// High-Performance Local-First Data & Infrastructure
Purpose-Built Systems for AI Agents,
Graph Databases & Syndication
Native binary speed. Self-hosted data sovereignty.
No JVM. No heap tuning. No ceremony. Just Friendly.
// Product Suite
Purpose-Built Data & Infrastructure Tools
AsanagiDB
High-performance document store & Gremlin graph engine. Native binary speed with zero JVM overhead.
AsanagiAMI
Agentic Memory Infrastructure. Native MCP server tools for Claude/Gemini agents and long-term memory graphs.
01. Philosophy
We believe software should be correct and simple, but never simplistic.
Infrastructure that stays out of your way means you think about your problem, not your tooling. That's the goal. Every design decision in AMI follows from it.
02. The Case
Ditch
the JVM.
Neo4j shipped its first release in 2010. The JVM was the right call then. Graph databases have outgrown it.
Neo4j Community
- RequiresJava 17+
- Min heap512 MB
- Recommended4 GB+
- Cold start8 – 15 s
- GC pausesunpredictable
- Binary size~450 MB
JanusGraph
- RequiresJava 11+
- BackendCassandra / HBase
- IndexElasticsearch / Solr
- Setup time45 min minimum
- Processes3 JVMs to start
- Binary size>1 GB w/ deps
v1.2.0
- Requiresnothing
- Idle memory~50 MB
- Recommendedwhatever you have
- Cold start< 50 ms
- GC pausesnone. no GC.
- Binary size~5 MB
Enterprise-class graph queries
on a Raspberry Pi.
LMDB is a memory-mapped B-tree used inside OpenLDAP, the Tor Browser, and Apple Mail. It doesn't buffer — it lets the OS page cache do what the OS page cache is already great at. Reads are cache hits. There's no buffer pool to tune. There's no heap to size.
Zig compiles to native machine code with no runtime. No garbage collector means no latency spikes during traversals. What you measure in benchmarks is what you get in production.
// Verified on Raspberry Pi 4 (4GB RAM)
< 2 ms
won't start (OOM)
// Full benchmarks vs Neo4j + JanusGraph — coming soon
03. Products
Your new friends.
Batteries included. Minus the Python.
The CLI and the MCP server are the same binary — one codebase, no drift between what you script and what your agent uses. We build what's actually needed. Nothing here exists because it was trending this quarter.
Core Engine
AsanagiDB
The graph engine. Listens for Gremlin queries over WebSocket or HTTP. Stores data in LMDB — your data directory is the entire database. Back it up with cp -r.
- → Gremlin 3.x query engine
- → WebSocket + HTTP transports
- → ACID transactions (LMDB)
- → Fleet config for multi-instance
Memory Layer
AsanagiDB-mcp
The Model Context Protocol server. Your AI agent's persistent brain. Exposes a vocabulary of memory tools so models can read, write, and traverse their own knowledge graph.
- → Works with Claude, Gemini, any MCP client
- → Graph-structured context (not flat files)
- → memory_save / search / context / relate
- → Same binary, different subcommand
Local Inference
AsanagiLIS
High-performance local inference server. Connects directly to the live AsanagiDB MCP graph — mid-generation native tool calling, multi-model adapters, write-gating security.
- → Embedded llama.cpp engine (Metal GPU / AVX)
- → Mid-generation native tool calling (Gemma, Qwen, Llama)
- → Write-gating guardrails & context optimization
Query Console
asna
The interactive Gremlin console. Connect over a Unix socket, plain TCP, or WebSocket and drop into a REPL — or run a script and exit.
- → Unix socket, TCP, ws:// / wss://
- → Line editing, history, named connection profiles
- → REPL mode or single-script execution
Command Line
AsanagiDB-admin cli
Database operations from the terminal. Export to GraphSON, import from any supported format, manage licenses. Pipe it, script it, automate it.
- → AsanagiDB graphson-export — full graph export
- → AsanagiDB graphson-import — GraphSON NDJSON
- → AsanagiDB csv-import / apoc-import / dataset-import
- → AsanagiDB activate — license management
Visual Console
AsanagiDB-admin ui
Browse, query, and manage your graph visually. Live-rendered graph topology, vertex/edge inspector, Gremlin query console. Native on macOS, Windows, and Linux.
- → Live graph visualization
- → Interactive Gremlin console
- → Import / export UI
- → macOS / Windows / Linux native