Kumiho is a graph-native platform for revisions, lineage, and automation - plus optional AI Cognitive Memory with long-term recall, provenance, rollback, and audit trails.
Works with your storage and workflows. Built for traceability, not just chat history.
Kumiho Platform manages assets, revisions, lineage, and automation.
AI Cognitive Memory turns the same graph primitives into long-term memory for agents (episodic to semantic consolidation, dependency-aware updates, auditable reasoning).
LLM model layer is decoupled
Kumiho does not provide or resell LLM inference. Connect your own OpenAI, Anthropic, local model, or AI agent runtime. Kumiho provides memory, provenance, indexing, and auditability.
How buying works
Core platform tiers for creators, studios, and teams.
$0
For exploring Kumiho
Try graph-native revisions, lineage, and AI Cognitive Memory before production rollout.
Optional: Add Memory Standard for higher node caps.
$40/month
For solo creators and freelancers
Manage personal workflows, versions, and outputs with full memory capabilities.
$99/month
For small teams shipping real work
Shared knowledge, traceable decisions, and agent workflows that do not forget.
$170/month
For high-throughput studios and production environments
Heavier automation, larger memory graphs, and faster retrieval on high-performance infrastructure.
Contact
For org-wide deployment and compliance
Security, governance, and custom architecture at enterprise scale.
All platform plans include BYO storage. You keep control of your files.
AI Cognitive Memory is included at every tier. Add Memory Standard to boost your Free plan limits.
$29/month
For Free users who need more memory capacity
Boost your node cap and memory limits without upgrading to a paid platform tier.
Creator, Studio, and Studio Pro already include higher memory limits — no add-on needed.
Step 1
Session-local context in Redis for fast store/retrieve operations.
Step 2
Consolidated facts and links persisted with provenance edges.
Step 3
Scheduled consolidation refines memory and supersedes stale beliefs.
Memory Ops, retention, cadence, and graph scale.
| Limit | Free | Creator | Studio | Studio Pro | Enterprise |
|---|---|---|---|---|---|
| Nodes (total) | 1k | 30k | 500k | 2M | Unlimited |
| Node cap with Standard add-on | 20k (+1 project) | — | — | — | Custom |
| AI Cognitive Memory | Included | Included | Included | Included | Included (Custom) |
| Working memory retention (per session) | 6h | 24h | 24h | 72h | Custom |
| Memory ingest / day | 100 | 500 | Included | Included (higher) | Custom |
| Max buffered messages / session | 50 | 200 | 1,000 | 2,000 | Custom |
| Dream State (nightly consolidation) | On | Nightly | Nightly | 2x nightly or deeper pass | Custom cadence |
| Memory retrieval mode | Hybrid (BM25 + vector) | Hybrid (BM25 + vector) | Hybrid (BM25 + vector) | Hybrid (BM25 + vector) | Hybrid (BM25 + vector) |
| Vector-indexed memory items / month | 1k | 10k | 100k | 250k | Custom |
| AI Memory Ops / month | 1k | 25k | 150k | 400k | Custom |
| API rate limit (req/sec) | 100 | 100 | 100 | 100 | Custom |
| Events / day | 100 | 2,000 | 5,000 | 10,000 | 50,000 |
AI Cognitive Memory uses the same graph primitives and counts toward your node limit.
BYO-LLM: Kumiho charges for infrastructure and indexing. LLM usage runs on your own provider key.
AI Memory Ops / month: Memory Ops = store + retrieve + consolidate. These can map to event stream throughput.
Security, privacy, and billing behavior at a glance.
It stores structured revisions and explicit relationships so agents can trace sources, revise beliefs, and explain recall decisions.
Yes. Every tier includes AI Cognitive Memory. Free users can add Memory Standard ($29/mo) for higher node caps and limits.
New information can supersede older memory while preserving linked history for traceability and rollback.
Add usage packs, upgrade tiers, or apply throttles and retention policies.
Start on Free with AI Cognitive Memory included, boost with Memory Standard, or go directly to Creator or Studio for higher limits.