llm-cost

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.

Claude Code, Codex and Pi write down everything you do. bough draws it and prices it: a day, the work inside it, every prompt, and what each piece cost. One Go binary, runs on your machine, sends nothing anywhere.

Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted

Nadir is a Python package designed to dynamically choose the best llm for your prompt by balancing complexity and cost and response time.

Cloud FinOps Skill & MCP by OptimNow. FinOps Foundation aligned knowledge for AI agents: cloud cost (AWS/Azure/GCP/OCI), AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, waste detection, GreenOps. Installs into 12 AI tools, or connect the hosted MCP server by URL. Refreshed weekly.

Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.

LLM spend tracking and budgets for Rails — by user, feature, or any tag, in your own database, no proxy.

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~45% lower cost. Glues busyBee-cpu, honey-comb, and rust-brain.

Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱：成本/用量监控 · 自动更新 · 定时任务

Token and cost reports for 17 AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, Copilot, pi and more), read from local session logs across all your machines

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

Claude Code token usage and cost dashboard. Cost per prompt, cache misses and usage limits for Claude Code, Codex and GitHub Copilot CLI, read from local logs. Zero dependencies, nothing leaves your machine.

Agentic development environment: run Claude Code, Codex, OpenCode and Gemini CLI side by side, and follow every PR from agent to release with its cost. Desktop app for macOS, Windows and Linux. Local, free.

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line Python API for Claude Code, Codex, Cursor, OpenAI, Anthropic & Ollama. pip install foveance