"Coze" matching MCP servers:

Enables Claude Code to search, browse, and read its own past conversation history across all projects using BM25 keyword search.

Enables AI assistants to maintain persistent project context across sessions by storing and retrieving structured information in markdown files organized in a memory bank directory.

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

Enables assistants to save commitments with context and next actions, recall them in later sessions, and resume them as next-step cards over MCP.

Self-hosted MCP server for long-term memory in AI coding assistants, capturing decisions, conventions, and discoveries as structured traces with tag and keyword search.

Automatically captures technical and product decisions from Claude Mac app sessions and writes them into project files, enabling seamless context transfer between strategy and coding sessions.

A local, cross-editor MCP server that provides persistent memory for coding agents, capturing and recalling decisions, conventions, and fixes across sessions without API keys.

Provides semantic code search and code insights via a knowledge graph, enabling AI to understand, navigate, and modify complex projects with deep dependency and architecture analysis.

Local-first personal cognitive engine that provides MCP tools for managing relationships, conversations, agenda, and memory, powered by Ollama.

A high-performance code knowledge graph server implementing MCP, indexing codebases into a structured AST knowledge graph with semantic search, call graph traversal, and HTTP route tracing.

A generic X/bookmark intelligence MCP core for ingesting, enriching, and retrieving bookmarks with semantic search, brief generation, and academic paper scanning, exposed as MCP tools.

A headless local knowledge library and RAG substrate that enables LLM clients to search, retrieve chunks, and list documentation packs through read-only MCP tools.

Gives AI coding agents persistent memory by storing observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine.

Enables AI agents with persistent, multi-layer memory, multi-agent collaboration rooms, and video generation, all accessible via MCP tools.

A local capability layer for AI agents providing persistent memory, credential management, connectors, and activity tracking.

MCP server providing a searchable security knowledge base for AI coding assistants, enabling retrieval of secure-coding instructions and feature-specific security guidance.

MCP server for semantic code search and dependency graph analysis. Indexes codebases into a knowledge graph with vector embeddings for AI-powered code understanding.

Search and reference your Claude Code conversation history directly from Claude, with full-text search, conversation viewing, and project browsing.

A persistent, tree-sitter-backed code knowledge cache MCP server that reduces token usage by storing parsed structure and enabling fast symbol lookup, inheritance graph, call graph, and semantic search.

Enables autonomous multi-agent workflows to capture, preserve, and retrieve immutable transcripts and atomic memory cards through a local MCP server, providing tools for forensic search, topic mapping, and structured fact access without losing context fidelity.