Havuz

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU

三个 AI 客户端的内置提示词一键替换：DSH / WorkBuddy / ZCode。双击即用、可自证、改前备份、一键还原。v8.29：卡片式界面、登录强制激活码、DSH 插件自动注入、官方群验证。免装 Python 单文件 exe，完全免费开源。

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable deliv

A coding agent engine and CLI with cache-aware context management.

Per-window model switcher, subagent router, and automatic 429 failover for Claude Code — switch any window with /provider, delegate subagent

跨 AI 桌宠：跟着你用的 AI 换形象、跟着 AI 的工作状态做动作

TokenSpeed, agentic workloads için LLM inference sunumunu hızlandırmayı ve istek yönetimini daha güvenli hale getirmeyi amaçlayan bir inference engine’dir.

Neden yükseliyor · 144 günde 2.178 yıldız ve son 28 günde 385 commit ile 20 farklı yazar, hem ilgi hem de yakın dönem geliştirme faaliyeti gösteriyor. README ayrıca PyTorch Ecosystem’e katılımı ve yeni model desteğini vurguluyor; performans iddiaları ise proje tarafından sunulan kıyaslamalara dayanıyor.

Uncensored & abliterated AI models (GLM-5.3, DeepSeek V4, Qwen3) + Claude, GPT, Kimi, Gemini — one OpenAI/Anthropic-compatible API key. Docs

把腾讯 WorkBuddy 账号变成 OpenAI 兼容 API 的多账号网关。请求头照官方桌面端逐项对齐，主备入口 + HTTPDNS 自动切换，国内 / 国际双域合池，企业号可用 Claude，签到与成长任务全自动，React 管理面板支持一键更新。原版 workbuddy2

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

Turn a model gateway into a standard OpenAI-compatible API with a built-in web console. Zero deps (Node.js built-ins only). 把华为云果办 OfficeAce

Use GPT, DeepSeek, GLM, Gemini, Kimi and 400+ models in Claude Desktop's own model picker and in Claude Code, while staying signed in to you

Use DeepSeek, GLM, Kimi, OpenRouter and more in Codex CLI and Claude Code: one local endpoint, API translation, failover. Single Rust binary

Your friendly, blazing-fast, self-hostable AI gateway

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with

Lightweight Rust Agent only use 50MB RAM, but Claude Code Plugin compatible, Dynamic Workflow, Goal, Artifacts, Free Web Search, full featu

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

Run the pi coding agent as a self-hosted service: jobs from cron, the CLI, or GitHub, GitLab, Forgejo and Azure DevOps events, each in a loc

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

ACP agent in TypeScript that uses the Z.AI / Zhipu AI GLM Coding Plan models (GLM-5.3, GLM-5 Turbo, GLM-4.7) as the reasoning core

ZCode 插件集：AI 会话自动命名、会话操控 MCP（Stop Hook + 官方远控通道）

Gnome extension to monitor the status of Anthropic (Claude), OpenAI (Codex) and more

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH

Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

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

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

Windows 版 Codex Desktop 简体中文语言包，一键安装汉化；支持 codex汉化、Codex 中文菜单、国产模型接入、DeepSeek/千问/智谱、多账号切换、跳过官方登录。

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

Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by defaul

免 API Key 用 DeepSeek/GLM/Kimi 等 9 家国产大模型的 AI 编程 Agent · 技能自进化引擎(GEPA 自我改进) · 3D 桌宠 · 九宫格工作台 · 长期记忆 · OmO 智能体编排(生命周期钩子+6 Discipline Agent+计划审

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

Turn ChatGPT Web (including Pro) into Codex. Turn Claude Web into Claude Code. Also DeepSeek, Gemini, Grok, Kimi, GLM. No API key, no MCP, n

You pick the model per task, with review, evidence, and a PR at the end.

Use GLM models in GitHub Copilot Chat with your own API key. Supports image input, tool calling, and streamed thinking.

潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Uncensored AI API and browser chat: DeepSeek and GLM models, streaming, Python and TypeScript examples, pricing and setup guides.

Claude orchestrates and reviews; Sonnet, Codex, GLM, or Grok implements. A Claude Code plugin for the orchestrator/implementer split: /serve

GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec d

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

Free AI models in VS Code Copilot Chat / DSH via browser auth. No API keys required.

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

QA agent swarms. Test web apps autonomously with greater speed and accuracy. Visual navigation, real workflows, evidence-backed reports.

Claude省钱版 — 效果基本一致的情况下可以节约Token消耗约90%，超级省Token，支持OpenAI及国产大模型(DeepSeek/GLM/通义千问)的AI编程助手。本项目基于ClaudeCode源码实现。