Open-core memory infrastructure for AI
Spectral memory engine, Rust-powered RAG, native knowledge graphs, 3D visualization. Bring your own LLM, your own database, your own data.
Apache-2.0 engines · PostgreSQL-backed · Self-host or managed
$ docker compose -f docker-compose.bundle.yml up
The memory your agent accumulates is your IP — user intents, factual context, retrieval embeddings, audit trails. Closed memory backends mean your data lives on someone else's servers, indexed by their schema, queryable on their terms. Kumbukumbu engines are Apache-2.0. Self-host the whole stack, or use the managed SaaS — same engine in both.
Each engine ships as its own package. Run them together via the bundle, or pick the one you need.
ASMIS
A fact, a how-to, a recent event, an uncertain hunch — they're different shapes of memory. Kumbukumbu retrieves the right shape, not just the closest match. Beyond vector similarity.
pip install kumbukumbu-asmis
RAG
Four Rust crates: core, server, CLI, Python bindings. Benchmarks for chunking, embeddings, vector search, and cache — you measure, not trust marketing numbers.
pip install kumbukumbu-rag
Knowledge graphs
core.knowledge ships graph + vector together.
Unified KMS layer — query memory by similarity AND by relationship.
from kumbukumbu_asmis.core.knowledge
Viz
Interactive 3D views of memory graphs, goal hierarchies, agent networks, temporal patterns. Browser-side, npm package.
npm i @theaistep/kumbukumbu-viz
Plus kumbukumbu-sidekick: an autonomous optimization service
using LangGraph workflows to keep your memory layer healthy without manual tuning.
Self-hosted means you keep the data and the bill. Kumbukumbu engines provide the memory layer; everything around it stays yours.
Bring your own LLM
OpenAI, Anthropic, Google, Mistral, or fully local. The engine is provider-agnostic.
Bring your own database
PostgreSQL is the supported backend. Same SQL connection your app already uses.
Apache-2.0 engines
ASMIS, RAG, Viz are all Apache-2.0. Read the code, fork it, audit it.
No phone-home
Self-hosted instances never call back. Telemetry is opt-in and clearly named.
Thin clients for ASMIS and RAG, in the language your stack already speaks. No bundled HTTP client, no opinionated runtime.
pip install kumbukumbu-asmis-sdk-py
cargo add kumbukumbu-asmis-sdk
npm i @theaistep/kumbukumbu-asmis-sdk
pip install kumbukumbu-rag-sdk-py
cargo add kumbukumbu-rag-sdk
npm i @theaistep/kumbukumbu-rag-sdk
Self-host the engines for free, or use the managed SaaS. Same engines in both.
Try it
For evaluation
Indie
First production app
/month
Pro
Audit-ready memory
/month
Enterprise
Your domain, your region
/month, contact for scope
Or run the engines yourself — Apache-2.0, no usage limits, no phone-home, your PostgreSQL.
Memory isn't one kind of thing. A user fact, a procedural skill, a long document, a short conversation — these need different lifecycles. Kumbukumbu ships a three-tier registry: core types in the Rust engine, platform types added at startup, and your own types registered per-app.
Tier 1 · Core
Seven types baked into the Rust engine, covering the canonical shapes:
document_part
conversation
fact
context
user_memory
computed_statistic
…
Plus platform types (system, batch,
document) added by ASMIS at startup.
Tier 2 · Your own
Devs register custom types, scoped by tenant. Two tenants can register the same
type_id with different schemas — no collision.
registry.register_app_type(
"quiz_answer",
"Quiz Answer",
"User responses",
tenant_id="acme",
)
Tier 3 · Premium
Three managed-cloud types with extra guarantees, for regulated workloads:
regulatory_evidence — audit-ready compliance artifactsaudit_trail — immutable, tamper-evident write logsigned_intent — intent records co-signed with a Sawabona keyShipping AI under audit?
Kumbukumbu is the memory layer of the LLM Compliance Bundle — paired with build-time analysis (Jagora), runtime sandboxing (Zelo), and a signed evidence chain (Ushahidi).
Also from theAIstep — the rest of the stack: