Folkbench — AI skill for Claude Code
AI API 中转站评测排行与切换工具:实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex.
How to install Folkbench
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Folkbench/folkbench and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Folkbench does
AI API 中转站评测排行与切换工具:实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex.
Alternatives in AI
- AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
- Room — Open-source earning-focused swarm intelligence engine 838 ★
- Claude Code Switch — One-command model switcher for Claude Code (Only for Anthropic API) 655 ★
README
Folkbench
选中转站,不靠感觉,靠数据。
AI API 中转站评测排行(API relay benchmark)· Claude Code / Codex 一键切源客户端
[](https://github.com/Folkbench/folkbench/releases) [](LICENSE.md) [](https://github.com/Folkbench/folkbench/releases) [](https://tauri.app/) [](https://t.me/+ZCsDR_BEHLw1OGRl) [](https://qm.qq.com/q/71NzSTrPVK)
[🌐 在线评测大盘](https://folkbench.com/rankings/board?utm_source=github&utm_campaign=folkbench-blog) · [⚡ Switch 客户端](#2-用线路folkbench-switch-客户端) · [📦 下载安装](#3-下载安装) · [🔥 热门模型](#热门模型) · [💬 交流群 (TG)](https://t.me/+ZCsDR_BEHLw1OGRl) · [💬 QQ 群](https://qm.qq.com/q/71NzSTrPVK) · [English](README.en.md) · [日本語](README.ja.md)
平时用 Claude Code、Codex 这类 AI 编程工具,核心其实就是两件事:**选一条靠谱的中转线路**,以及**把线路配进工具里**。
Folkbench 将这两件事串联成了一个完整的工作流:
- 🌐 1. 选线路:多节点探针 7×24 小时真实压测,看各中转站的可用率、P95 延迟与价格,挑出稳定不掺水的服务。
- ⚡ 2. 用线路:开源桌面客户端统一管理 Base URL 与 API Key,在 Claude Code、Codex 等工具之间一键切源,免去手动修改配置文件的繁琐步骤。
1. 选线路:Web 评测大盘
主站探针通过持续自动化调用,公开各中转站的实时监测数据,拒绝黑盒与虚标。
- 📊 综合总榜:综合考量可用率、P95 响应耗时与计费单价。
- 🛡️ **[稳定性榜](https://folkbench.com/rankings/board?metric=availability&utm_source=github&utm_medium=readme&utm_camp
Related Skills
RivalCode
Open source profiler, replay debugger and benchmark arena for AI coding agents. Compare Codex, Claude Code, Ge
PIBench
PIBench is an open-source benchmark for evaluating AI coding agents on realistic, end-to-end payment integrati
Agent Eval Harness
Live, open-source benchmark for comparing AI coding agents on real GitHub issues
Smart Switch
Multi-app model provider switcher: manage OpenAI/Anthropic-protocol providers (base URL + API key + models) an
onWatch
Open-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHu
TOMC
TOMC Memory: open-source context compression and task memory for Claude Code, Codex and LLM APIs. CPU-only pre
Related Agents
Paf Reviewer
Runs one phone-a-friend relay or review command in the background and reports back a receipt plus the findings
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Mathodology Evidence Researcher
Use for literature, data source, background, benchmark, and citation work in award-level modeling submissions.