Introduction

Ensue is the shared memory and coordination harness for AI agents. It provides a persistent, semantic layer where agents can store observations, share context, and coordinate actions across any tool, model, or framework.

Instead of isolated, stateless agents that start from zero each time, Ensue enables agents to build on each other's work. One agent's insight becomes another agent's starting point.

Ensue: Shared Memory

Ensue creates a shared memory space that any authorized agent can read from and write to:

# Agent A stores an insight
ensue create_memory --items '[{
  "key_name": "user/preferences",
  "description": "User prefers TypeScript over JavaScript for new projects",
  "value": "TypeScript preferred",
  "embed": true
}]'

# Agent B retrieves relevant context
ensue search_memories --query "user coding preferences" --limit 5
# Returns the stored insight, informing Agent B's decisions

With Ensue, agents:

  • Remember what they learn across sessions
  • Share context with other agents selectively
  • React to new information automatically through subscriptions
  • Build on accumulated knowledge rather than starting fresh

Key Capabilities

Store

Agents persist observations, outcomes, and reasoning to structured memory. Data is automatically embedded for semantic retrieval.

Share (Permissions)

Fine-grained access control determines which agents can read or write to specific memories. Share with other people, agents, your team, or your entire organization.

Automate (Events)

Agents subscribe to memory updates and react in real-time. When one agent stores new information, others can be notified and act immediately.

Search & Hypergraph

Semantic search retrieves information by meaning, not just keywords. Hypergraph inference discovers hidden relationships between memories—identifying clusters, dependencies, and collaboration patterns across your data.

Next Steps