"How to invoke Claude code or API" matching MCP servers:

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

Searches your local Claude Code conversation history to recall and resume past solutions.

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

An MCP server that reads all your Claude Code project memory files and exposes them as tools. Lets any Claude instance — in any project, or via Claude.ai — query your full project history and preferences.

MCP server that indexes a knowledge base of past bugs and fixes, making them searchable via BM25 from Claude Code or any MCP client.

MCP server for reading Claude Code session history from the local filesystem, exposing project and session data to MCP-compatible clients.

An MCP server that enables users to retrieve, filter, and search through Claude Code conversation history stored in local projects. It provides tools for listing projects and sessions, paginating through message history, and searching across conversations with keyword filtering.

Turns Claude into a structured interviewer with a collective evolution system that gets smarter with each conversation.

Enables Codex to list and read saved Claude Code conversations, retrieve incremental context updates before replies, and optionally ask Claude text-only follow-up questions within a selected session without disrupting the workflow.

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.

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.

Enables Claude Code to retain cross-session memory of facts, decisions, and lessons with semantic search, while tracking user corrections as behavioral patterns and evolving self-improving frameworks over time. All processing runs locally through an MCP server and hooks, requiring no cloud service or API key.

Gives Claude Code persistent memory across sessions with semantic search, tracks and classifies user corrections to surface behavioral patterns, and evolves behavioral frameworks over time based on accumulated evidence. Runs entirely locally through 15 MCP tools and hooks, requiring no API key or cloud service.

Gives Claude Code persistent cross-session memory with semantic search, automatically detecting and classifying user corrections to track behavioral patterns over time. It also extracts signals from each session to evolve, promote, or retire behavioral frameworks, letting the assistant develop judgment that improves across sessions.

Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections, and evolving behavioral frameworks that develop over time. Runs fully locally through Claude Code's hooks and 15 MCP tools, requiring no API key or cloud service.

Enables Claude Code to retain identity, memories, and behavioral frameworks across sessions — saving facts and decisions for later semantic search, detecting and classifying user corrections, and evolving learned frameworks over time. Everything runs locally through a SQLite-backed engine with 15 MCP tools plus hooks, requiring no cloud service or API key.

Gives Claude Code persistent cross-session memory with semantic search over saved facts, decisions, and journals, alongside automatic detection and classification of user corrections as trackable behavioral patterns. It also extracts behavioral signals from sessions and evolves self-authored frameworks over time, so the assistant develops judgment that carries forward between conversations — all local, with no cloud or API key required.

Gives every Claude surface (claude.ai, Desktop, mobile, Office add-ins, Claude Code) read and write access to the memories, transcripts and notes produced by Claude Code instances on all of your machines, with hybrid keyword and semantic search. Runs as a self-hosted remote MCP server with GitHub allowlist authentication, secret redaction and audit logging.

Enables Claude Code sessions to automatically capture and retrieve architectural decisions, code changes, bug fixes, and configuration context across sessions using local SQLite storage and hybrid semantic/keyword search.

Gives Claude Code a persistent identity and cross-session memory with semantic search over saved facts, decisions, and journals. It also detects and classifies user corrections into behavioral patterns with lifecycle trends, reflecting periodically to promote or retire working frameworks.