Documents and notes decision
Brevilabs
A competent developer can reproduce the core Obsidian copilot workflow (local indexing, RAG, chat UI, simple agents) using existing OSS components, but the full paid product — notably bundled/exclusive hosted models, polished UX, and brand trust — is not practical to match by a single developer.
Visit website↗Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Brevilabs alternatives, with the arithmetic →
What a replacement has to do
- Load vault files, build embeddings/RAG index, provide chat UI with contextual prompts, run simple agent tools (web/youtube fetchers), and glue a model API for responses.
What it still won’t have
- Polished, award-winning UX and cross-user polish
- Bundled "exclusive" hosted chat model and hosted embeddings (no API key needed)
- Built-in proprietary agent tools and tight Obsidian integration maintenance/support
- Marketing, brand trust, and ongoing product polish
What remains hard
- Brand trust
Best Obsidian AI Integration Award Winner 2024. Loved by users worldwide.
First-year cost
No published price
Brevilabs does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build an Obsidian plugin (TypeScript, Obsidian API, Vite) that provides a local-first AI Copilot: include a chat pane, context menu above messages, inline edit/completion, and project-based profiles. Scope in: reading vault markdown, PDFs and images; local embedding index stored in a SQLite or small vector store (Weaviate/pgvector optional); nearest-neighbor retrieval and RAG prompt assembly; model integration using configurable external LLM APIs (OpenAI/Anthropic) and an option for a bundled self-hosted model endpoint; simple agent tools: web search fetcher and YouTube-to-markdown converter; profile management (prompts, model settings); error handling for I/O and API failures, retries, and input validation; unit tests for indexing, retrieval, and chat flow. Out of scope: training proprietary models, multi-user online sync, and paid hosting. Provide CI, documentation for installation, and basic automation tests.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 4 cited sources+3
- Evidence score60
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 4
Every page the run actually retrieved.
- official productBrevilabs — official product
- open sourceobsidian-smart-composer
- open sourceDocsGPT
- open sourcenanoclaw
Integrity checks
What held up, and what did not.
