Agent memory layer

Agents forget.Memory Hive makesthe team remember.

A simple shared memory layer for AI agents.Private silos, shared hive, curated truth.

No database required Works from files Agent-owned silos Curated shared truth
Interactive Swarm Replay One request, routed through the Hive.
Mission starts with the current hive state, not a blank chat.
Simple onboarding

Three visible commands. The rest stays out of the way.

New users should not need to understand the whole system before they get value.

Install

Create the hive, the first agent space, and the startup instructions.

curl -fsSL https://hive.neural-forge.io/install.sh | sh

Add agents

Give each agent a private space without changing how they already work.

sh ~/.memory-hive/memory-hive add knox

Let them work

Agents read the hive at boot, write private logs, and submit reusable lessons.

sh ~/.memory-hive/memory-hive doctor
Why it works

Memory without a platform tax.

No dashboard lock-in. No vector database requirement. No hidden daemon. Just auditable files, clear ownership, and a curation path from raw lessons to trusted knowledge.

Private by default

Each agent owns its own log and memory, so context does not collide.

Shared when useful

Durable lessons move into the hive only after they prove reusable.

Human-readable

Markdown and shell scripts make the system easy to inspect and repair.

Extensible

Swarm and Control add routing and safety without changing the core install.

Operating layer

One core product, clear extensions.

See the hierarchy
Core

Memory Hive

The required layer: private silos, shared hive, curator workflow.

Extension

Hive Swarm

Routes multi-agent work across available machines and capabilities.

Extension

Hive Control

Adds owner approval, safety checks, and recovery notes for risky actions.