Score8.0
Popularity489.0
Risklow
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity8.8
Open-source/build8.4
Evidence8.0
Workflow potential9.1
Setup ease8.8
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for **AI agent users (Claude Code / Codex / Cursor / OpenCode) who want a portable markdown knowledge base their agents can read AND edit** — OpenKnowledge is the GPL-3.0-or-later native macOS markdown editor + LLM Wiki with first-class MCP, skills, and agentic search, three layers (Editor + Knowledge Engine + Content) wired to Claude Code, Codex, Cursor, and OpenCode. Useful for **teams im
Who should use it
**AI agent users (Claude Code / Codex / Cursor / OpenCode) who want a portable markdown knowledge base their agents can read AND edit** — OpenKnowledge is the GPL-3.0-or-later native macOS markdown editor + LLM Wiki with first-class MCP, skills, and agentic search, three layers (Editor + Knowledge Engine + Content) wired to Claude Code, Codex, Cursor, and OpenCode**Teams implementing Karpathy's LLM Wiki pattern** — the workflow page in the docs describes the canonical 'agent maintains a structured knowledge base' pattern**Teams implementing an entity-vault / second-brain pattern** — the Entity vault (GBrain-compatible) workflow gives a structured schema for storing entities and relations**Teams that need an open-source Obsidian/Notion alternative that AI agents can drive** — Full WYSIWYG editing, plain markdown files (`.md`) under the project directory, git-tracked, portable**Teams that want no-code Team Sharing and Auto-sync** — Auto-sync via git/GitHub means the knowledge base syncs to a GitHub repo without manual steps**Teams that need Timeline and Recovery** — every edit is versioned; recovery is built in**Teams that need agent activity visibility** — the agent's icon appears in the top right; click to see agent activity across files in the knowledge base**Teams that need plain-text portability** — the files are plain markdown, so the knowledge base survives any single vendor going away**macOS users (M1 or later)** — the native desktop app is a DMG that opens with no Gatekeeper prompt**Linux / Windows / Intel Mac users** — the same editor runs as a local web app via `npm install -g @inkeep/open-knowledge && cd your-project && ok init && ok start --open`**Teams that want spec-driven development** — out-of-the-box MCP, skills, and agentic search for spec-driven workflows**Teams that need share links** — read-only or edit-mode share links for sharing knowledge with stakeholdersEvaluation: macOS — download the desktop app DMG, drag to Applications, launch; Linux/Windows/Intel Mac — `npm install -g @inkeep/open-knowledge && cd your-project && ok init && ok start --open` (Node.js 24+ required, git for timeline and recovery). For testing with an agent: open the project, initialize a knowledge base, open it in your AI agent, type what you want to build (e.g. 'Create a knowledge base about Large Language Models. Include an overview page and separate pages for three key concepts.'), watch the agent's icon in the top right and click to see agent activity across files. For the three layers: (1) **Editor** — WYSIWYG or source mode, backlinks; (2) **Knowledge Engine** — keeps content consistent, agentic search, timeline/recovery, git/GitHub sync; (3) **Content** — plain `.md` files, portable, git-tracked. For the integrations: Claude, Cursor, Codex, OpenCode. For the workflows: Karpathy's LLM wiki workflow, Entity vault (GBrain-compatible) workflow, Supporting the Open Knowledge Format. For the open-source status: GPL-3.0-or-later (copyleft applies — derivative works must also be GPL-3.0-or-later; commercial closed-source forks are not allowed). For the maturity caveat: at 489 stars and 1 subscriber, OpenKnowledge is a relatively new project — fine for early adoption, monitor releases for stability before depending on it as a primary knowledge base. For the Inkeep note: Inkeep is a YC-backed company; PRs to this public repo are mirrored into the internal monorepo for review and merge
Who should skip it
Skip inkeep/open-knowledge if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
inkeep/open-knowledge is tracked by RepoRadar as a gpl-3.0-or-later native macos ma in the inkeep/open-knowledge (GPL-3.0-or-later, Inkeep) section. It was first seen on 2026-06-26 and last updated on 2026-06-26. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for inkeep/open-knowledge are workflow potential (9.1) and maturity (8.8), while evidence quality (8.0) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned inkeep/open-knowledge a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 489.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Risk explanation
license caveat: GPL-3.0-or-later is copyleft — derivative works must also be GPL-3.0-or-later; commercial closed-source forks are not allowed; users building proprietary products on top of OpenKnowledge must contribute back under the same license. Platform caveat: macOS desktop app requires M1 or later; Intel Mac users must run the local web app via the Node.js CLI. Maturity caveat: at 489 stars and 1 subscriber.
Evidence links
Closest alternatives / related signals
open-knowledgeinkeepllm-wikimarkdown-knowledge-basenative-macos-appweb-app-clim1-or-laterintel-mac-linux-windows
