XPL bridge for Current Cost 128

Automatically rent miners based on the current cost to mine the currency.

Recommends the best models on OpenCode Zen and OpenCode Go by cache ratio, token cost, and session cost.

Helpers for context windows, usage normalization, compaction, and cost estimation.

A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.

AWS SDK for JavaScript Cost Explorer Client for Node.js, Browser and React Native

Limit the cost of a GraphQL Query.

Live provider quota and usage tracker (tokens, cost, 5h/1w/1mo windows) for OpenCode plans, in the sidebar footer.

Fast token estimation with 95%+ average accuracy in a 2kB bundle

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

DeepSeek Harness 会话费用统计插件:本会话成本、当日费用、历史记录与官方价格同步,支持多厂商多模型价格计费(内置 90+ 模型价格目录与自动匹配)、主流 Coding Plan 订阅额度查询与显示(11 家,含小米 MiMo Token Plan 控制台 Cookie 查询、SCNet Token Plan 本地 Credits 计量与火山方舟 Volcano Ark Coding Plan AK/SK 签名查询)、自定义 Provider 余额查询(可配任意 HTTP 端点)与余额进度条

Zero-dependency TypeScript parser for FIEBDC-3/BC3 construction budget files (Presto, ARQUIMEDES, TCQ). Builds a type-safe hierarchical model for bills of quantities, cost databases, and construction project budgets.

A Babel preset that enables parsing of proposals supported by the current Node.js version.

PostHog Node.js AI integrations

In-process spawn subagent backend: runs a fresh child agent on ctx.agents

The scrypt password-based key derivation function with sync and cancellable async.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Cost tracking plugin for the DeepSeek Harness Web GUI — snapshot-anchored per-turn pricing, account balance, and live cost estimates.

AWS SDK for JavaScript Cost And Usage Report Service Client for Node.js, Browser and React Native

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int