<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>开源 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%BC%80%E6%BA%90/</link><description>Recent content in 开源 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 16 Jul 2026 11:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BC%80%E6%BA%90/index.xml" rel="self" type="application/rss+xml"/><item><title>开源智能体生态2026：框架、工具与平台全景图</title><link>https://guijiagi.com/posts/b1-3ebc88c1/</link><pubDate>Thu, 16 Jul 2026 11:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/b1-3ebc88c1/</guid><description>2026年开源智能体生态全景梳理，涵盖Agent框架、开发工具、部署平台与社区发展现状</description></item><item><title>开源Agent框架全景图2026</title><link>https://guijiagi.com/posts/article-19/</link><pubDate>Sun, 12 Jul 2026 20:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-19/</guid><description>系统盘点2026年开源Agent生态的主要框架和工具，为开发者提供选型参考和技术地图</description></item><item><title>开源Agent框架全景图2026</title><link>https://guijiagi.com/posts/b2-f0812155/</link><pubDate>Sun, 12 Jul 2026 20:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-f0812155/</guid><description>系统盘点2026年开源Agent生态的主要框架和工具，为开发者提供选型参考和技术地图</description></item><item><title>LangChain 2026演进：从框架到平台</title><link>https://guijiagi.com/posts/langchain-2026-evolution/</link><pubDate>Thu, 02 Jul 2026 11:27:00 +0800</pubDate><guid>https://guijiagi.com/posts/langchain-2026-evolution/</guid><description>2026年LangChain生态系统演进全景，从LLM框架到AI应用平台</description></item><item><title>vLLM 2026社区进展：高性能推理引擎的进化</title><link>https://guijiagi.com/posts/vllm-2026-community/</link><pubDate>Thu, 02 Jul 2026 11:26:00 +0800</pubDate><guid>https://guijiagi.com/posts/vllm-2026-community/</guid><description>2026年vLLM社区发展动态与技术创新，LLM推理引擎的标杆</description></item><item><title>Ollama 2026生态系统：本地LLM的最佳伙伴</title><link>https://guijiagi.com/posts/ollama-2026-ecosystem/</link><pubDate>Thu, 02 Jul 2026 11:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/ollama-2026-ecosystem/</guid><description>2026年Ollama生态系统全面解析，从模型管理到生产部署</description></item><item><title>2026开源vs闭源：差距还在缩小吗</title><link>https://guijiagi.com/posts/ai-open-source-vs-closed-2026/</link><pubDate>Thu, 02 Jul 2026 10:23:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-open-source-vs-closed-2026/</guid><description>开源与闭源大模型的性能差距在2026年是否继续缩小？</description></item><item><title>通义千问3企业版：开源生态布局</title><link>https://guijiagi.com/posts/alibaba-qwen3-enterprise/</link><pubDate>Thu, 02 Jul 2026 10:13:00 +0800</pubDate><guid>https://guijiagi.com/posts/alibaba-qwen3-enterprise/</guid><description>阿里巴巴发布通义千问3企业版，全面布局开源AI生态</description></item><item><title>DeepSeek V4完整评测：国产大模型的崛起</title><link>https://guijiagi.com/posts/deepseek-v4-full-evaluation/</link><pubDate>Tue, 30 Jun 2026 10:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/deepseek-v4-full-evaluation/</guid><description>全面评测DeepSeek V4在推理、代码、中文理解等维度的表现，分析国产大模型的突破</description></item><item><title>AI开源vs闭源2026：谁在赢谁在输</title><link>https://guijiagi.com/posts/ai-open-vs-closed-2026/</link><pubDate>Tue, 30 Jun 2026 10:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-open-vs-closed-2026/</guid><description>2026年AI开源与闭源模型竞争格局深度分析：性能差距、商业生态与未来走向</description></item><item><title>Dify 