GitHub project

Memory Hivefor agent teams.

A small file-based memory layer for AI agents.Private silos, shared hive, curated truth.

SQLite/FTS5 recall Cited bundles Agent-owned silos Curated shared truth

create this skill... 5 recipes for tacos created 4k logo for Tendril remember: no bland UI source notes saved deployment lesson learned

Simple onboarding

Start with three commands.

Install the hive, give an agent a memory silo, then run the health check. No dashboard ritual required.

Install

Creates the hive, first agent silo, and boot instructions.

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

Add agents

Gives each worker a private memory space without changing the workflow.

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

Verify

Checks the install so agents can boot, remember, and submit lessons.

sh ~/.memory-hive/memory-hive
doctor

v1.1 HyperRecall

Recall got fast without losing proof.

Memory Hive now builds a local SQLite/FTS5 recall index beside the markdown. Agents ask for cited bundles instead of dragging the whole hive into context.

Markdown stays truth. Every result carries source path + line span. Bundles stay small enough for swarm handoffs.

memory-hive recall build --json
memory-hive recall query "task context" --json
memory-hive recall bundle "task context" --for-agent hermes

Speed proof Before broad context. After cited recall.

Beforefull hive context

209k tokens

Afterrecall bundle

386 tokens

542×smaller context packet

8msbundle cache hit

1,089files indexed locally

Measured on Travis's live hive: 20,652 chunks indexed, FTS5 enabled, stale files clean. The index accelerates lookup; cited markdown remains the source of truth.

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.