mrkeyoor.com_
Wed 12 Aug 14:37 UTC
AI Toolsevaluationupdated 12 Aug 2026

OpenKB

OpenKB turns PDFs, office files, web pages, and text into a local folder of linked Markdown summaries, concepts, and entity pages that an LLM can query. Instead of storing only chunks in a vector database, it spends model calls up front to compile a browsable wiki that grows as more sources are added.

Verdict

OpenKB has a genuinely useful idea: compile knowledge once into files that humans and agents can both inspect, edit, and reuse. It is a strong experiment for a focused research collection, especially if Obsidian or agent skills are part of the workflow. It is not yet the right engine for massive archives, unattended factual publishing, or local-model-only deployments where predictable tool calling is mandatory.

Setup4/5Easy cloud-model trial, with provider and ingestion caveats
Docs5/5Clear architecture, commands, examples, configuration, and API guides
Community4/5Active issue discussion and quick fixes for a young project
Maturity2/5Young 0.x release with unresolved scale and local-model gaps

Who it’s for

Researchers and analysts who want a durable, inspectable wiki rather than a hidden vector index.
Obsidian users who want generated summaries, concepts, entity pages, and wikilinks as normal Markdown files.
Claude Code, Codex, and Gemini CLI users who want to package a document collection as a reusable agent skill.
Small teams willing to pay the up-front model cost of compiling sources for repeated querying and synthesis.

Who it’s NOT for

Teams backfilling hundreds or thousands of related documents: issue #203 reports that repeatedly rewriting growing concept and entity pages made a 1,100-document corpus impractical and approximated quadratic work.
Ollama users who need dependable local query and chat today: issue #205 reproduces incomplete tool loops, raw JSON, empty output, and timeouts across several local models.
Image-heavy long-PDF workflows that expect figures in the browsable wiki: issue #166 says extracted images remain in source data but do not appear in summary, concept, entity, or index pages.
High-stakes knowledge bases without human fact review: issue #214 documents invented biographical claims and misspellings that openkb lint caught only when a person remembered to run it.
Multi-user services requiring accounts and role-based permissions: the bundled web service starts with authentication off and documents only an optional bearer token.

Setup reality

A cloud-model trial is straightforward: install with pip, initialize a directory, provide one model credential, and add a document. The real effort starts during compilation. Long PDFs invoke PageIndex, each source can rewrite 10 to 15 wiki pages, and model quality, latency, token cost, parsing, and tool-call compatibility all affect the result. Local models are possible through LiteLLM, but current Ollama and LM Studio reports show that configuration support does not guarantee a working ingest and query loop. The web interface needs an extra package and an API token before any network exposure; issue #130 also reports that uv tool install openkb from PyPI installed no executable, with Git installation as the workaround.

A knowledge base you can actually open

OpenKB takes a different position from most retrieval systems. Traditional RAG usually converts documents into chunks and embeddings, stores them in a vector database, and retrieves a few chunks whenever somebody asks a question. OpenKB instead asks a model to compile each source into a persistent wiki. It writes summaries, concepts, entities, cross-links, an index, and a log as plain Markdown and supporting data. Later questions use that accumulated structure rather than rediscovering every relationship from raw chunks.

The output is the attraction. Open the wiki directory in Obsidian and the knowledge base is legible without OpenKB running. People, organizations, places, and products receive dedicated pages. Concepts are synthesized across documents instead of remaining isolated source summaries. Because the files follow a documented structure and use ordinary wikilinks, a researcher can inspect what the model wrote, correct it, put it in source control, or use another text tool on top.

OpenKB also turns the wiki into several outputs. The CLI supports cited one-off questions, persisted multi-turn chats, an interactive graph, and single-file HTML slide decks. Its Skill Factory distills the knowledge into a portable agent skill with validation, trigger evaluation, version history, and rollback. A bundled skill lets Claude Code, Codex, and Gemini CLI read the wiki without an MCP server or a running OpenKB process. That is a clever bridge between personal knowledge management and agent tooling.

Vectorless does not mean computation-free

Short documents go through Microsoft’s MarkItDown and are read in full by the language model. PDFs with at least 20 pages take a different path: PageIndex builds a hierarchical tree and summaries so the model can navigate the document without embedding every chunk. PageIndex runs locally by default. Its optional cloud service adds OCR for scans, faster structure generation, and support for large or complex PDFs.

