Havuz

Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and

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.

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

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

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

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

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

Claude Code'u EVREN'in model filosuna bağla: tek komut kurulum, geri alma, Linux/WSL/Windows

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

OpenAI- and Anthropic-compatible local gateway for ZCode plan quota. Single Go binary, stdlib only.

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

Local-first AI agent workbench for long-running projects: background work, built-in memory (no Docker), six web search services, MCP. macOS,

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

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

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

Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程

Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

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

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

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

LinkTokenView（联视未来）国产大模型 Token API 聚合平台，提供 OpenAI 兼容接口，统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型，支持 Token Plan 与 Coding Plan。支持Codex、Claude、Harne

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

vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.

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

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

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

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

A static performance model for LLM inference: given (model, GPU, interconnect, workload), instantly answer VRAM feasibility, latency(TTFT, T

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

国内主流 LLM Coding Plan 真实用量榜单：厂商宣称 vs 用户探针实测 vs 官方 monitor 三方对照。一眼看穿动态倍率、积分通胀、隐藏限流——买之前，先查账。

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

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

Any Model for VS Code Copilot

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。

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

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

Restores reasoning content dropped from multi-turn OpenCode conversations (DeepSeek, Kimi, GLM, MiMo, MiniMax, InclusionAI/Ling, OpenRouter)

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