obsidian-llm-wiki-local
Local-first AI wiki that integrates Markdown notes with LLMs for auto-linking concepts and personal knowledge management.
GraphCanon updated Aug 12, 2026 · GitHub synced Aug 12, 2026
31views this month
Decision brief
Local-first AI wiki for auto-linking Markdown notes with LLMs in Obsidian, designed to maintain user privacy.
Good fit when
- When you require a self-contained wiki solution that uses local Large Language Models (LLMs) and keeps all data private.
- For integrating with Obsidian, if your workflow involves extensive use of Markdown for note-taking and you want AI assistance in linking concepts.
Avoid when
- If you do not have a preference for using local LLMs over cloud-based solutions that might offer more powerful models.
- When you are willing to share your data with external services for potentially better integration features or enhanced AI capabilities.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (78d since push)
- As of Aug 12, 2026
- Provenance
- Not a fork · Personal account
- As of Aug 12, 2026
- Security (OSV)
- No lockfile
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install obsidian-llm-wiki-localSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
This repository provides an automated process to extract key ideas from Markdown notes and link them in an Obsidian-based wiki using local large language models (LLMs). The system offers a self-contained solution where the user's data remains private.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 12, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 12, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
1. Install From PyPI (recommended): Or with : From source (latest development version): detects or falls back to , verifies the install, and tells you to run the next step. Install Ollama: https://ollama.com/download ollama pull gemma4:e4b fast model — analysis and routing ollama...
For agents
This page has a .md twin and JSON over the API.