Nexus-PRIME Labs

The stack expanded

Five layers.
One operating system.

Every layer below is a real product. Two ship as open installs today. Three run inside enterprise engagements. The stack composes — you can run one layer, three, or all five.

Book intro call Engagement modes
Catalog · 05 layers

Inspect every layer in the stack.

Layer 01 · control plane

Nexus Prime

agent memory at its core

OPEN

The control plane every multi-agent system eventually needs. Persistent memory, token-aware planning, repo-aware file selection, and review gates — wired into one orchestrator that Codex, Claude, Cursor, and your own agents can call.

  • Persistent memory across sessions
  • token-aware planning
  • review gates
  • multi-client MCP surface
$ npm i -g nexus-prime
  • npm latest · nexus-prime@7.9.27

Coordinate agent memory, context, and execution across handoffs inside a production workflow.

Open product site Docs
Layer 02 · compression

tetris.codes

fits the window

OPEN

Real compression for real agents. Tetris collapses prose, code, and traces with a multi-channel pipeline so long coding-agent sessions don't blow the context window — and don't blow the bill.

  • Multi-channel compression
  • token-aware reads
  • MCP-native
  • drop-in for Claude, Codex, Cursor
$ curl -fsSL https://get.tetris.codes | sh
  • one-line installer · live

Compress long coding-agent sessions before context windows become the bottleneck.

Open product site
Layer 03 · protocol

Grain

carries it cleanly

ENTERPRISE

Production agents need to read the business — its processes, its artifacts, its rules — without bespoke glue for every integration. Grain is the protocol layer that makes workflows agent-readable so handoffs stop leaking.

  • Agent-readable workflow schemas
  • typed handoffs
  • audit-grade artifact trails

Define a clean protocol boundary so agents can read your workflows the way an engineer can read your codebase.

Talk to us
Layer 04 · runtime

NXL

runs it cheap

ENTERPRISE

Naive agent loops burn tokens and stall on cold paths. NXL is the runtime — speculative execution, cache-warm planning, deterministic replay — that turns agent loops into a unit-economical execution layer.

  • Speculative execution
  • cache-warm planning
  • deterministic replay
  • token unit-economics

Drop the runtime into a hot agent loop and measure cost-per-task before and after.

Talk to us
Layer 05 · missions

Phantom

directs the work

ENTERPRISE

Real agent work spans hours, days, weeks. Without a mission layer agents drift, work loses intent, and review becomes impossible. Phantom shapes long-horizon work into mission packets your organization can route, remember, and review.

  • Mission packets
  • route + remember + review
  • long-horizon traceability

Shape one long-horizon workflow into a mission packet and ship it as a reviewable operating unit.

Talk to us