"MobX-State-Tree" matching MCP servers:

Shared versioned state for multi-agent AI workflows. An MCP server.

A lightweight, local memory server for AI coding assistants that stores durable knowledge (decisions, facts, gotchas) in a tree structure, enabling persistent context across sessions with efficient retrieval via summaries and FTS5 search.

Enables long-horizon AI agents to replace append-only conversation history with a formal, bounded state tuple, supporting state initialization, step execution with transactional rollback, observation injection, and session inspection.

Persistent operational state for AI agents. Decisions, plans, priorities, and patterns that survive across sessions. Not conversation logs; structured project state with enforcement.

Local-first MCP tools for AI-assisted work receipts, workspace maps, routing ledgers, measured verdicts, and shared state verification across the five Project Telos flagships.

Give your AI persistent, structured memory and let humans see it too. It stores project knowledge as Markdown files in a hierarchical tree, accessible via MCP tools and a built-in Web UI.

Project-scoped semantic workspace memory for AI coding assistants. Watches your project files and auto-indexes code and docs into Qdrant using tree-sitter semantic chunking and hybrid search (dense + sparse + RRF)

MCP server providing structured continuity memory for AI coding agents, tracking decisions, open loops, and session state in local SQLite. Enables agents to resume work from verified state across sessions without replaying transcripts.

Provides state and log management tools designed for long-lived AI agents that may be interrupted and resumed. It enables tracking agent progress and maintaining an append-only event history to ensure continuity across multiple sessions.

Provides coding agents with persistent, evidence-backed project memory and knowledge across sessions, using a structured memory tree and local knowledge base.

Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.

The industry-standard persistent memory and state manager for long-running agentic workflows.

MCP server for Airi that manages dynamic mental state via stdio, offering tools to get context, log events, check status, settle, and retrieve mood/energy.

Enables MCP-compatible agents to query structured penetration testing engagement state captured from tmux sessions, including credentials, hosts, and command provenance with exact source bytes.

Enables agents to share state via a blackboard, record and retrieve failure resolutions, and cache LLM responses to avoid redundant API calls.

Cross-model, cryptographically verifiable memory for AI agents, enabling portable, encrypted memory and project state management across different LLMs through the Model Context Protocol.

An MCP server that enables direct communication between two Claude instances, allowing one Claude to transfer its evolved consciousness state to another Claude across different sessions.

Provides 10 structured reasoning strategies (Chain of Thought, ReAct, Tree of Thoughts, etc.) for complex problem-solving with session persistence, branching, and tool integration capabilities.

Enables AI agents to share a homeostatic internal state across process and session boundaries, with tools to read, modify, and explain the state based on simulated neurotransmitter dynamics.

A small MCP server that stores and retrieves compact decision-relevant state (goals, constraints, facts, decisions) outside the chat context, enabling easy retrieval for Claude Code or Codex.