Havuz

Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limit

A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

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

Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, con

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisi

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

Give the agent "this" and he gets a real PC.

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。

Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op

A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.

本地运行的大模型聚合网关，GUI桌面端app，零代码部署，把Coding Plan、大模型 API 额度聚合成一个虚拟 Plan，一键接入 Claude Code、Claude Desktop App、OpenClaw、OpenCode 等工具。Bundle your scatt

Fully local vulnerability research pipeline - 14B code-specialized LLM reviews every source file exhaustively.

CCswitch的全面升级，专门优化codex体验。支持官方订阅和第三方模型混用，自动路由，支持v2subagent使用第三方模型

Clone a voice from a few minutes of audio and generate speech locally — Qwen3-TTS fine-tuning pipeline with CLI and web UI

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-c

Drop-in OpenAI-compatible API gateway for Qwen AI models. Use your Qwen account (chat.qwen.ai) as a free AI API provider in any OpenAI-compa

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

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

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

AI 厂商动态别挨家追：每天巡检 OpenAI、Claude、Gemini、DeepSeek、通义、Kimi 等的官方博客与更新页，生成可订阅的 RSS，英文原文逐段精译为中文，并附 70 家免费额度 / 限时活动总表（实时抓自官方页、带官方链接可复核）

Proxy API OpenAI-compatible que usa automação com Playwright para rotear requisições para modelos do Qwen com suporte a múltiplas contas, to

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by a

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

为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

A 4B decision model built for Korean.

🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools,

Hybrid rule-based and context-aware LLM evaluation system for Chinese-to-Japanese game localization QA.

ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verifi

Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memo

Your smart, reliable, and friendly personal AI assistant.

ComfyUI nodes for Strata: text, structured prompts, vision and managed local inference with GPU handoff. Publisher: t8star.

Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels in

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

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Tinybot is a lightweight personal AI Agent that is constantly evolving

一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

No longer developed. Use Speech Studio: https://github.com/timoncool/speech-studio. Portable Windows TTS — Higgs Audio v3 + AI text director

High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient to

Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Specul