zrg-team/memorall
Local-first AI extension that turns what you read into a searchable knowledge graph with hybrid search, temporal context, and proactive recall—fully private.
Combines in-browser runtimes (Wllama, WebLLM, Transformers) with optional external providers (OpenAI, Ollama, LM Studio), using PGlite for local knowledge storage and background job services to offload heavy operations from the UI thread. Features a multi-surface architecture: the core app includes document library, topic-scoped knowledge graphs, customizable agent flows with sandbox/browser tooling, and an embedded in-page assistant that captures selected text, page content, and screenshots routed into topics. Built as a browser extension using Extension.js and React, supporting MCP adapters (in-progress) and workspace-aware agents that access stored documents and knowledge graphs for iterative, long-running workflows.
Stars
7
Forks
2
Language
JavaScript
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/zrg-team/memorall"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
brianpetro/obsidian-smart-connections
Chat with your notes & see links to related content with AI embeddings. Use local models or 100+...
gmickel/gno
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers,...
Terronex-dev/aifbin-pro
AIF-BIN Pro — Professional AI Memory Management with Semantic Search
mantisfury/ArkhamMirror
Local-first AI-powered document intelligence platform for investigative journalism
Terronex-dev/aifbin-lite
AIF-BIN Lite — Free & Open Source CLI for AI Memory Files