gknowledge
The gknowledge MCP server lets an agent search, read, extend, and maintain a gknowledge wiki.
Search wiki pages by keyword and return matching pages with slug, type, and summary.
Read a page as Markdown, including its sources and backlinks.
List wiki pages, optionally filtered by type: source, entity, concept, topic, or answer.
Ask questions and get cited answers from the configured provider; optionally save the answer back into the wiki.
Import local Markdown, text, PDF, or HTML files and ingest them into the wiki.
Detect stale sources whose original files changed after ingestion and identify affected pages.
View recent wiki log activity such as ingests and saved answers.
Install
One line, on Ubuntu 24.04+ and Debian 13+. It adds the signed gknowledge APT repository, so updates arrive with apt upgrade (other distributions get a per-user install):
curl -fsSL https://github.com/openapi/gknowledge/releases/latest/download/install.sh | bashOr add the APT repository yourself. apt also pulls GTK 4, Libadwaita and PyGObject:
sudo curl -fsSLo /usr/share/keyrings/gknowledge.gpg https://openapi.github.io/gknowledge/gknowledge.gpg
sudo curl -fsSLo /etc/apt/sources.list.d/gknowledge.sources https://openapi.github.io/gknowledge/gknowledge.sources
sudo apt update && sudo apt install gknowledgeOn any distribution, with Flatpak (the GNOME runtime comes from Flathub):
flatpak install --user https://openapi.github.io/gknowledge/io.github.openapi.Gknowledge.flatpakrefBoth repositories are described at openapi.github.io/gknowledge.
Then open gknowledge from the app grid. To remove it: sudo apt remove gknowledge (or flatpak uninstall io.github.openapi.Gknowledge).
Fedora, Arch and others: install PyGObject, GTK 4 and Libadwaita with your package manager, then run the one-line installer above. It installs into
~/.localwithout root.From source:
git clone https://github.com/openapi/gknowledge && cd gknowledge && make install.Single files: every version's
.deband Flatpak bundle is on the Releases page, e.g.sudo apt install ./gknowledge_all.debafter downloading gknowledge_all.deb.
Related MCP server: llm-wiki-mcp
Why gknowledge
If you have used LLM Wiki, Tolaria, OpenKnowledge, Reor or Khoj, you already know the loop: ingest sources, let the model build and maintain a wiki, then ask questions against it. gknowledge does the same thing as a real GNOME application.
Native, not a web view. GTK 4 and Libadwaita, built to follow the GNOME HIG. No Electron, no Tauri, no browser engine.
Works with no account. A built-in heuristic engine ingests and answers offline. Add a model when you want better synthesis.
Your data stays yours. Markdown with YAML frontmatter plus a readable SQLite index. Open the folder in Obsidian or any editor.
Cited, reviewable, incremental. Every generated page records its sources, answers cite pages, and a review queue keeps you in control.
The workflow you already know
You know this from… | What it is | In gknowledge |
Karpathy's LLM Wiki, LLM Wiki | Ingest: read a new source, update the pages it touches | Done: two-step extraction with provenance |
Reor, Khoj | Ask: questions answered from your notes, with citations | Done: lexical search plus graph expansion, citations, saved answers |
LLM Wiki, OpenKnowledge |
| Done |
LLM Wiki, Tolaria | Review AI changes before they stick | Review queue done, Git diff planned |
Karpathy's LLM Wiki, OpenKnowledge | Lint: orphans, contradictions, stale pages | Planned |
LLM Wiki | Knowledge graph, clusters, gaps | Planned |
Tolaria, OpenKnowledge, LLM Wiki | MCP server so agents can read and write the wiki | Done: |
LLM Wiki | Web clipper, folder watch, deep research | Planned |
See ROADMAP.md for dates and TODO.md for the backlog.
Karpathy's LLM Wiki, native on GNOME
In April 2026 Andrej Karpathy described the LLM Wiki pattern: instead of re-reading raw documents on every question, an LLM builds and maintains a persistent wiki that compounds over time. gknowledge implements it as a desktop app.
What we kept
Three layers: immutable
sources/, the generatedknowledge/wiki, and settings that tell the engine how to work.The operations: ingest (read a source, update the pages it touches) and query (answer from the wiki, with citations). Lint is next.
index.mdas the catalogue andlog.mdas the append-only history.Plain Markdown with
[[wikilinks]]and YAML frontmatter, so the folder opens in Obsidian.The human curates, the model maintains.
