Havuz

AI 中转站福利导航：31 个中转站的邀请链接合集，含签到状态与实测备注

Qwen-Image 3.0 API 中文文档：模型 ID、每张 $0.0206 计费、图像参数与调用示例，含 curl / Python 代码与 OpenAI 兼容接口说明。

Seedream 5.0 Pro API 中文文档：模型 ID、每张 $0.0146（1K-layer） 计费、图像参数与调用示例，含 curl / Python 代码与 OpenAI 兼容接口说明。

A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter

Memory-aware GGUF inference runtime with OpenAI-compatible serving

No Mac Mini? No problem. HermesFace is the best free way to deploy Hermes Agent on HuggingFace Spaces — 2 vCPU, 16GB RAM, 50GB storage, alwa

Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style up

Seedream 5.0 Pro API 한국어 가이드: 모델 ID, 장당 $0.0146 (1K-layer) 요금, 파라미터, cURL·Python 예제와 OpenAI 호환 엔드포인트 설명.

Review every AI edit before it touches your LaTeX. A local web app: comment on a passage, get a word-level diff, accept or reject. Uses Clau

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apa

Nano Banana 2 API の日本語ガイド：モデル ID、1枚あたり $0.015 の料金、パラメータ一覧、curl・Python の実行例と OpenAI 互換エンドポイントの解説。

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy

Gray is an open-source (MIT) AI agent harness shipped as one static Rust binary. Bash-only tools, resumable JSONL sessions, a self-compactin

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-

Local LLMs that run lean, load instantly and keep getting smarter. A from-scratch runtime + model format in Zig: zero-copy mmap, CPU/CUDA/Vu

zen-proxy is a local translation proxy that bridges Claude Code's Anthropic Messages API with OpenCode Zen's OpenAI‑compatible Chat Completi

ModelFlux: OpenAI-compatible model traffic router with health-aware key-pool scheduling and failover

Open-source engine for personal AI assistants that chat on web, WhatsApp, Telegram, email and Slack, with memory, connectors, sandboxed code

一览：稳定的网页 AI 摘要扩展，支持长文分段总结、历史记录、分享卡与多接口适配。 A local-first Chromium extension for AI web summarization and reader mode, with BYOK support, hist

BrighTO LLM Router: free open-source, ultra-fast Rust LLM gateway/router and LiteLLM/Bifrost alternative with OpenAI + Anthropic APIs, Claud

Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.

Run RKLLM only in one docker command. Already converted models here.

Windows x64 本机模型网关：让 Cursor、Devin、Codex、Claude Code CLI 与 Claude Desktop 使用你自配的模型 API，含模型库、调用记录与 Token 统计。

Zero-dependency Go proxy for rotating free-tier AI API keys. No more 429s.

One hotkey to ask any AI on Mac. Open-source menu bar assistant: press ⌥Space to ask with your own API key (OpenAI, Claude, any OpenAI-compa

Local-first desktop coding agent with BYOK, MCP, and OpenAI-compatible / Ollama hosts

Unified interface to call OpenAI and Anthropic compatible LLM APIs from Rust and other languages

The fastest-growing AI community on Discord. Chat, earn, and build together. discord.gg/crow

Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.

Bulk classification and decision inference on one GPU: the content is read once, every question about it is scored in the same pass. OpenAI-

Windows utility focused on local AI API server, local endpoint manager, and OpenAI compatible API for local AI workflows.

Governed AI agents for sensitive data and business-critical apps. Agents never hold credentials: a gateway checks every call against per-res

Real-time Windows system-audio translation captions for Chinese, Japanese, English, and Korean, with optional LLM revision.

Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model acc

Interface web pour Hermes Agent, l'agent auto-apprenant de Nous Research : plusieurs agents avec rangs et pôles, délégation tracée, mémoire

Prism — a one-click desktop LLM gateway. Embeds 37 providers (OpenAI / Anthropic / Gemini / Bedrock / …) behind one OpenAI-compatible endpoi

为 Hark 提供统一的OpenAI 兼容 API，支持文本对话、图片生成、图片编辑、异步任务和本地控制台。Q交流群1124104343

Offline Telegram Bot API for testing bots, Mini Apps and LLM integrations.

HR policy RAG assistant with LangChain LCEL, RunnableBranch, FAISS, FastAPI, and an OpenAI-compatible model API.

HR policy RAG workflow with LangGraph StateGraph, conditional routing, FAISS, FastAPI, and an OpenAI-compatible model API.

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

OpenAI-compatible Go gateway for Vertex AI Gemini with explicit model routing, live catalog refresh, and Cloud Run setup.

划词即理解的 AI 阅读工具 — Select text anywhere on macOS or windows system and get instant AI translate / explain / summarize in a floating bar. Tauri

把 FutureSearch 的异步任务 API 反代成 OpenAI 兼容端点 + 管理面板 + 两组 MCP（研究 / 本地文件）。号池、租户额度、本地预览。

开源 AI 应用评测平台，支持 RAG、AI Agent、多轮对话、LLM-as-Judge、接口评测、评测报告和人工盲测。Open-source AI evaluation platform for RAG, AI Agents, multi-turn conversation

Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet

OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Ant

Pool free-tier API keys from any provider and rotate through them — round-robin key selection, per-key usage/quota tracking, and a drop-in H

macOS-first desktop translator built with Wails, comparing multiple OpenAI-compatible providers, models, and target languages in parallel.