2026：开源AI应用开发平台的崛起</title><link>https://guijiagi.com/posts/dify-2026-open-source-ai-platform-rise/</link><pubDate>Tue, 30 Jun 2026 09:50:00 +0800</pubDate><guid>https://guijiagi.com/posts/dify-2026-open-source-ai-platform-rise/</guid><description>深入评测Dify 2026作为开源AI应用开发平台的核心能力、架构演进与生产实践</description></item><item><title>开源vs闭源大模型：2026年到底谁赢了</title><link>https://guijiagi.com/posts/open-vs-closed-llm-2026/</link><pubDate>Tue, 30 Jun 2026 09:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/open-vs-closed-llm-2026/</guid><description>2026年中期，开源与闭源大模型的路线之争终于有了阶段性答案。从性能差距到生态建设，从成本对比到安全考量，全面解析这场AI世纪之争</description></item><item><title>AutoGPT 2026：自主智能体的复兴与进化</title><link>https://guijiagi.com/posts/autogpt-2026-revival/</link><pubDate>Sun, 28 Jun 2026 11:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogpt-2026-revival/</guid><description>探索 AutoGPT 2026 年的重大架构升级，从自主目标执行到安全约束框架的全面进化</description></item><item><title>开源 vs 闭源 2026 终局：谁赢了</title><link>https://guijiagi.com/posts/open-source-vs-closed-source-2026-who-won/</link><pubDate>Sun, 28 Jun 2026 10:13:00 +0800</pubDate><guid>https://guijiagi.com/posts/open-source-vs-closed-source-2026-who-won/</guid><description>2026 年开源与闭源大模型的终局对决：技术性能、商业模式、生态影响力全方位对比分析</description></item><item><title>Gemma 3 评测：谷歌开源轻量模型的定位</title><link>https://guijiagi.com/posts/gemma3-review-google-open-lightweight-model/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/gemma3-review-google-open-lightweight-model/</guid><description>Google Gemma 3系列轻量开源模型深度评测：能力分析、场景适配与竞品对比</description></item><item><title>2026开源Agent框架横评</title><link>https://guijiagi.com/posts/agent-opensource-comparison-2026/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-opensource-comparison-2026/</guid><description>2026开源Agent框架横评</description></item><item><title>2026开源大模型选型指南</title><link>https://guijiagi.com/posts/opensource-llm-selection-2026/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/opensource-llm-selection-2026/</guid><description>2026开源大模型选型指南</description></item><item><title>CrewAI多Agent开源方案</title><link>https://guijiagi.com/posts/crewai-multi-agent-opensource/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/crewai-multi-agent-opensource/</guid><description>CrewAI多Agent开源方案</description></item><item><title>RAGFlow开源RAG方案</title><link>https://guijiagi.com/posts/ragflow-opensource-rag/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/ragflow-opensource-rag/</guid><description>RAGFlow开源RAG方案</description></item><item><title>vLLM开源推理引擎</title><link>https://guijiagi.com/posts/vllm-opensource-inference/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/vllm-opensource-inference/</guid><description>vLLM开源推理引擎</description></item><item><title>开源 vs 闭源大模型：2026 终局之战</title><link>https://guijiagi.com/posts/open-source-vs-closed/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/open-source-vs-closed/</guid><description>2026 年开源与闭源大模型的全面对比，从性能追赶到生态之争，谁将赢得 AI 的未来</description></item><item><title>2026 本地 AI 技术栈：从模型到应用的完整方案</title><link>https://guijiagi.com/posts/local-ai-stack-2026/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/local-ai-stack-2026/</guid><description>技术栈选型、硬件需求、Docker Compose 编排、安全加固与维护策略，2026 本地 AI 全栈指南。