MaxKB
by MaxKB · Open-source RAG and agent platform you self-host
BenchRank score
Screenshots of MaxKB
Homepage
Overview
MaxKB is an open-source, self-hosted platform for building agents backed by retrieval-augmented generation. It ingests documents by upload or by crawling online documents, splits and vectorises the text, and answers questions from the resulting knowledge bases. A workflow engine, function library and MCP tool-use handle more complex processes, and it works with private or public models.
- Best for
- Teams self-hosting a RAG chatbot over internal documents for support or knowledge bases
- Pricing
- The OSS edition is free at $0; the Pro edition is an annually billed self-hosting plan with no published price — you contact sales.
- Runs on
- Self-hosted
Strengths and trade-offs
Strengths
- Free OSS edition allows 50 knowledge bases and 5 applications
- Runs private or public models: DeepSeek, Llama, OpenAI, Claude, Gemini
- Uploads documents or crawls sites, then splits and vectorises text
- Workflow engine with function library and MCP tool-use
Trade-offs
- OSS edition caps use at 2 users, 5 applications and 50 knowledge bases
- SSO, Open API and Slack/DingTalk/Lark integrations are Pro edition only
- Pro edition price is not published; you must contact sales
- Annual billing only, self-hosted only — no monthly plan and no SaaS option
How MaxKB markets itself
A structured read of the promise, proof and page design on MaxKB’s captured homepage.
Homepage capture
“Open-source platform for building enterprise-grade agents”
- Angle: Open source / ownership
- Hero: Product screenshot
Pricing
Published plans and prices from MaxKB’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
API quality
Public API surface: machine-readable spec, official SDKs, documented auth, errors, rate limits and versioning.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Pricing transparency
Whether real prices are published, self-serve signup exists, and usage costs are knowable without a sales call.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with MaxKB’s score
Where this comes from
The MaxKB pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Alternatives in Agent Platforms
Ranked 1
71.5 — BenchRank score out of 100Agenta
Agenta · Open-source workspace for building, running and tracing LLM agents
Best for: Teams building and scheduling LLM agents who want tracing, versioning and evaluation, self-hosted or hosted.
Ranked 2
69.3 — BenchRank score out of 100n8n
n8n · Visual workflow and AI agent automation with code steps and self-hosting
Best for: Technical teams building AI agents and integrations that need code steps and a self-hosting option.
Ranked 3
67.5 — BenchRank score out of 100Zapier
Zapier · AI orchestration and no-code automation across 9,000+ apps
Best for: Teams connecting AI assistants and no-code workflows to business apps under central IT control.
Is this your product?
Claim MaxKB to manage its profile. Claiming lets you suggest edits to the descriptive fields — it never changes scores or rankings.