Havuz

opencodex, Codex ve Claude araçlarını farklı LLM sağlayıcılarına yönlendiren yerel bir proxy sunuyor.

Neden yükseliyor · 101 günlük yaşına rağmen 16.344 yıldız ve son 28 günde 3.591 commit ile dikkat çekiyor; 11 farklı yazarın katkısı da yakın dönem hareketliliğini destekliyor. Bu ilginin özel nedenini verilen verilerden doğrulamak mümkün değil.

Open Executive, şirket bilgisi ve geçmiş kararları kullanan uzman agent'ları tek bir tutarlı yönetici persona'sı üzerinden sunan bir AI yönetim asistanıdır.

Neden yükseliyor · 108 günde 5.323 yıldız alması, yönetici iş akışlarını multi-agent AI ile destekleme fikrine güçlü ilgi olduğunu gösteriyor. Ancak son 28 günde 345 commit'e karşılık yalnızca 2 farklı yazar var; ilgi sinyali belirgin olsa da katkı tabanı dar ve yıldızlar gerçek kullanımın kanıtı değil.

vibecode-pro-max-kit, AI coding agents için planlama, uygulama ve kontrol aşamalarını bir araya getiren, projeye eklenen spec-driven bir geliştirme iş akışı kitidir.

Neden yükseliyor · 124 günlük yaşında 1138 yıldız almış olması belirgin ilgiye işaret ediyor; kapsamlı agent iş akışı ve tek komutla kurulum vaadi bu ilgiyi açıklayabilir. Ancak yıldızlar kullanım kanıtı değil; son 28 günde commit ve farklı yazar verisi sıfır olduğundan ivmenin sürüp sürmediği bilinmiyor.

Open-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos w

CLI, SDK, and IDE plugins for Duel Agents

Open-source AI interfaces built with Claude (Fable 5) including hero sections, GLSL shaders, design systems, animations, 3D components and

A custom Agent OS built to be hackable, heavily inspired by OpenClaw.

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang

An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 1

Local-first MCP gateway. Set up MCP servers once and use them in every AI client, with secrets in the OS keychain, tool integrity checks and

Automatic AI video editing. Claude directs HyperFrames (HTML + GSAP motion graphics) and Remotion (timeline assembly) to turn raw footage in

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, co

cc-switch 中转站的专用增强版（cc-switch for API relay providers），免去配置各种 密钥 endpoint 的烦恼。

Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, an

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

An AI-powered Quran knowledge graph — place verses on a canvas and discover thematic, linguistic, and theological connections.

Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Sesión Cloud 2026: Agenda Inteligente, Facturación y Videollamadas con IA para Psicólogos

Advanced Multi-Agent AI Crude Oil Trading System with Adversarial Validation 2026

CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git worktree, task orchestration,

Proxy patch for Google Antigravity that intercepts internal Cloud Code API and adds support for OpenAI, Claude, Ollama, Gemini and any custo

Revolutionizing Indonesian Exam Prep: AI Teacher Tools 2026

Smart Factory LLM Routing & OAuth Gateway Plugin 2026

2026 NEO Impact Triage: Bayesian AI Cross-Validation Against Sentry-II & ESA NEOCC

Model Context Protocol server giving Claude (or any MCP client) full read + write access to your Whoop fitness data via the private reverse-

AI Company로 자동화 조직을 만드세요

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read

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

AZMX AI — The sovereign agent platform.

Official Cursor SDK to Anthropic-compatible HTTP gateway with native MCP tool continuation.

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, re

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

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Agent Reliability Analyzer: deterministic scanner that finds and fixes AI agent reliability failures

⚔️ Compare AI models side by side — same prompt, streamed answers, live code previews, speed, tokens and cost. Keys never leave your browser

Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Zotero MCP server: search, citations, add by DOI, safe writes, semantic search and PDF page images for Claude, ChatGPT and any MCP client. T

Plan-first companion for Claude Code - draft the plan, learn every Claude Code feature inline, run it as a crew, and see your token usage. L

Claude Code 的桌宠与本地工作台 · A desktop pet & local workbench for Claude Code — 实时动画、权限卡片、Token 看板，兼容 codex-pet / cc-switch ⚓

跨平台桌面工具箱·36+ 工具·AI Chat/翻译/Provider 切换/Claude·Codex 用量洞察·剪贴板/HTTP 调试/取证/编解码/加密。Wails + Go + React + TS

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover,

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6%

One command to cut token usage by up to 50%+

A Claude Code status line with a reactive character plus cost, git, and usage widgets. Zero token spend, local-first, MIT.

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

Persistent memory for Claude Code. Your AI never starts from scratch again.