state-memory-mcp is a zero-infrastructure, deterministic Model Context Protocol (MCP) server for developer AI agents, providing persistent long-term state memory.
Why it matters
API Docs
API Available
overview
state-memory-mcp is a Model Context Protocol (MCP) server tool developed by PuterVision that enables developer AI agents to track workflow state, decisions, and blockers. It provides persistent long-term state memory for AI agents, managing task execution DAGs, architectural decision logs, and session context.
features
state-memory-mcp provides a suite of features designed to enhance the performance and reliability of AI agents by offering structured, persistent memory and deterministic operations. These capabilities aim to reduce context bloat and improve the efficiency of multi-turn AI interactions.
.state-memory-mcp/graph.db) for externalizing workflow state.use cases
state-memory-mcp is primarily designed for developer AI agents and the developers who build and deploy them. Its capabilities are particularly beneficial in scenarios requiring consistent state tracking, decision logging, and efficient context management across complex development workflows.
.feature files.how to use
state-memory-mcp functions as a local, structured memory server for AI coding assistants. It integrates via the Model Context Protocol (MCP) to manage and store various aspects of a development workflow.
pricing
state-memory-mcp operates on a freemium and open-source business model, offering usage-based pricing for its services. The cost is calculated per million tokens processed, with various tiers available.
Enjoying this? Get one like it in your inbox each morning.
one email a day · unsubscribe in two clicks · no third-party tracking
state-memory-mcp itself are not prominently detailed beyond its initial description.Similar Tools
state-memory-mcp differentiates itself from other memory solutions and graph databases by offering a specialized, zero-infrastructure, deterministic Model Context Protocol (MCP) server focused on AI agent state management. It contrasts with general-purpose graph databases and probabilistic vector search systems.
A mature, dedicated graph database designed for highly connected data, offering powerful query capabilities with Cypher.
Neo4j is a general-purpose graph database, requiring more setup and explicit schema design for workflow state compared to state-memory-mcp's specialized focus. It offers greater flexibility and scalability for complex graph data but might have a steeper learning curve for simple state tracking.
A multi-model database supporting graph, document, and key-value data, allowing for flexible data modeling beyond just graphs.
ArangoDB provides a multi-model approach, which can be more versatile if your state tracking needs extend beyond pure graph structures, but it might require more configuration to specifically replicate state-memory-mcp's deterministic graph server behavior. It offers broader database capabilities at the cost of specialized focus.
A distributed, open-source graph database designed for scale and real-time queries, using GraphQL as its query language.
Dgraph is built for distributed environments and offers GraphQL API access, which can be advantageous for scalable AI workflows. However, it might have a steeper operational overhead for smaller, single-instance deployments compared to state-memory-mcp's potentially simpler server model.
More on Stork
Other tools in this category, matched by shared tags
One short daily email of tools worth shipping. No drip funnel.
one email a day · unsubscribe in two clicks · no third-party tracking
For builders
AI agents read it. Buyers land on it. It answers in eight languages and over MCP. Your tool can have one like it — live in 24 hours.