Havuz

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

Ekko Studio, birden fazla AI agent runtime’ını ortak chat, coding ve visual workflow arayüzünde birleştiren local-first bir masaüstü ve self-hosted web uygulamasıdır.

Neden yükseliyor · 169 günde 11.205 yıldıza ulaşması dikkat çekiyor; son 28 gündeki 204 commit ve 10 farklı yazar da yalnızca README iddialarından ibaret olmayan güncel geliştirme faaliyetine işaret ediyor. Yıldızlar benimsemenin veya kalitenin kesin ölçüsü değil.

Open CoDesign, farklı AI modellerini kullanarak masaüstünde prototip, sunum ve pazarlama varlıkları üreten açık kaynaklı bir tasarım uygulamasıdır.

Neden yükseliyor · Claude Design ve benzeri araçlara açık kaynaklı, BYOK ve local-first bir alternatif sunması dikkat çekiyor; 163 günlük yaşına göre 7.970 yıldızın yanı sıra son 28 günde 66 commit ve 6 farklı yazar kayda değer geliştirme hareketliliğine işaret ediyor. Yıldızlar tek başına kullanım veya ürün kalitesi kanıtı değil.

End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, meter

Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git work

The memory & storage engine for AI agents. Multi-model, edge-to-cloud, PostgreSQL-compatible.

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, de

本地优先的多模型 AI 图片生成工作台，支持 GPT Image、Gemini、图像编辑、素材库、模板与并发任务。Local-first AI image workbench for GPT Image & Gemini, with editing, reusable asset

Build for agents — from the AI Gateway to the entire application stack.

GPT-5 / Claude Opus 4.7 / Gemini 3.1 / Sora 2 / Suno / DeepSeek / Kimi - AI API integration cookbook for Cursor, Cline, Claude Code, ChatBox

Drop in a UI screenshot and RēDesign runs it past many AI models at once, then gives you a browsable wall of self-contained HTML redesigns t

The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Toke

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistra

AI Coding Agent Orchestrator 2026: Pro-Level Strategy & Review Framework

Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents

Advanced AI Code Strategy Advisor for Developer Agents (2026)

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

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

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

Kimi for Claude Code, Codex, and DeepSeek Harness: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and

GJC(Gajae Code) 5구독 멀티벤더 셋업 — 3대 리서치(Codex/LLM Council/Opus ultracode) + 엔진 ground-truth + red-team 통합 가이드

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video generation agents — from a single

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro