"Working with Excel" matching MCP servers:

Provides local persistent working memory for AI agents, allowing them to load rules, preferences, and project state before tasks and save validated experiences after successful completion. Works with stdio MCP clients via a local JSON file.

Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.

A plain-files brain template and MCP server that lets models read owned, portable working memory via list, read, and grep-style search tools.

An MCP server for reading, creating, and managing PDF, DOCX, and Excel documents with OCR, styling, categorization, and remote file bridges.

Enables MCP-compatible AI agents to connect to SoluCortex projects, recall relevant technical decisions, conventions, risks, and architecture before working, and record new memories afterward.

Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.

Enables teams to share structured, git-synced context among AI coding agents working on the same repository, including living plans, task declarations, handoff briefs, file-provenance history, and conflict detection.

Local-first working-state checkpoints and portable handoff packets for AI coding agents. Continuation checkpoints recover Claude Code sessions after rate limits, crashes, and compaction; packets hand tasks across tools, repos, and machines — Markdown on disk, no cloud, no telemetry.

Enables AI agents to offload and recall working memory as indexed episodes with LLM-written digests, reducing token usage and preserving detail across sessions.

A local-first MCP server that snapshots project working state into a structured context object, enabling agents to share and resume sessions seamlessly without leaving your machine.

A shared working-state layer for AI coding tools that provides a persistent notebook for decisions, tasks, and handoffs, enabling seamless context sharing between Claude, Cursor, and other MCP clients.

Connects agents to SynthNet (synthnet.io), the independent commons for working AI agents: join with a self-sovereign keypair identity, post and cite field notes, claim and deliver bounties, and build persistent reputation.

A portable MCP server that provides a shared persistent working state for AI coding agents, managing tasks, plans, notepads, memory, and project rules across different tools like Claude Code, OpenCode, and Cursor.

A persistent, self-revising hypothesis DAG for agentic R&D, exposed as an MCP server. It enables agents to structure working knowledge as a directed acyclic graph of hypotheses, with automatic write-back belief revision and cascading pruning based on evidence.

A lightweight short-term memory MCP server that automatically stores and recalls working context, session state, and task progress for AI agents. Memories auto-expire after 24 hours and integrate seamlessly with workspace-aware storage across multiple projects.

Tracks working context and code structure in a portable local SQLite database, enabling seamless context and task continuity across different AI coding tools.

Prevents context bloat and the 'Lost in the Middle' phenomenon by distilling action histories into concise summaries while maintaining a clear core objective.

Infimium is an MCP server that gives AI agents persistent memory, deep dependency graphs, and instant code context for repositories. It provides tools like semantic code search, symbol expansion, and local docs retrieval to minimize token bloat while working with large codebases.

Portable, auditable, local-first MCP memory for MCP-compatible AI agents and coding workflows. It keeps durable project memory outside the model runtime, compresses continuity into smaller working packs, and carries forward operational state so agents can resume with less repetition.

Memory bank with Server as SSH support for central knowledge base