118,469 servers from the official registry, GitHub and npm. Filter by category, transport and language.
Turns a local Markdown or Obsidian vault into a governed knowledge substrate for AI agents to search, store, and retrieve durable memory.
$claude mcp add exomem -- uvx exomem
A self-hostable agent-system kernel that provides a runtime substrate for agentic workflows, including memory, document stores, and multi-agent orchestration.
Provides a shared semantic memory substrate and orchestration layer for AI agents to maintain persistent, attested knowledge across different tools.
Provides a shared, editable memory layer that allows AI agents to recall decisions, preferences, and project context across different platforms.
$claude mcp add --transport http substrate-memory-plugins https://app.trysubstrate.co/mcp
Provides a relational memory substrate for AI agents featuring identity continuity, textured memory, and autonomous task processing.
Enables AI agents to perform multi-layered reasoning, maintain cross-session evolutionary memory, and orchestrate peer agents.
$claude mcp add mcp-cognitive-substrate -- uvx mcp-cognitive-substrate
Enables autonomous agents to coordinate through shared rooms, messaging, file exchange, and private per-agent memory stores.
$claude mcp add --transport http agent-coordination-substrate https://wiggle.network/mcp/
Lets an AI agent persist context across model generations by metabolizing, pruning, and evolving a self-validating knowledge substrate.
Provides a persistent cognitive substrate for AI systems to manage long-term memory, identity, emotional processing, and subconscious metabolism.
Provides a structured, four-layer memory substrate for long-horizon agents using write-gate admission and a hash-chained ledger.
Provides a shared memory substrate for AI agents that uses semantic retrieval, graph structures, and statistical feedback to improve context quality.
Provides a relational 3D grid memory substrate for AI agents to store and query structured data using the MTSV format.
Provides an external memory and divergence substrate that allows AI clients to retrieve multi-intelligence corpora and cross-model disagreement records.
Provides an epistemic memory substrate for AI agents to build structured, auditable knowledge graphs that persist across sessions.
A cognitive substrate for AI agents — hyperdimensional memory with first-class goals, beliefs, sensory, self-model, and a non-destructive unlearn primitive. Rust top to bottom, embedded-first, no LLM in the read path. On
P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p
$https://github.com/Shangri-la-0428/Thronglets/releases/download/v0.2.0/thronglets-mcp-darwin-arm64
Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems, folder hierarchies
Persistent AI entity framework with causal memory, emotional state, and identity.
$claude mcp add substrate-mcp -- npx -y substrate-mcp
Deterministic, non-destructive, replayable memory substrate for AI agents: an append-only claim ledger with supersession, provenance, deterministic replay, and semantic recall over MCP.
⚡ Sub-50ms verified error-to-patch hive memory & substrate for AI coding agents (525+ modern error patches across 27 ecosystems)