由于 trendforge.devlive.top 访问受限,请切换到 trendforge.devlive.org 域名
ollama
话题找到数量
JetBrains/koog
Koog是官方Kotlin框架,用于在所有平台上构建和运行稳健、可扩展且满足生产就绪要求的AI智能体——从后端服务到Android与iOS、JVM乃至浏览器环境均可部署。该框架基于我们在AI产品领域的专业经验,针对复杂的LLM与人工智能问题提供了经过实践验证的解决方案。
nyldn/claude-octopus
面向Claude Code的多触手协调器——整合Codex CLI与Gemini CLI,通过智能上下文路由实现并行任务执行
raullenchai/Rapid-MLX
专为Apple Silicon打造的最快本地AI引擎。比Ollama快4.2倍,缓存TTFT仅0.08秒,100%工具调用。支持17种工具解析器、提示缓存、推理分离与云路由。可直接替代OpenAI,兼容Claude Code、Cursor、Aider。
PurpleDoubleD/locally-uncensored
即插即用的本地人工智能工作室:未经审查的聊天、图像和视频生成、编码代理。 Runs abliterated LLMs + ComfyUI 100% offline. One installer, no Docker, no cloud.
datawhalechina/handy-ollama
动手学Ollama,在CPU上玩转大模型部署,在线阅读地址:https://datawhalechina.github.io/handy-ollama/
techjarves/Portable-AI-USB
一款 100% 离线、完全便携、零痕迹的 AI(Ollama + Llama 3 + AnythingLLM),可在 Windows 和 Mac 上从 USB 驱动器原生运行。
carloslfu/slotstream
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
Muvon/octomind
Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.
aayushch/laya
Laya is an open-source, local-first AI notification command center that aggregates Slack, Gmail, GitHub, Jira, Notion, Outlook, Calendar (and more) notifications using local LLMs via Ollama and LM Studio. Supports cloud models via BYOK.
KenKaiii/gg-framework
The coding agent that gets more out of your AI subscription. Fastest and leanest of 20 agents tested, with unlimited local search of real open-source code.