Local, cache-aware LLM usage and cost telemetry for OpenClaw.
Git-native granular cost accounting for AI-developed repos, what did this commit cost? Reads Claude Code / Codex / Gemini CLI / aider logs, joins them to git history, and prices every commit, PR and release. Measured from real tokens, never estimated.
Building production-grade AI infrastructure — RAG, agents, evals, and cost-aware LLM systems. Currently: routing queries to the cheapest model that can handle them.
Claude Code plugins for the full feature lifecycle: idea → Value Increment → ARD → spec → design → Epics → implementation → docs → release notes, each gated by an Opus review. Tracks what every feature costs in $ by phase, role and model, and captures friction in-flight so the workflow keeps improving.
Track OpenClaw LLM calls, show real costs, and cut agent spend with a local dashboard and no data leaving your machine
Seven patterns for adding AI features to existing products: sidecar vs in-process, streaming, caching tiers, eval-gated deploys, fallback UX, cost guardrails, vendor-lock hedging. Each says when to skip it. CI parses the doc and lints out fabricated numbers.
Offline LLM cost attribution recipes for OpenAI-compatible gateway logs by user, feature, route, model, retry, and tool call.
Enterprise AgentOps platform — traces every agent run, attributes LLM cost, scores output quality async, and maps decisions to financial outcomes. FastAPI · LangGraph · React · SQLite
GitHub Copilot plugins for the full feature lifecycle: idea → Value Increment → ARD → spec → design → Epics → implementation → docs → release notes, each gated by an AI review. Tracks what every feature costs in $ by phase, role and model, and captures friction in-flight so the workflow keeps improving.
AI copilot retrofitted into an existing multi-tenant Django SaaS without touching its schema or auth: semantic search, ask-your-data behind a SQL guardrail, summarization, each with a per-tenant cost cap, PII redaction and an eval gate in CI. Tests run offline, no API key.
Code examples for Tokonomics — AI cost metering proxy for OpenAI, Anthropic, DeepSeek, Gemini & more. Track every LLM token, set budget alerts. https://tokonomics.ca
Self-hosted telemetry stack for AI coding tools (Claude Code, Codex): OTLP ingest, VictoriaMetrics/Loki storage, Grafana dashboard for token usage & cost
Experimental CLI for estimating AI-agent request costs and tracking budget assumptions across OpenAI, Anthropic and GitHub Copilot.
Streamlit dashboard for clustering + RFM segmentation + agent telemetry analytics. Multi-LLM provider routing with cost tracking.
Ghost-text reply autocomplete retrofitted into an existing Laravel + Vue support desk: PII redacted before the prompt is built, prefix cache, per-requester daily token budget, rate limiting, cost report. The engine is swappable, so tests run offline with no API key.
Offline LiteLLM pricing and model metadata diff CLI for AI gateway cost reviews
Offline-first OpenAI-compatible LLM cost tracking and budget guardrail CLI.
The core FortifyRoot LLMOps SDK for Python.
Runnable Python, TypeScript and .NET examples for tracking LLM cost across 15+ providers with the AI SpendOps proxy.
ntkn is project-level token accounting for AI agent work.
To associate your repository with the llm-cost-tracking topic, visit your repo's landing page and select "manage topics."