</description></item><item><title>AI 开源 vs 闭源 2026：Llama/Qwen/DeepSeek 能追上 GPT-4 吗</title><link>https://guijiagi.com/posts/ai-open-source-vs-closed/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-open-source-vs-closed/</guid><description>开源模型全面追赶闭源：Llama 4/Qwen 3/DeepSeek V4与GPT-5/Claude 4的差距分析</description></item><item><title>Ollama 生产部署指南：本地 LLM 的最佳实践</title><link>https://guijiagi.com/posts/ollama-production-guide/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/ollama-production-guide/</guid><description>从架构原理到生产部署，全面覆盖 Ollama 的模型管理、API 兼容、GPU 配置、并发调优与监控方案。</description></item><item><title>OpenClaw 评测：个人 AI Agent 的开源实践</title><link>https://guijiagi.com/posts/openclaw-agent-review/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/openclaw-agent-review/</guid><description>OpenClaw 如何用 Skill 系统构建个人 AI Agent？多渠道集成、Memory/Heartbeat 记忆机制、Cron 定时调度——开源 Agent 框架的实战评测。</description></item><item><title>Langfuse 可观测性：开源的 LLM 监控方案</title><link>https://guijiagi.com/posts/langfuse-observability/</link><pubDate>Wed, 24 Jun 2026 16:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/langfuse-observability/</guid><description>深入解析 Langfuse 的 Tracing、Prompt 管理、A/B 测试功能及与 LangSmith 的对比</description></item><item><title>Google Gemma 模型指南：轻量级开源选择</title><link>https://guijiagi.com/posts/gemma-model-guide/</link><pubDate>Wed, 24 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/gemma-model-guide/</guid><description>全面解析 Google Gemma 2/3 系列架构、规格、多模态支持与部署方案。</description></item><item><title>DeepSeek V4 完整版发布：开源模型的新巅峰</title><link>https://guijiagi.com/posts/deepseek-v4-%E5%AE%8C%E6%95%B4%E7%89%88%E5%8F%91%E5%B8%83-%E5%BC%80%E6%BA%90%E6%A8%A1%E5%9E%8B%E7%9A%84%E6%96%B0%E5%B7%85%E5%B3%B0/</link><pubDate>Wed, 24 Jun 2026 00:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/deepseek-v4-%E5%AE%8C%E6%95%B4%E7%89%88%E5%8F%91%E5%B8%83-%E5%BC%80%E6%BA%90%E6%A8%A1%E5%9E%8B%E7%9A%84%E6%96%B0%E5%B7%85%E5%B3%B0/</guid><description>DeepSeek V4 完整版正式发布，MoE 架构+1M 上下文+多头潜在注意力，深度解析技术细节与实测表现</description></item><item><title>Qwen3.5 发布：阿里通义的全面进化</title><link>https://guijiagi.com/posts/qwen35-%E5%8F%91%E5%B8%83-%E9%98%BF%E9%87%8C%E9%80%9A%E4%B9%89%E7%9A%84%E5%85%A8%E9%9D%A2%E8%BF%9B%E5%8C%96/</link><pubDate>Tue, 23 Jun 2026 00:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/qwen35-%E5%8F%91%E5%B8%83-%E9%98%BF%E9%87%8C%E9%80%9A%E4%B9%89%E7%9A%84%E5%85%A8%E9%9D%A2%E8%BF%9B%E5%8C%96/</guid><description>阿里发布 Qwen3.5 系列，涵盖 0.8B 到 397B 六个尺寸，深度解析其 MoE 架构优化与中文能力突破</description></item><item><title>Llama 4 系列全面评测：Meta 的开源反击</title><link>https://guijiagi.com/posts/llama-4-%E7%B3%BB%E5%88%97%E5%85%A8%E9%9D%A2%E8%AF%84%E6%B5%8B-meta-%E7%9A%84%E5%BC%80%E6%BA%90%E5%8F%8D%E5%87%BB/</link><pubDate>Mon, 22 Jun 2026 00:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llama-4-%E7%B3%BB%E5%88%97%E5%85%A8%E9%9D%A2%E8%AF%84%E6%B5%8B-meta-%E7%9A%84%E5%BC%80%E6%BA%90%E5%8F%8D%E5%87%BB/</guid><description>Meta 发布 Llama 4 系列（Scout/Maverick/Behemoth），全面评测其性能、部署成本与社区生态，分析是否值得从 Llama 3 升级</description></item></channel></rss>