"Zsh" matching MCP servers:

Enables deep, recursive multi-source scientific literature research across 8+ academic databases, producing cited, evidence-graded reports with red-team review and cost details through an outline-first, user-confirmed workflow.

Turns a plain-Markdown Obsidian vault into a second brain that any MCP-speaking coding agent can search, read, extend, and maintain, using swappable SQLite, Qdrant, or markdown memory backends with automatic re-indexing and wiki-link graph navigation. Exposes read, write, and index tools plus an operator CLI for health, linting, and graph export.

Provides persistent OKF memory for DeepSeek Harness by storing and indexing Markdown memories in SQLite FTS5, enabling agents to search, store, and export memories through MCP tools.

Enables agents to search and read a fully offline BM25-indexed Conjugate Spectral Geometry knowledge base of 251 articles and 869 verified truths, with citation-enforced retrieval. Also supports writing and archiving articles, symbolic formula verification, claim-graph auditing, sector assignment, workspace file access, git and local state operations.

Enables AI agents to store, recall, link, and manage durable local memories using ranked fuzzy search and optional graph context through a compact MCP interface.

An Elasticsearch-based AI memory system optimized for Chinese that enables persistent knowledge storage and complex entity relationship management via the Model Context Protocol. It features advanced semantic search using the IK analyzer and supports multi-zone memory isolation for specialized knowledge graphs.

Enables local document semantic search and retrieval for DeepSeek Harness agents, with source citations and fully local embedding without external APIs.

Provides a cross-session experience knowledge base for AI agents, enabling retrieval of past problem-solution experiences via MCP tools. It helps agents reuse solutions without retraining, with zero-LLM runtime retrieval.

A Docker-based local RAG backend that provides advanced document search capabilities using vector, graph, and full-text retrieval via the Model Context Protocol. It supports over 28 file formats and tracks evolving relationships between concepts using a Neo4j-backed graphiti implementation.

Enables DeepSeek Harness to use OpenViking persistent memory by recalling relevant context into conversations, mirroring sessions, committing at thresholds, replaying offline writes, and exposing OpenViking tools via MCP while guarding viking:// URIs.

Enables MCP-compatible agents to retrieve Chinese expert documents, prompt examples, and task skeletons before writing Chinese prompts.

Enables AI agents to build and query a private, on-device long-term memory through 15 MCP tools for storing decisions, searching past context, tracking entity state, merging duplicates, and resolving conflicts. Automatic hooks capture each prompt and inject relevant memories at session start, so context carries across sessions without leaving the machine.

Enables searching Bilibili videos by question and retrieving specific timestamped segments that answer it, with direct jump-back links. It performs local transcription, caching, and Chinese BM25 ranking to provide precise video evidence without external APIs.

Transforms Claude into a production-grade pair programmer by orchestrating best-in-class APIs (Morph, Chroma, DSPy) for iterative code evolution to 95%+ quality, semantic codebase search, package discovery across 3,000+ libraries, and pattern learning.