What we changed and added
A native app instead of an idea file. GTK 4 and Libadwaita, with sources, wiki, assistant and review in one window.
Works with no model at all. An offline engine ingests and answers; a model makes it better.
Bring your own brain. Your ChatGPT plan through Sign in with ChatGPT, Ollama, or any OpenAI-compatible endpoint.
Two-step ingest with provenance. Analysis first, then pages; every page records its sources.
No empty pages, no duplicates. Pages are created only with real content, names are merged across sources ("Kasparov" and "Garry Kasparov"), minor names stay as mentions until a second source cites them.
A review queue for what the model is unsure about.
An MCP server, so Claude Code, Codex or Cursor can search, read and grow the same wiki.
Use your wiki from Claude Code, Codex or Cursor
gknowledge ships an MCP server. Point any agent at a project folder:
claude mcp add gknowledge -- gknowledge-mcp ~/Knowledge/my-project # Claude Code
codex mcp add gknowledge -- gknowledge-mcp ~/Knowledge/my-project # Codex CLIFor Cursor or other clients, add this to the MCP configuration:
{ "mcpServers": { "gknowledge": { "command": "gknowledge-mcp", "args": ["/home/you/Knowledge/my-project"] } } }Tool | What the agent can do |
| find pages by keyword |
| read a page with its sources and backlinks |
| list pages by type |
| get a cited answer, optionally saved back into the wiki |
| import and ingest a file |
| see what changed recently |
Try it from source
sudo apt install python3-gi gir1.2-gtk-4.0 gir1.2-adw-1 # Ubuntu / Debian
git clone https://github.com/openapi/gknowledge && cd gknowledge
make start # opens a demo project with six AI papers already ingestedmake start also restarts the app whenever you edit the source, which makes it the fastest way to hack on gknowledge. Install it for daily use with make install.
Bring your own brain
Provider | Needs | Notes |
Offline (default) | nothing | Heuristic extraction and extractive answers. Fully private. |
ChatGPT plan | A Plus or Pro account | Preferences, Provider, Sign in with ChatGPT. Usage is charged to your own plan, no API key. |
Ollama / LM Studio / vLLM | A local server | Any OpenAI-compatible endpoint on your machine. |
OpenAI-compatible cloud | An API key | OpenAI, OpenRouter, Together, and similar. |
Nothing is sent anywhere unless you pick a provider that is not offline.
How it compares
gknowledge | LLM Wiki | Tolaria | OpenKnowledge | Reor (archived) | Khoj | |
Native GNOME / GTK 4 | yes | Tauri | Tauri | Electron | Electron | web + Electron |
Works offline, no key | yes | needs a model | AI optional | agent-driven | local model | self-host |
Plain Markdown vault | yes | yes | yes | yes | yes | reads yours |
Linux packaging |
|
| AppImage, |
| AppImage | pip, Docker |
License | MIT | GPL-3.0 | AGPL-3.0 | GPL-3.0 | AGPL-3.0 | AGPL-3.0 |
Details and history of each project are in DISTRIBUTING.md.
gknowledge is an alternative to…
gknowledge sits at the intersection of LLM-powered knowledge bases, local-first note tools, and document RAG systems. If you have used any of the tools below, you already understand the shape of the problem — gknowledge addresses it as a native GNOME/GTK application that is local-first, provider-agnostic, and usable fully offline (no API key required, thanks to a built-in heuristic extraction engine).
LLM wiki / auto-knowledge-base builders (the closest peers, several studied in NOTES.md):
LLM Wiki (
nashsu/llm_wiki) — Tauri desktop app implementing Karpathy's incremental "LLM builds and maintains a wiki" patternTolaria — files-first, git-first Markdown knowledge base with AI-assisted editing
WeKnora (Tencent) — enterprise RAG + agents + auto-wiki framework
OpenKnowledge (Inkeep) — WYSIWYG Markdown editor with agent/MCP integrations for LLM wikis
Reor — local-first AI note-taking that auto-links related notes
Khoj — self-hostable AI "second brain" over your documents
Not a peer: Google NotebookLM offers a similar cited-notebook experience but is closed-source and cloud-only.
