Back to directory

Epicode

An open-source spatial AI memory system that stores agent memories as tetrahedrons in 3D space, builds a knowledge graph from them, and serves persistent cross-session memory to AI agents over MCP.

Epicode

Epicode stores memories in continuous 3D space and automatically extracts relationships between them into a knowledge graph, giving AI agents persistent memory across sessions. Search combines BM25 keyword matching with HNSW vector search, and memories carry validity windows and a freshness-decay score for time-aware recall.

It exposes 35 tools over MCP for any MCP-compatible agent, uses a structured memory response format with topology and placement metadata, and supports multi-tenant cloud use with quotas and invite codes. A self-hosted defense component watches SSH, web and honeypot traffic and bans attackers automatically, and call-detail statistics are exposed on a stats endpoint.

The backend is written in Rust with Axum, Tokio, SQLite and ONNX Runtime for embeddings; the frontend is React, TypeScript and Vite. It runs locally with Docker Compose.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.