"Zsh" matching MCP servers:

MCP server providing managed persistent memory for AI agents. Read and write structured state across sessions, tools, and restarts at 1000+ requests per second, with no infrastructure to self-host or operate.

Bridges TiMEM's cloud MCP server with DeepSeek Harness to provide long-term memory tools and automatic memory skills for AI models, enabling persistent context and learned behaviors across conversations.

Enables DeepSeek Harness agents to access DeepBrain's judgment store, including quoting verified lines, retrieving historical positions, and reusing analysis methods.

Enables structural knowledge-graph code search, AST snippet retrieval, architecture analysis, call-path tracing, and textual code search across indexed repositories, plus an auto-started graph visualization UI.

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.

MCP server for verifying narrative consistency and querying story-state facts in DeepSeek Harness, exposing read-only ledger tools for canonical evidence and continuity checks.

Exposes DeepSeek Harness capabilities—durable memory, task ledger, project-agent dispatch, and the wider MCP estate—as declared MCP tools for any MCP client.

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.

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.

A fully local, offline Chinese-optimized MCP memory server using SQLite and local embeddings, enabling MCP clients to store, semantically search, recall, and count memories without any API calls.

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.

Memory bank with Server as SSH support for central knowledge base

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.

Provides persistent, searchable memory for Claude Code using local SQLite, semantic embeddings, and full-text search, enabling Claude to recall and retrieve context across sessions and projects without external services.

Enables keyword search across local Claude Code, Codex, and ZCode session histories by title and content, returning matching snippets, timestamps, and file paths. It also lets an agent read a session's recent messages, launch the corresponding desktop app, or reveal the session log file in the file manager.

Enables searching and browsing past Claude Code sessions via hybrid FTS5 and vector search, with tools for session search, drill-down, coverage, and health reporting.

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.

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.

Exposes 13 tools that let an agent search a personal IMA knowledge base and notes, retrieve document content, and download original literature files. It also supports creating notes, appending content, and importing URLs, with self-check credential validation.