by liliu-z
Turn your local files into a Wiki for your agents. Open-source and local-first.
# Add to your Claude Code skills
git clone https://github.com/liliu-z/stashbaseLast scanned: 7/30/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@electron/asar: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@electron/universal: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "app-builder-lib: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "brace-expansion: brace-expansion: DoS via unbounded expansion length causing an out-of-memory process crash",
"severity": "high"
},
{
"type": "npm-audit",
"message": "dir-compare: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "dmg-builder: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "ejs: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "electron-builder: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "electron-builder-squirrel-windows: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "electron-winstaller: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "filelist: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "glob: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "jake: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "minimatch: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "rimraf: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "temp: Vulnerability found",
"severity": "high"
}
],
"status": "WARNING",
"scannedAt": "2026-07-30T06:27:15.682Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how stashbase compares with popular alternatives.
stashbase is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by liliu-z. Turn your local files into a Wiki for your agents. Open-source and local-first. It has 632 GitHub stars.
stashbase returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/liliu-z/stashbase" and add it to your Claude Code skills directory (see the Installation section above).
stashbase is primarily written in TypeScript. It is open-source under liliu-z on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh stashbase against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Turn your local files into a Wiki for your agents.
StashBase is an open-source, local-first app that helps your agents find and reuse context across personal notes, research libraries, project docs, and knowledge bases.
Build linked Markdown Wiki Pages from your sources, make difficult formats searchable, and work with OpenQuill, Claude Code, Codex, or other MCP clients. Your original files stay in place, and the Wiki Pages remain ordinary files you own.
Browse local sources and work with an Agent in the same workspace. This demo uses the bundled guides to answer “How do I use StashBase?”

Giving an Agent access to a folder is a starting point. Useful evidence may be buried in a long document, use different words from your question, or live in a scan or recording. StashBase helps turn that material into reusable context:
macOS 12+ (Apple Silicon) and Windows 10+ (x64) are the primary platforms. Linux x86_64 Debian 12+ / Ubuntu 22.04+ is community-supported.
On macOS, install with Homebrew:
brew install --cask liliu-z/stashbase/stashbase
Or download the latest release:
| Platform | Download |
|---|---|
| macOS Apple Silicon | StashBase-*-mac-arm64.dmg |
| Windows x64 | StashBase-*-win-x64.exe |
| Linux x86_64 | StashBase-*-linux-amd64.deb or .AppImage |
See Installation for platform steps, updates, and troubleshooting.
Choose your material. Open your own folder, or explore the Gallery in the app and choose Make a copy to download and open a ready-made Wiki.
Choose an Agent. OpenQuill is included and selected initially; sign in to StashBase to use its free credits. You can also select Claude Code or Codex and use your own provider account.
Build and use the Wiki. In a Chat scoped to your folder, try:
Build a Wiki from the sources in this folder. Create an overview, organize the main topics, and link back to the source files.
Then ask a question about the material, open its sources beside the Chat, and ask the Agent to improve the pages as you learn more.
A Build Wiki request creates or improves wiki/index.md and, when useful,
pages beside it, preserving Sources outside wiki/. Building or updating
these pages is an explicit Agent request; opening a folder does not
schedule automatic Wiki maintenance.
Search by meaning is off until you add your own OpenAI or OpenRouter key under Settings → Search by Meaning. Keyword search works without it, and turning it on is independent of building Wiki Pages.
See Using StashBase for search, transcription, and everyday file workflows. You can also ask Chat “How do I use StashBase?”
Start with a real folder that already has a Wiki built from it. Gallery entries include starter prompts, and entries with a build request let you copy it for your own material.
For example, How to Start a Startup brings together Stanford CS183B lecture transcripts and a founder playbook. Use it to explore questions about startup ideas, product-market fit, and growth.
Your own starting point might be a research collection, project documents, or personal notes. Build an overview of the topics, decisions, and sources, then use it with your Agent as the work continues.
Sources and Wiki Pages stay in ordinary local folders. Extracted text and search indexes are app-managed data. Removing a folder from the Library clears StashBase's state for it without deleting your files.
Local browsing, editing, preview, and keyword search need no cloud account. OCR and optional audio/video transcription run locally. With your own embedding key added, search by meaning sends relevant text to that provider for indexing and queries for retrieval.
OpenQuill runs locally, with prompts and necessary model context sent through StashBase's hosted model gateway. Claude Code and Codex use their own provider accounts. Local-first means you retain your files and control which folders join the Library; model-backed features can still use cloud services.
StashBase configures its MCP connection automatically for OpenQuill and for Claude Code or Codex used in the built-in Chat. You can review tool calls and file edits in the app.
To use an external MCP client, keep StashBase running and copy the connection configuration from Settings → MCP into that client. It can search the library, read prepared source content, and use bounded file operations within the authorized folders.
See MCP Configuration for client examples, transports, and access settings.
For contributors and developers running StashBase locally from source.
Install Node.js 24+, pnpm, and Python 3.10+. On Ubuntu / Debian, install the native build tools used by the packaged sidecars:
sudo apt install build-essential binutils cmake curl git nasm pkg-config python3 python3-venv xz-utils
git clone https://github.com/liliu-z/stashbase
cd stashbase
pnpm install
pnpm setup:python
# Optional: local PDF and image OCR extraction from this checkout
pnpm setup:python-extract
# Build the renderer and run Electron
pnpm build:web
env -u ELECTRON_RUN_AS_NODE pnpm electron
# Development mode
env -u ELECTRON_RUN_AS_NODE pnpm dev
# Optional: include the local PDF/OCR extractor sidecar
pnpm build:python-extract-sidecar
The launch commands above use POSIX shell syntax to clear an inherited
ELECTRON_RUN_AS_NODE. On Windows, clear that variable in your shell before
running pnpm electron or pnpm dev.
Before opening a PR:
pnpm check
Packaging is release-only and runs from a validated release tag. Maintainers should follow the release pipeline instead of creating ad hoc distributable builds.
StashBase is also an experiment in human-directed, AI-first development. Humans own product direction and trust decisions; AI helps connect design, implementation, review, and evidence. The Project Maintenance Model describes that working loop.
Small focused PRs are preferred. Open an issue before larger changes so scope and direction can be discussed first.
Early alpha. Feedback and contributions are welcome, especially around Agent workflows, search quality, preparation and recovery, and cross-platform reliability.
Report an issue or join the Discord community for support and discussion.
StashBase is an independent open-source project built by Li Liu, bringing vector-retrieval experience to making local knowledge useful to Agents.
Licensed under Apache 2.0.