Havuz

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

把 Claude Code CLI (claude -p) 包装成 OpenAI 兼容端点，供 SillyTavern 的 Custom (OpenAI-compatible) 源直接调用

Local-first novel-to-comic generator — free, no GPU, pluggable providers.

deepseek-harness 便携式变体 | 即插即用 U 盘 AI 助手：免安装 LLM Web UI、离线可用、适配中国网络，支持 OpenAI 兼容网关（Ollama / 阿里云百炼 / OpenRouter），Windows / Linux / macOS 三端即开即

Konfigurator gateway OpenAI-compatible untuk Claude Code, OpenCode, dan Codex CLI. Zero-dependency, interaktif + CI, backup atomik + restore

Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

LLM gateway comparison: self-hosted and managed AI API gateways compared on protocol compatibility, billing units, timeout and retry semanti

Local-first Chrome extension that turns images into generator-ready prompts.

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM pla

Intelligent multi-LLM router with task-aware routing strategies, cost optimization, and production safety controls — drop-in OpenAI-compatib

Browser-based Android phone agent using WebADB/WebUSB and OpenAI-compatible vision models

Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents

302API 开发者资料与接入示例：Python / Node.js / cURL、客户端配置、前端组件与本地账单验算器。Apache-2.0 开源，再分发请保留 NOTICE 署名。

本地 AI 订阅与 API 网关：统一管理多家服务商账号，为桌面应用和编程工具提供接口。

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

grok-build with the leash off — one binary, any OpenAI-compatible endpoint, zero phone-home. No x.ai account.

Compliance-first AI gateway for Kiro: connect OpenAI, Anthropic, ACP, Claude Code, Cursor, OpenCode, and MCP through the official kiro-cli b

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

Let Your AI Play Detroit：Become Human

Open-source Fugu: the open-source LLM orchestration brain.

get -- get anything from your computer

CCB · AI 编程助手一键配置 —— 把 Trae / Qoder / CodeBuddy / WorkBuddy / Cursor / ZCode 等客户端一键接入 CCB：全部模型自动写入、自动设为默认、自动启动（仅桌面客户端开源）

Zero-cost LLM routing across free-tier model APIs with Bifrost, certification scripts, and agent-ready fallback chains

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workf

The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

Use GitHub Copilot as a local OpenAI/Anthropic-compatible API for Codex CLI, Claude Code, and Continue.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the

面向 OpenAI 兼容模型接口的模型状态监控面板，支持公开状态页、后台管理、SQLite 持久化、重试策略和 Docker 部署。

Use Claude Code, Codex, OpenCode, Cline for free — one local gateway to 14+ free LLM providers. OpenAI & Anthropic compatible.

Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.

Cross platform GLM proxy for AutoClaw's Zhipu AI models. Provides OpenAI-compatible Chat Completions and Anthropic Messages APIs for Claude

Open-source native Apple client for the AI you choose - iPhone, iPad, Mac, Apple Watch, and CarPlay. Your keys; no intermediary.

Open-source human-in-the-loop AI content automation with n8n, Notion, Telegram, AI generation, and LinkedIn publishing.

Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 https:

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor. Fully local voice dictation (

System-wide AI text transformation for Windows

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible

Paused Codex App auth-split proxy experiment; future work would need a Responses-to-Chat-Completions adapter.

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

A TUI around llama.cpp for running, managing, and benchmarking local GGUF models and launching the pi coding agent against your local server