Ecosystem

Three layers.
One stack for agents.

lattice runs inference locally. khive holds memory. lionagi orchestrates. Three independent, open-source projects, built to work together. We also maintain pydapter, a data adapter library, alongside them.

01latticeinference
02khivememory
03lionagiorchestration
01 · lattice

lattice

Local inference

LLM inference engine for Apple silicon: run, quantize, and fine-tune models with Metal acceleration. Pure Rust, no Python, no CUDA, no ONNX. Optimized for Apple silicon; runs on Linux as well.

RustApache-2.0crates.io
02 · khive

khive

Knowledge & memory runtime

Research knowledge-graph runtime for AI agents. Typed entities, a closed edge ontology, and hybrid search, served from a single Rust binary over MCP.

34Rust crates
1single binary
MCPnative
Apache-2.0open source
RustApache-2.0crates.ionpm
03 · lionagi

lionagi

Agent orchestration

Agent orchestration framework for building and running multi-step LLM workflows in Python, with the li command-line interface for building, running, and observing agents.

PythonApache-2.0PyPI
04 · Lion Studio

Lion StudioComing soon

Orchestration & observability

Orchestration and observability studio built on lionagi: agent runs, schedules, and live telemetry, in one place.

pydapter

Data adapter library for moving structured data between Python objects and external systems through a common interface.

Start with khive. Self-host today.

Run the open-source binary yourself, or go managed with khive cloud when you're ready to skip the infra.

05 · Consulting

AI Architecture & Agent Systems Consulting

Production agent systems — multi-agent orchestration, memory infrastructure, LLM integration. I built khive as a cognitive OS for AI agents in Rust. I consult on the same class of problems.

Quick Call

One specific question

$89/ 15 min
  • Architecture gut-check
  • Build vs buy decision
  • Quick sanity check on an approach
Book 15 min session

Working SessionMost popular

Enough time to dig into a problem

$189/ 30 min
  • System design review
  • Technical due diligence
  • Implementation planning
  • Written follow-up
Book 30 min session

Deep Dive

Full session with deliverables

$399/ 60 min
  • End-to-end system design
  • Code review
  • Agent orchestration planning
  • Written brief
  • 30-day async follow-up
Book 60 min session

All sessions prepaid via Calendly.