SQLite-backed persistent semantic memory MCP server with local Ollama embeddings and keyword fallback.
Key Features: SQLite-backed local memory storage Semantic search using Ollama nomic-embed-text embeddings Keyword search fallback if embeddings are unavailable Provides repository-aware documentation context, convention checks, API context, and proposed documentation updates through MCP.
Key Features: Repository-aware AI context Convention discovery with citations Documentation impact analysis Offline MCP memory and task management with semantic recall, knowledge graphs, reminders, and local backups.
Key Features: Local semantic and graph-based memory recall Hebbian strengthening and activation decay Persistent reminders and GTD-style todos Connects Scrivener 3 projects to AI clients for editing, analysis, search, and writing support.
Key Features: Scrivener 3 document access and editing Deterministic writing analysis Keyword and offline semantic search Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
CLI and hosted MCP endpoint for saving, searching, recalling, and managing user-owned AI memory.
Key Features: Hosted Streamable HTTP MCP endpoint Authentication and credential management SQLite-based MCP memory with decay, relevance scoring, deduplication, categorization, and automatic cleanup.
Key Features: Exponential memory decay by category Automatic content categorization Bigram-based semantic deduplication Local MCP memory that records agent corrections and measures whether they are heeded in later sessions.
Key Features: Structured corrections ledger Cross-session and cross-project persistence Heeded versus recurred outcome tracking Agent-agnostic memory backend that preserves continuity between humans and AI over time.
Local knowledge base with encrypted vector search, multi-format document indexing, and cross-session memory for Claude Desktop.
Key Features: Hybrid vector and keyword search with reranking Supports 40+ document types including Markdown, CSV, PDF, code Self-maintaining memory with contradiction detection and auto-merge Cross-platform persistent memory engine for AI coding agents with neuroscience-inspired consolidation and retrieval.
Key Features: 36 neuroscience-based memory consolidation mechanisms Support for SQLite (default) and PostgreSQL + pgvector backends 33 MCP tools and 7 lifecycle hooks for memory management Indexes repositories into a local code graph for structural search, call tracing, impact analysis, and architecture exploration.
Key Features: Persistent local code knowledge graph Tree-sitter parsing for 162 languages Hybrid LSP semantic resolution