This avoids operating a vector database and makes the retrieval structure easier to reason about. It does not remove model work. When a source is added, OpenKB generates its summary, reads existing concept and entity pages, rewrites relevant pages with cross-document synthesis, then updates indexes and logs. The README says one source may touch 10 to 15 wiki pages. That up-front compilation is the product, but it also creates latency and cost before the first useful query.

Issue #203 shows the limit of the incremental design. In a backfill of about 1,100 related documents, frequently mentioned entities and broad concepts grew after every ingest, and the system regenerated those pages repeatedly. The reporter measured individual rewrites taking several minutes and consuming thousands of output tokens, with total work approximating quadratic growth. The repository’s roadmap lists large document collections, hierarchical topics, nested folders, and database storage as aspirations. Those items should not be treated as current scale guarantees.

Setup favors a capable hosted model

The happy path is appealing: pip install openkb, initialize a directory, select a LiteLLM provider, put a key in .env, and add a file, folder, or URL. Supported inputs include PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, and text. The bundled web extra serves a Workbench and REST API on localhost for browsing, uploads, compilation, queries, and chat. Authentication is disabled by default, so an API token is essential before binding or proxying it beyond a trusted machine.

Provider breadth needs qualification. LiteLLM gives OpenKB a common route to OpenAI, Claude, Gemini, subscription OAuth providers, and compatible local servers. The downstream agent still depends on the chosen model producing reliable structured tool calls. Issue #205 reports that ingest worked through Ollama while query and chat failed to complete their tool loop across several tested models. Results included raw call JSON, empty objects, incomplete answers, and timeouts. Another report describes hours of failed PageIndex retries with local models through LM Studio on a well-equipped Mac. Local operation is possible in configuration, but it is not the low-friction path today.

Packaging has one narrower blemish. The normal pip command is documented, but issue #130 says uv tool install openkb from PyPI installed a metapackage without a binary or dependencies on macOS. Installing directly from the Git repository worked for that reporter. This is a workaround, not a reason to avoid the project, but it weakens the otherwise clean install story.

Compilation needs editorial oversight

A generated wiki can make model mistakes durable. Issue #214 reports misspelled names, an unsupported characterization, and fabricated biographical details written during compilation. The same model found some errors when the user later ran openkb lint, leading to a request for automatic self-review. Until such a gate exists, lint and source comparison belong in the normal workflow. Citations help a reviewer find evidence; they do not make synthesis automatically true.

Multimodal claims also have a visible gap. Issue #166 says the long-PDF path extracted images and recorded correct paths in JSON, yet the renderer omitted them from every page a human browses. Image-heavy manuals and scientific papers therefore need a real output inspection, not an assumption that extraction means presentation.

Project health is promising but young. OpenKB was created in April 2026, released v0.4.5 on July 20, and was pushed on July 22. That release quickly pinned an OpenAI dependency after a breaking change. On August 12, GitHub showed 37 open issues and pull requests combined, and the installation issue received a fresh maintainer reply. The recent issue activity offsets the three-week gap since the last push; it does not turn a four-month-old 0.x system into mature infrastructure.

OpenKB is best for a bounded collection where people will read and refine the wiki repeatedly. Its plain-file output is more durable and transparent than an opaque index. Start small, measure compilation cost, review generated facts, and verify the exact document types and model you intend to use before committing a large archive.

Alternatives

ProjectWhat it isPick it when
RAGFlowA full retrieval application focused on document parsing, chunking, search, and grounded chat.pick this instead when you want a production-style RAG service and web application rather than a compiled Markdown wiki.
KhojA personal AI assistant that searches personal files, notes, and connected information sources.pick this instead when an end-user assistant and personal knowledge experience matter more than generated concept pages.
HaystackA Python framework for building custom retrieval, search, and agent pipelines.pick this instead when developers need control over indexing and retrieval components inside their own application.

What people are saying

  1. [github-trending] VectifyAI/OpenKB

Sources

  1. OpenKB repository and README
  2. OpenKB v0.4.5 release notes
  3. Issue #203: bulk-ingestion scaling report
  4. Issue #205: Ollama query and chat tool-loop failures
  5. Issue #214: compilation hallucination examples
  6. Issue #166: long-document images missing from rendered wiki
  7. Issue #130: uv tool installation failure
  8. Issue #140: LM Studio long-document ingestion failure