MCP server providing automated, context-aware documentation and code convention insights for GitHub repos.
Key Features: Compact pre-edit repo context including conventions and gaps Change impact analysis linking code paths to docs and conventions Structured API endpoint context for touched code paths Persistent memory MCP server with knowledge graph, semantic search, cloud sync, and cross-session context management.
Key Features: Persistent storage with SQLite or cloud sync (S3, R2, D1) Hierarchical memory organization with sections and subsections Semantic search using TF-IDF, sentence-transformers, and OpenAI embeddings MCP server providing safe read/write access and comprehensive operations on Obsidian vault notes via MCP.
Key Features: Safe YAML frontmatter parsing and AST-aware updates File operations: read, write, patch, delete, move notes/files Partial reads: get note outlines and specific line ranges Self-hosted MCP server providing persistent memory with Qdrant vector search, Neo4j graph, Ollama embeddings, and Claude/Ollama LLM support.
Key Features: Qdrant vector memory storage and search Optional Neo4j knowledge graph integration Ollama embeddings and local LLM support Local code intelligence engine indexing repos into a persistent knowledge graph with fast structural queries across 159 languages.
Key Features: Indexes 159 languages using tree-sitter and Hybrid LSP Supports 15 MCP tools including graph search, tracing, and impact analysis Runs as a single static native binary with zero dependencies Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
Self-hosted coordination layer providing shared semantic memory, tasks, messaging, and session handoffs for AI agent fleets.
Key Features: Shared semantic memory with multiple types and confidence decay Ambient memory plugin for automatic knowledge injection and capture Durable capture queue with background archivist for memory compaction MCP server providing structured, offline access to ZIM knowledge archives like Wikipedia with advanced search and navigation.
Key Features: Supports ZIM archives from Kiwix Library Advanced 8-tool schema plus Simple natural-language query mode Archive-type presets for optimized retrieval per source Local-first MCP server that compresses and audits AI coding context to reduce cost and verify responses.
Key Features: Recoverable compression using BM25, entropy, and dependency graph knapsack Stable prompt prefixing for provider cache discounts Bayesian routing of tasks to cheaper models MCP server to ingest and search knowledge from Slack, Discord, web, Google Drive, Linear, GitHub, and more via Graphlit.
Key Features: Ingest files, emails, messages, issues, and web pages Extract and convert documents to Markdown Transcribe audio and video files Local-first AI memory server storing knowledge as Markdown files with semantic search and optional cloud sync.
Key Features: Local-first plain text Markdown storage Two-way human and AI file editing Semantic knowledge graph with wikilinks Local memory layer indexing coding agent session histories for fast recall and cross-machine sync over SSH.
Key Features: Zero-dependency single binary, fully local operation Search 3.5 GB of session history in ~1.5 ms Supports multiple coding agents via MCP protocol