LLM cost-control layer — response caching, budget gates, model routing, per-tenant metering. The margin-protector for managed AI runs.

CLI for Llummo — real-time LLM cost tracking & proxy

Obsivara AI observability SDK — track LLM cost, tokens, errors, traces and health for AI agents and n8n workflows.

Lenxes Node SDK — one-line auto-instrumentation for LLM cost & observability (OpenAI, Azure, Anthropic, Google, Mistral, Bedrock, Vercel AI SDK, LangChain).

Forecast LLM cost from Linear issue estimates before work begins.

Zero-config LLM cost shield. One line. Cut your OpenAI / Azure / Anthropic bill by 30-60%.

💰 Beautiful CLI to count tokens and estimate costs for any LLM model (Claude, GPT, Gemini, Mistral, and 300+ more). Auto-updates prices from OpenRouter.

MCP server that estimates the dollar cost of LLM API calls and workflows from token counts, using ComparEdge's verified per-1M-token prices for 60+ models across 16+ providers.

GitHub Action for Inferwise — posts LLM cost diff comments on pull requests

Core types, schemas, utilities, and configuration for LLM cost telemetry

Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings,

LLM cost calculator powered by LiteLLM pricing — 2400+ models, auto-cost on API calls

Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings,

Cost collection, multi-dimensional aggregation, and budget enforcement for LLM cost telemetry

OpenTelemetry tracing, metrics, and structured logging for LLM cost telemetry

Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold

Per-agent LLM cost attribution + budget enforcement + cross-provider fallback for Node.js. Wraps your provider client (OpenAI, Anthropic, Bedrock, Gemini, Mistral) and emits a metering row to the spaturzu gateway on every call, with frame-based agent attr

Local-first security scanner for AI Skills (Anthropic Skill bundles, Newmax, OpenClaw, MCP, GPTs Actions). Catches malicious code, supply-chain attacks, and prompt injection — pure static analysis, sub-2s, zero LLM cost.

MCP server exposing Tessera's LLM cost optimization layer as tools for Claude Desktop, Claude Code, Cursor, Cline, Continue, and other MCP-aware clients. Returns savings decisions (anchored spend, drift detection, recommendation approval), not raw logs.

MCP server for LLM token counting and multi-model cost estimation (GPT-4o, Claude, Gemini, and 25+ models). Local-first, no API key.