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 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 Cross-tool memory for your AI that recalls first every turn and admits when it doesn't know.
Provides up-to-date, version-specific code documentation and examples for libraries via CLI or MCP server.
Key Features: Version-specific documentation retrieval Supports CLI commands and MCP server integration Library ID resolution for precise doc fetching Shared team knowledge platform serving docs, agents, workflows, and skills via MCP to Claude, Cursor, and others.
Key Features: CRUD operations for files, agents, skills, workflows, and tags Semantic search across all team documentation Workflow and project management with phases and tasks Agent memory system enabling AI agents to learn and recall long-term information with high accuracy.
Key Features: State-of-the-art long-term memory accuracy Supports multiple LLM providers (OpenAI, Anthropic, Gemini, etc.) Easy integration via LLM wrapper or direct API calls 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 MCP server to access and manage your Mendeley reference library and global catalog via API.
Key Features: Library document search and retrieval Folder and collection management Global catalog and DOI paper lookup Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
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 Query the Noteboxd fragrance encyclopedia (fragrances, notes, brands, reviews, and charts).
Loads a personal profile mined from local AI coding session logs to make agents act like you.
Key Features: Local mining of session logs from Claude Code, Codex, Copilot CLI, OpenCode, and Google Antigravity Multi-layer profiles for different task categories Native loading in Claude Code and Codex agents