Lamina

Lamina gives AI coding agents a centralized, transactional product graph: one place to publish product intent, observe the implementation, and attach verification evidence without collapsing those kinds of knowledge together.

Observed

Repository sources

Managed CocoIndex worker emits rebuildable observations.

Inferred

Agent proposals

Typed resources and statements enter explicit sessions.

Runtime evidence

Mission runs

Adapters normalize events and attach evidence.

Sole writer

graphd

Authenticates, validates, versions, and commits atomically.

Canonical

Ladybug

Stores GraphVersions, views, missions, runs, and facts.

Content-addressed

Evidence CAS

Keeps immutable evidence payloads outside graph facts.

Every ingress crosses graphd; no observer, agent, or adapter opens Ladybug. Scroll horizontally to inspect the full flow.

Ladybug is the canonical local knowledge graph. It stores stable Resources, normalized Statements, versions, branch/session/observation views, Missions, Runs, and evidence. Git identifies source revisions and branches but does not store graph changes.

Read the architecture from left to right:

The managed worker turns repository files into rebuildable observations.
Agents stage typed proposals in explicit graph sessions.
Mission adapters normalize live product events into runtime evidence.
Every write crosses graphd. It is the only process that opens Ladybug read-write, and it publishes graph changes transactionally.

Start


curl -fsSL https://github.com/aryaniyaps/lamina/releases/latest/download/install.sh | sh
npx skills add aryaniyaps/lamina --skill '*' -a <active-agent> -y
lamina doctor --json
/lamina-init
# then use ordinary product requests

Setup also runs lamina setup --agent <provider>. Use lamina graph status to inspect the resolved GraphVersion and lamina context status to inspect the derived hybrid-retrieval generation.

Why it is different

Serializable sessions publish completely or leave the branch unchanged.
Intent, observations, agent inference, Persona simulation, human evidence, and runtime evidence stay separate.
Conflicts remain inspectable as Contradictions.
Every active Persona receives an independent Mission and Run.
Every implementation obligation is mapped to code and verification before edits.
UI verification requires functional, visual, responsive, and accessibility evidence.
Source changes update an observation view without mutating canonical Claims.
Hybrid retrieval selects Workflow roots and source symbols without replacing graph authority.
Existing legacy run files are ignored by the runtime.

Continue with The product loop, or inspect the transactional graph in detail.