Databricks App for cross-workspace AI stack governance. Unified view of agents, serving endpoints, knowledge bases, and AI Gateway usage, backed by system tables + Lakebase with auto-refreshing discovery workflows.

OTel-native typed primitives for LLM cost attribution and telemetry — published on PyPI.

PyPI-distributable LLM control plane: gateway choke point, cost attribution, OTel instrumentation, and offline reporting as an inspectable engineering artifact.

Behavioral GNN for cloud cost attribution

Pre-dispatch policy evaluation and cost attribution for LLM inference, built on llmscope.

Per-subagent cost attribution for Claude Code. Reads local JSONL session logs, computes shadow cost at marginal Anthropic API rates with proper TTL pricing.

Terraform cost attribution CLI/API for mapping cloud billing costs to Terraform resources, modules, owners, and pull requests.

Project OpenTelemetry GenAI traces into a queryable graph (Neo4j or DuckDB) — agent delegation, cost attribution, blast radius.

Offline LLM cost attribution recipes for OpenAI-compatible gateway logs by user, feature, route, model, retry, and tool call.

Lightweight AWS Lambda proxy for OpenAI Codex CLI — per-developer token auth, full request/response logging, cost attribution, and centralized access control.

AI FinOps Engine - GPU/LLM cost attribution for Kubernetes

Policy-bounded decision traces for AI-assisted financial operations: versioned policy enforcement, human-in-the-loop gating, cost attribution, and auditable case outcomes.

AI-assisted cost attribution methodology for finance practitioners — usage-based allocation, automated validation, and self-service financial intelligence across manufacturing, healthcare, logistics, and technology.

FinOps cost attribution for AI code agents: maps Kiro, Cursor, and Claude Code spend to git commits to reveal per-task cost, waste patterns, and agent ROI signals.

OpenTelemetry SpanProcessor that translates GenAI spans into business-metric spans (cost_usd, tokens_total, latency_ms, tenant). Drop-in for any Go service running OTel. Per-model pricing table; overridable.