"A tool for comparing design documents and source code, and accumulating business knowledge" matching MCP servers:

Enables saving URLs, local files, plain text, and platform content (WeChat, X, YouTube, PDF, images, audio/video, Telegram) as structured Markdown knowledge cards in an Obsidian vault, with optional AI-powered classification and tagging.

Read-only MCP server providing AI access to verifiable web, GitHub, and local sources, plus a managed fantasy entity catalog, with strong security and provenance tracking.

Local knowledge engine for codebases with hybrid search, knowledge graph, and interaction tracking, enabling Claude Code to search and interact with project knowledge locally.

An MCP server that acts as a knowledge engine for software projects, delivering relevant context at the start of a task and accumulating knowledge at its end through tools like start_task, context, finish_task, remember, and search, with a file-based source of truth and optional semantic retrieval via Graphiti/Neo4j.

Provides source-backed design context, route card validation, contract generation, critique and verification reports, evidence packages, Penpot change plans, and anti-repeat checks for design workflows. Does not directly mutate Penpot, but consumes read-only Penpot snapshots.

A local MCP server that gives LLMs long-term memory by indexing code, infrastructure, logs, and docs into a queryable graph. It enables semantic and structural search, evidence-backed reasoning, and tracked plans that persist across sessions and teams.

Enables querying company knowledge base using RAG, providing accurate answers from internal documents via MCP.

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

Serves locally stored knowledge bases (e.g., Trading-Knowledge, Bug-Bounty-Knowledge) to MCP agents, enabling listing, searching, and fetching documents without GitHub authentication.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Provides centralized knowledge management for projects, allowing users to store, search, and maintain project-specific knowledge that persists across sessions.

Enables cross-session memory and recall for AI coding assistants through a git-synced knowledge base, hybrid semantic and TF-IDF search across tool transcripts, and automatic distillation of insights with secrets scrubbing.

MCP server bridging ChatGPT-compatible clients to the Design Flow System, enabling project session management, draft import, round locking, and read-only access to design state and traceability.

A forkable RAG project with an MCP server for VS Code/Copilot, enabling indexing and querying of knowledge from URLs, PDFs, or TeX files.

Long-term memory for AI agents. Compiles conversations into a structured knowledge base with Claim/Evidence model, source provenance, append-only timeline, and contradiction detection. Multi-path retrieval (Exact + BM25 + Graph + weighted RRF + reranker) — 96.6% R@5 on LongMemEval-S, zero vector dependencies.

A knowledge base MCP server that aggregates team knowledge from multiple sources into Postgres. It provides hybrid search (full-text + vector + RRF) via MCP tools, and enables direct recording of decisions, learnings, and pitfalls.

A local knowledge graph MCP server that provides AI agents with permanent, structured memory about codebases, enabling semantic search, blast radius analysis, and convention enforcement.

Transforms YouTube into a queryable knowledge source with search, video details, transcript analysis, and AI-powered tools for summaries, learning paths, and knowledge graphs. Features quota-aware API access with caching and optional OpenAI/Anthropic integration for advanced content analysis.

Enables building and managing knowledge workspaces with tools for ingesting content from text, clipboard, or URLs and searching organized knowledge bases. Supports multiple configurable workspaces with separate inbox and knowledge directories for structured information management.

Persistent project memory + architectural decisions + pre-execution safety hooks for Claude Code. Local-only storage, multi-repo workspace, automatic knowledge extraction via background auditor.