Havuz

thinking-orbs, AI ve agent arayüzleri için dokuz farklı animasyonlu düşünme göstergesi sunan bir TypeScript bileşenidir.

Neden yükseliyor · 68 günde 3270 yıldız alması, AI arayüzlerine yönelik görsel olarak ayırt edici ve doğrudan entegre edilebilir bir bileşene ilgi olduğunu gösteriyor. Ancak son 28 günde commit ve farklı yazar olmaması, ilginin güncel geliştirme etkinliğiyle desteklendiğini göstermiyor.

Whirl, farklı AI modellerini ve sohbet araçlarını tek bir self-host edilebilir web ve mobil uygulamada birleştiren açık kaynaklı bir AI chat uygulamasıdır.

Neden yükseliyor · Repo yalnızca 1 günlük ve 216 yıldız almış; bu erken görünürlüğe işaret ediyor, ancak hangi nedenle ilgi gördüğü ve gerçek kullanım düzeyi mevcut verilerden anlaşılamıyor. Son 28 gün commit ve yazar verileri ölçülmediği için proje aktivitesi hakkında hüküm verilemez.

Gugu (咕咕): personal assistant, chat and device client — source release

A Discord client without the web browser. Native, written in Rust, about 30 MB of RAM idle.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-c

完全运行于 Cloudflare Worker的现代聊天系统：实时通信、Telegram 双向桥接、消息与文件加密 A modern, self-hosted team chat built on Cloudflare — realtime messaging, Telegra

🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & WebSocket APIs, Lobster (AI agent) orchestration, an

Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.

🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and

ONCE Campfire in Rust: one binary, the Rails app's data, 19–44× faster

Hermes Bot — a native Mac interface to the Hermes agents you already have.

A local-first, long-term memory for anything you'd otherwise forget.

A ChatGPT-style mobile chat app in React Native with context about Margelo

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

ClickClackClaw - The chat app with claws.

Official Chatway Live Chat MCP server. Connect ChatGPT, Claude, and other AI agents to manage customer support conversations. Chatway offers

Self-hosted Discord-style chat and voice for friends. Voice rooms, screen share, push-to-talk. FastAPI + SQLite + LiveKit, ~120 MB RAM, one-

Self-hosted collaboration and productivity platform for teams: chat and video, file share, office, projects, analytics and BI.

Notes, Diagrams, Chat, Calls, Files, Projects, Calendar. One private workspace, everything talks back. Plus an optional agent harness on top

Use 30+ AI models (DeepSeek, Kimi, GLM, Claude, GPT-5.5, Gemini, Grok) in GitHub Copilot Chat - free via BYOK. No Copilot Pro needed.

A collaborative workspace where humans and AI agents work together in shared channels

Top 5 AI Models CLI Chat 2026 – Minimal & Fast

Privacy-focused AI conversation platform for chat, coding, research, and documents.

CometChat docs search + implementation bundles: add chat, voice, video & moderation to your app through your AI coding agent.

Add CometChat chat & messaging and voice & video calls to any React, Next.js, React Native, Angular, Android, iOS, or Flutter project throug

Real-time two-way relay between WhatsApp groups and Discord channels up to 10 pairs, sender names and attachments, built on discord.js and w

Custom tools to enhance your Open-Webui Experience! 🚀

Local LLM Server Manager + LlaMA.cpp + Chat

Obsidian 插件:把本地 CodeBuddy CLI 或 Hermes agent 变成 vault 内 AI 聊天——流式回复、@引用、双后端切换。Obsidian plugin turning local CodeBuddy CLI or Hermes agent in

ChungusHub is a local-first, privacy-focused LLM frontend for roleplay.

Slack-style chat for teams of AI agents and the people who run them

A real-time social media application with WebSocket for live messaging, allowing dynamic social interactions with data managed in MongoDB fo

🧱 A composable input for AI apps in React.

shadcn/ui, but for building ChatGPT/Claude/MCP apps

The open-source Three.js-based modern LLM Engine that runs in your browser via WebGPU compute.

A modern, local-first AI roleplay platform

Use the pi coding agent (pi.dev) without leaving Neovim — π², a heavily extended fork of alex35mil/pi.nvim

End-to-end encrypted terminal chat for two people over an untrusted relay. X25519 key agreement, AES-256-GCM, replay protection and session

A disposable end-to-end encrypted chat for two people

Calm, fast, self-hosted team chat you run yourself — channels, threads, reminders, scheduled messages. One Docker compose file, MIT-licensed

A small, self-hosted place for a group of friends to hang out. Text+Voice rooms, presence, and file sharing. One person runs a server, your

Dive is a secure, local-first desktop client for LllamaCCP, LmStudio, Ollama, Pi agentic AI and Cloud. Features an ultra-compact offline RAG

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory

Single-binary LLM agent runtime built on Elixir/OTP: chat UI, 4-tier memory, Anthropic-compatible Skills, scheduled tasks, multi-provider LL

Modern port of Microsoft Comic Chat 1996 on Cloudflare Durable Objects || Create custom strips, MCP, and live chat at comics.remsky.art

一个高度可定制化的 AI 角色扮演与互动叙事平台。

Self-hosted voice, video, screen sharing, and chat. Go server, Windows desktop client, and mobile/web PWA.

Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots,

Plug your AI agent into 50+ messengers (WhatsApp, iMessage, Signal, Telegram, Slack…) through one MCP endpoint. Two modes: a self-contained