Folkbench/folkbench

HL-2026-1020·0219

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

Historial de estrellas

7 capturas

3694

2182

13 OCT26 OCT

Últimos 7 días: +1512 en 5,4 días
Últimos 30 días: Historial insuficiente (7 capturas)
Método: Diferencias entre capturas almacenadas. Cómo funcionan las tendencias

GitHub search: LLM projects created recently; GitHub search: New Rust tools.

JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
115,1 mil
NousResearch/hermes-agent
The agent that grows with you
257,1 mil
earendil-works/pi
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
117,7 mil
heygen-com/hyperframes
Write HTML. Render video. Built for agents.
72,4 mil
ggml-org/llama.cpp
LLM inference in C/C++
132,4 mil
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
175,7 mil