| dendron_mesh-1.0.0.tar.gz | 8.8 kB | Without provenance | Details for dendron_mesh-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| dendron_mesh-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for dendron_mesh-1.0.0-py3-none-any.whl |
Total release size: 17.8 kB
Release files / dendron_mesh-1.0.0.tar.gz
| Download URL | dendron_mesh-1.0.0.tar.gz |
|---|---|
| Size | 8.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
56d986b97f93ac305161ec93a36c7b8293c2a75abd22b01d30c3ee17f066b910
|
|
BLAKE2b-256 checksum How to use checksums |
8b97fdf22cf2049591f0a66c8f21334b819a7004bb8580bda00a63ab616f7b6e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Release files / dendron_mesh-1.0.0-py3-none-any.whl
| Download URL | dendron_mesh-1.0.0-py3-none-any.whl |
|---|---|
| Size | 9.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
523a938c2294fae0fb8f71473a481af77db8a3e72fc006bb016ddd13b6847f5e
|
|
BLAKE2b-256 checksum How to use checksums |
0bd516bbf21a32b0e2cd0ad4cd2d530dd8aaca8811ffd18b0db0a5aeefc053c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Security for dendron-mesh 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.