[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73195":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},73195,"LLocalSearch","nilsherzig\u002FLLocalSearch","nilsherzig","LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.","",null,"Go",5954,365,30,52,0,5,64.19,"Apache License 2.0",false,"main",true,[24,25],"llm","search-engine","2026-06-12 04:01:07","> [!WARNING]  \n> This version has not been under development for over a year. Im working on a rewrite \u002F relaunch within a private beta - to gather feedback without wasting everyones time by publishing incomplete software. Please contact me if youre interested to join.\n\n# LLocalSearch\n\n## What it is and what it does\n\nLLocalSearch is a wrapper around locally running `Large Language Models` (like ChatGTP, but a lot smaller and less \"smart\") which allows them to choose from a set of tools. These tools allow them to search the internet for current information about your question. This process is recursive, which means, that the running LLM can freely choose to use tools (even multiple times) based on the information its getting from you and other tool calls. \n\n[demo.webm](https:\u002F\u002Fgithub.com\u002Fnilsherzig\u002FLLocalSearch\u002Fassets\u002F72463901\u002Fe13e2531-05a8-40af-8551-965ed9d24eb4)\n\n### Why would I want to use this and not something from `xy`?\n\nThe long term plan, which OpenAI is [selling](https:\u002F\u002Fwww.adweek.com\u002Fmedia\u002Fopenai-preferred-publisher-program-deck\u002F) to big media houses:\n\n> Additionally, members of the program receive priority placement and “richer brand expression” in chat conversations, and their content benefits from more prominent link treatments. \n\nIf you dislike the idea of getting manipulated by the highest bidder, you might want to try some less discriminatory alternatives, like this project. \n\n### Features\n\n- 🕵‍♀ Completely local (no need for API keys) and thus a lot more privacy respecting\n- 💸 Runs on \"low end\" hardware (the demo video uses a 300€ GPU)\n- 🤓 Live logs and links in the answer allow you do get a better understanding about what the agent is doing and what information the answer is based on. Allowing for a great starting point to dive deeper into your research.\n- 🤔 Supports follow up questions\n- 📱 Mobile friendly design\n- 🌓 Dark and light mode\n\n\n## Road-map\n\n### I'm currently working on 👷\n\n#### Support for LLama3 🦙\n\nThe langchain library im using does not respect the LLama3 stop words, which results in LLama3 starting to hallucinate at the end of a turn. I have a working patch (checkout the experiments branch), but since im unsure if my way is the right way to solve this, im still waiting for a response from the  [langchaingo](https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo) team.\n\n#### Interface overhaul 🌟\n\nAn Interface overhaul, allowing for more flexible panels and more efficient use of space. \nInspired by the current layout of [Obsidian](https:\u002F\u002Fobsidian.md)\n\n#### Support for chat histories \u002F recent conversations 🕵‍♀\n\nStill needs a lot of work, like refactoring a lot of the internal data structures to allow for more better and more flexible ways to expand the functionality in the future without having to rewrite the whole data transmission and interface part again.\n\n\n### Planned (near future)\n\n#### User Accounts 🙆\n\nGroundwork for private information inside the rag chain, like uploading your own documents, or connecting LLocalSearch to services like Google Drive, or Confluence.\n\n#### Long term memory 🧠\n\nNot sure if there is a right way to implement this, but provide the main agent chain with information about the user, like preferences and having an extra Vector DB Namespace per user for persistent information.\n\n## Install Guide\n\n### Docker 🐳\n\n1. Clone the GitHub Repository\n\n```bash\ngit@github.com:nilsherzig\u002FLLocalSearch.git\ncd LLocalSearch\n```\n\n2. Create and edit an `.env` file, if you need to change some of the default settings. This is typically only needed if you have Ollama running on a different device or if you want to build a more complex setup (for more than your personal use f.ex.). Please read [Ollama Setup Guide](.\u002FOllama_Guide.md) if you struggle to get the Ollama connection running.\n\n```bash\ntouch .env\ncode .env # open file with vscode\nnvim .env # open file with neovim\n```\n\n3. Run the containers\n\n```bash\ndocker-compose up -d\n```\n\n","LLocalSearch是一个完全本地运行的搜索聚合器，利用链式大语言模型（LLM）来回答用户提出的问题。其核心功能包括通过递归方式使用工具集进行互联网信息检索，并向用户提供搜索过程及最终答案的透明视图，整个过程无需依赖OpenAI或Google等外部API密钥。该项目采用Go语言编写，具有隐私保护、低成本硬件支持以及友好的移动界面设计等特点。适用于对数据隐私有较高要求且希望避免商业内容偏见影响搜索结果的研究者和个人用户。尽管目前版本已停止开发超过一年，但作者正在筹备基于私人Beta测试的新版本以收集反馈并改进。",2,"2026-06-11 03:44:28","high_star"]