Document RAG / "chat with your knowledge" engines:
Local-first / networked-thought note tools (which gknowledge complements with automated ingestion and provenance):
Obsidian (+ Smart Connections / Copilot plugins), Logseq, SiYuan, Trilium Notes, Zettlr, Foam, Dendron, Joplin, Notion, Tana, Capacities, Heptabase, RemNote
Document / reference managers with growing AI features:
How gknowledge differs
Native to GNOME, not Electron/Tauri or web-first — GTK 4 + Libadwaita, HIG-aligned, Flatpak-friendly.
Offline-first and provider-agnostic — a local heuristic engine ships in the box; OpenAI-compatible endpoints (OpenAI, Ollama, LM Studio, vLLM, OpenRouter, …) are optional, swappable, and configured per project.
Inspectable, user-owned format — knowledge is plain Markdown with YAML frontmatter (Obsidian-compatible) plus a readable SQLite index; nothing is locked behind a sync service.
Incremental, not stateless RAG — sources are ingested once into a persistent, cross-linked knowledge space with provenance, rather than re-retrieved from scratch on every question.
Human-in-the-loop — generated content is clearly marked and a review queue keeps you in editorial control.
Project docs
ROADMAP.md— milestones and the features we are borrowing from peersTODO.md— actionable backlogDISTRIBUTING.md— positioning and distribution study of comparable projects (Italian)CONTRIBUTING.md— how to contributedocs/DESIGN.md— the original product and design documentCHANGELOG.md— what changed in each release
License
MIT. Contributions are welcome, see CONTRIBUTING.md.
Star history
If gknowledge is useful to you, a star helps other GNOME users find it.
Available Tools
7 toolsadd_sourceB
Import a local file (Markdown, text, PDF, HTML) into the project and ingest it into the wiki.
Inputs: path (required), ingest.
askB
Answer a question from the wiki with numbered citations, using the provider configured in the project.
Inputs: question (required), save.
list_pagesB
List wiki pages, optionally filtered by type (source, entity, concept, topic, answer).
Inputs: type.
read_pageA
Read one wiki page as Markdown, including its sources and the pages that link to it.
Inputs: slug (required).
recent_activityC
Recent operations from the wiki log (ingests, saved answers).
Inputs: limit.
search_wikiA
Search the gknowledge wiki. Returns matching pages with slug, type and a one-line summary. Use read_page for details.
Inputs: query (required), limit.
stale_sourcesA
Lint the wiki for drift: sources whose original file changed after ingestion, with the pages that still reflect the old version. Re-import or refresh them in the app.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a fairly distinct capability: browsing (list_pages), querying (search_wiki), reading (read_page), question answering (ask), ingestion (add_source), activity log, and drift detection. The only mild overlap is list_pages vs search_wiki, but the descriptions clarify that one enumerates by type while the other matches a query.
Most tools follow verb_noun (list_pages, search_wiki, read_page, add_source), but recent_activity and stale_sources are noun phrases and ask is a bare verb. The convention is readable but clearly mixed.
Seven tools is well-scoped for a wiki/knowledge-base server: each covers a distinct part of the browse-search-read-ingest-lint lifecycle with no filler.
The surface covers discovery, reading, Q&A, ingestion, and drift linting, which is solid lifecycle coverage. Minor gaps: stale_sources only detects drift (refreshing is pushed to the app), and there is no update/delete or page-authoring operation for existing content.
Maintenance
Related MCP Connectors
Self-hostable team wiki; agents read & write it via MCP; Atlas turns your repo into a cited wiki.
Ask your own documents and get answers that cite the source passage. Workspace knowledge bases over MCP for Cursor, Claude and any MCP client.
Your personal library, readable by AI agents: durable snapshots, hybrid search, 46 MCP tools.
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables creation of persistent, compounding knowledge bases using Karpathy's LLM Wiki pattern with LLM-maintained markdown wikis. Supports automated ingestion, cross-referencing, synthesis, and linting of sources as an alternative to traditional RAG systems.63MIT
- AlicenseNot gradedqualityDmaintenancePersistent markdown wiki for your AI agent, built on Karpathy's LLM wiki gist.114 PyPI2MIT
- AlicenseAqualityCmaintenanceEnables MCP-capable agents to search, retrieve, cite, and graph-explore curated SEO, SaaS, and LLM-wiki knowledge locally without API keys.553 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables MCP-capable coding agents to query a self-hosted, LLM-compiled Markdown knowledge base through a single ask tool that answers from whole wiki articles and returns citations back to the source pages. Supports both local stdio and remote streamable-HTTP transports, with no embeddings or vector store involved.-