Tag
This paper presents GPTKB 2.0, a large-scale disambiguated knowledge base derived from LLMs, containing 38.4M triples over 1.6M canonical entities. It offers a web interface for browsing, SPARQL/ natural language querying, and auditing fact provenance and disambiguation decisions.
Wispr Flow introduces Wispr Notetaker, a meeting note tool that integrates with AI assistants like Claude, ChatGPT, and Cursor via MCP, turning transcripts into queryable context.
BackEngine MCP is a product that makes private company knowledge usable for AI, presumably via the Model Context Protocol.
A developer shares lessons from building a production n8n AI support workflow, emphasizing classification over generation, rule-based filters to cut costs, and grounding responses in a knowledge base to avoid hallucinated answers.
Presents TELLER, a dual-path iterative preference optimization approach for table entity linking, with direct-answer and reasoning paths that improve accuracy on TableInstruct and MammoTab V2 benchmarks.
WikiLoop is a feedback-coupled framework that jointly learns to build and navigate an agent-native Wiki, improving answer correctness on multiple benchmarks through a shared policy with sufficiency-before-efficiency objectives.
EdgeEver is an open-source, self-hosted AI knowledge base that runs on Cloudflare, integrates with AI agents via MCP, and supports web clipping and data migration from Evernote.
Simba is an open-source, self-hosted AI customer service assistant that offers customizable RAG pipelines and built-in evaluation metrics for retrieval and answer quality, allowing teams to improve their AI support systems.
A DSL based on Google Zanzibar's datalog language for Lean4 to represent and evaluate knowledge bases, manageable under git and without heavy external dependencies.
AutoDev Studio is an open-source multi-agent AI coding harness that reduces costs by building a persistent repository knowledge base, outperforming cold-start Claude Code runs on large repos in most tasks.
A developer shares how grounding an agent to a knowledge base with retrieval discipline, rather than a better model, solved hallucinations in automated slide generation. The approach splits retrieval from writing and enforces source checking before rendering.
This article discusses key implementation points for enterprise RAG systems, including simulating enterprise documents, embedding selection, citation tracing, version control, and handling unanswered queries, emphasizing that honesty is more important than fluent yet incorrect responses.
Lattics is a brain-like knowledge base that integrates AI writing and deep research capabilities.
A comprehensive, open-source penetration-testing knowledge base aggregating hundreds of tools, checklists, and guides across 23 security domains, hosted on GitHub.
A tool compresses 60 million text chunks from 201GB to 6GB for RAG without accuracy loss, enabling powerful local retrieval-augmented generation on a laptop.
Tencent's ima knowledge base can batch-read public account articles from WeChat favorites and supports deep integration with Agent products like WorkBuddy, Claude Code, and Codex, making AI processing convenient.
OpenKnowledge is an open-source knowledge base tool that combines the note-taking experience of Obsidian with the philosophy of LLM Wiki. It comes with built-in MCP, Skills, Chat, and TUI features, supports Git sync, and can complement Obsidian for efficiently organizing personal knowledge.
Built a WhatsApp automated customer service system for foreign trade using Hermes, featuring automatic customer filtering, knowledge base queries, personalized scripts, self-evolution, etc. Planned to launch mid-July.
This thread describes a method to reduce cognitive load in Obsidian by automating language learning workflow using Lineage to map grammatical relationships as a graph, cutting study time from 45 to 10 minutes per session.
A new open-source project, ai-content-kb, has been released on GitHub. It is a review-first AI-assisted knowledge base reference architecture that supports Markdown, Obsidian, and Codex, preventing AI hallucinations from polluting notes.