Persistent memory for AI agents
auditable by default.
Kumiho gives your AI assistants graph-native memory that survives context window resets, model swaps, and long-running projects.
Sound familiar?
The amnesia problem
Your agent forgets everything when the context window resets. Every session starts from scratch.
The hallucinated memory problem
You stuff old conversations into the prompt. The model confuses its own summaries with facts.
The black box problem
The agent "remembers" something, but you can't trace where that memory came from or verify it.
Kumiho solves all three. With a graph.
What Kumiho does
Persistent recall
Memories stored as immutable revisions in a graph. Survive context resets, model swaps, and provider changes.
Typed reasoning edges
DERIVED_FROM, DEPENDS_ON, REFERENCED — every memory knows what it came from and what depends on it.
Dream State consolidation
Async background process that enriches, links, deduplicates, and prunes memories. Like sleep for your agent.
LLM-decoupled
Memory lives in Neo4j + Redis, not inside any model. Switch providers without losing history.
A day in the life
Your AI assistant handles a design review. Kumiho stores the conversation summary, decisions, and references as a memory revision.
Three days later, the user asks "What did we decide about the hero layout?" The agent recalls the exact revision with full provenance.
Dream State runs overnight — links the design decision to the project brief, flags stale references, enriches metadata.
Two months later, a new team member asks the agent for project history. Every decision is traceable, every source is cited.
No prompt stuffing. No hallucination. Just recall.
Integration paths
Playground
Web chat powered by your own LLM API key. Talk to your agent and test memory store & recall in real time.
# Launch Kumiho Playground
kumiho playground
# Chat with your AI agent
# Bring your own LLM API key
# Test memory store & recall in real timeClaude Code Plugin
Install the MCP plugin and get persistent memory across every coding session. Zero config.
// .claude/settings.json
{
"plugins": {
"kumiho-memory": {
"url": "npm:kumiho-cowork"
}
}
}
// Memory persists across all sessionsClaude Cowork Plugin
Shared team memory for Cowork sessions. Every decision is traceable to its author.
// Team memory shared across Cowork sessions
// Every decision traceable to its author
kumiho_memory_recall("project architecture")
// → Team-wide decisions with full provenanceOpenClaw Plugin
Install in one command: openclaw plugins install @kumiho/openclaw-kumiho. Full graph traversal and memory lifecycle.
# Install the Kumiho plugin for OpenClaw
openclaw plugins install @kumiho/openclaw-kumiho
# Memory is live — persists across all sessions
# Full graph traversal & reasoning includedHow it works
Memory flows through a lifecycle — each stage adds structure and durability.
Kumiho vs. DIY memory stacks
An honest comparison
| What you need | RAG + Vector DB | Kumiho AI Cognitive Memory |
|---|---|---|
| Store conversations | You build chunking + embedding | memory_store() — one call |
| Recall by meaning | Vector similarity (no structure) | Hybrid: fulltext + graph + vector |
| Trace provenance | Not available | Every memory has typed edges |
| Handle contradictions | Hope the model figures it out | Dream State detects + resolves |
| Survive model swaps | Re-embed everything | LLM-decoupled by design |
| Audit trail | Build your own | Immutable revisions + timestamps |