Knemora

Knemora is an open-source, local-first knowledge and agent platform with a native Second Brain graph.

Knemora is an open-source, local-first knowledge and agent platform with a native Second Brain graph, a portable Markdown Wiki, and local AI inference. It works without a mandatory cloud service, external LLM API, vector database, or desktop knowledge application. The application includes local document ingestion for PDF, TXT, Markdown, DOCX, CSV, and XLSX files. It uses local Qwen inference through llama.cpp behind a provider-neutral boundary. A Vue 3 interface runs against an authenticated FastAPI boundary on the local machine with Google ADK for agent orchestration. It is designed for users wanting local-first AI knowledge management with provenance-bearing Wiki pages and graph views.

Knemora at a glance

Best for: Software engineer, Researcher
Runs on: macOS, CLI, self-hosted, open source
Pricing: Free
Released: November 2026
Category: AI agent tool
Website: github.com/federicolaterra/knemora

Key features

Local document ingestion for PDF, TXT, Markdown, DOCX, CSV, and XLSX
Portable LLM Wiki using Markdown, YAML frontmatter, and wikilinks
Native Sigma.js and Graphology Second Brain with global and local views
Local Qwen inference through llama.cpp behind a provider-neutral boundary
Deterministic Polars-based dataset analysis and chart-ready results
Authenticated sessions, backend RBAC, audit events, and observability
Backup, restore, migration, and Wiki maintenance workflows

Use it for

Ingest local documents and datasets into a portable Markdown Wiki
Explore knowledge using global and local Second Brain graph views
Analyze datasets with deterministic Polars-based tools
Run private local AI inference without cloud dependencies

Alternatives to Knemora

WeKnora — Combines RAG, multi-step agents, and automatic Wiki generation in one platform.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
Mnemosyne — It provides sub-millisecond memory access with no external service costs.
Beeuni — Agents retain context and improve skills over time through a controlled review process.
LLM Wiki Research — Compiles parallel agent research into source-backed markdown knowledge bases.
Jonex — Provides traceable, agent-ready knowledge from diverse enterprise data sources.
Mnemify — Runs locally on your machine and builds an interactive 3D knowledge map from multiple apps.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
OpenSquilla — Maximizes AI intelligence density while minimizing token costs through smart routing.
MemPalace — Achieves high recall with local-first storage and zero API calls.
FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.
Wigolo — Enables local web access for AI agents with no API keys, cloud dependency, or fees.

All Knemora alternatives