赛道情报 / 全球
本地大模型.
在自己设备上运行的模型与推理工具。
数据分类
存量红海
项目较密集，搜索需求未达到持续快速增长标准。切入前需要验证具体的用户迁移优势。
报告日期 · 方法版本 1.0.2 · 高 证据置信度
- 在公开的 GitHub 检索范围内，匹配到 847 个活跃项目。
- 关键词“local llm”有 104 个完整周，其中 0% 的周数据被报告为零。
- 匹配的活跃 GitHub 项目
- 847
- 搜索热度增速
- -73% · 最近 8 个完整周与此前 8 周对比
- 关键词与地区
- local llm · 全球
- 完整周观测数
- 104
判断依据
- 相邻两个 8 周窗口的搜索热度中位数下降 73%。
- 匹配到 847 个活跃仓库；公开的供给密集门槛为 50 个。
原始证据
GitHub 仓库搜索 · topic:local-llm fork:false archived:false stars:>=5 pushed:>=2026-03-19
采集于 2026-09-15T16:35:44.775Z
Google Trends 搜索热度 · 采集于 2026-09-15T16:26:01.539Z
主要仓库
| 仓库 | Star 数 | 简介 |
|---|---|---|
| HKUDS/nanobot | 48,187 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps |
| mozilla-ai/llamafile | 25,970 | Distribute and run LLMs with a single file. |
| LearningCircuit/local-deep-research | 9,094 | ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. |
| open-multi-agent/open-multi-agent | 6,925 | Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. |
| MakazhanAlpamys/Soup | 6,584 | Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
| dograh-hq/dograh | 5,654 | Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support. |
| maziyarpanahi/openmed | 5,324 | Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0 |
| vinta/pangu.js | 4,822 | Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment |
| langroid/langroid | 4,104 | Harness LLMs with Multi-Agent Programming |
| raullenchai/Rapid-MLX | 3,751 | The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider. |
结果的适用范围
- Google Trends 衡量相对搜索关注度，不能直接代表客户数、收入或付费意愿。
- 供给统计覆盖所选 GitHub 主题下的活跃仓库，不包含未标注主题的项目或闭源竞品。
搜索热度反映关注度，不能代表付费客户。分类门槛为公开的启发式规则，仍需实证校准。
