Bookmarks
Tag cloud
Picture wall
Daily
RSS Feed
  • RSS Feed
  • Daily Feed
  • Weekly Feed
  • Monthly Feed
Filters

Links per page

  • 20 links
  • 50 links
  • 100 links

Filters

Untagged links
page 1 / 2
36 results tagged llm  ✕   ✕
ob1ong/Llm-internal-monologue- https://github.com/ob1ong/Llm-internal-monologue-
Wed 04 Jun 2025 10:01:09 PM PDT archive.org

This project runs on a Raspberry Pi Zero and creates an AI-powered internal monologue by capturing photos, sending them to OpenAI's GPT-4o vision model, and speaking the result using gTTS and pygame.

Captures an image every few seconds using libcamera-still. Encodes the image and sends it to OpenAI with a reflective prompt. Converts the GPT-4o response to speech and plays it aloud. Works fully offline (except for OpenAI API calls).

ar images analysis art wearable llm python
kekePower/cognito-ai-search https://github.com/kekePower/cognito-ai-search
Wed 04 Jun 2025 03:34:00 AM PDT archive.org

Cognito AI Search offers a secure and private way to find information and get answers. It's designed for individuals who value their privacy and want more control over their digital footprint. This tool brings together the power of a local AI assistant and a private web search engine, all running on your own hardware, ensuring your data stays with you.

In an online world where tracking is common, Cognito AI Search provides an alternative. It allows you to explore the web and interact with artificial intelligence without concerns about your search history or personal data being collected or analyzed by third parties.

Uses local AI models like LLaMA or Mistral (via Ollama). Your conversations with the AI never leave your machine. What you ask and the responses you receive remain confidential. Because the AI runs locally, you can often get answers and assistance even without an active internet connection. You have the freedom to choose the AI model that best suits your needs and configure how it responds.

When you need to search the wider internet, Cognito AI Search uses a self-hosted instance of SearXNG. This is a powerful metasearch engine that fetches results from various sources without compromising your privacy. Your search queries are not logged or tied to your identity. Each search is a fresh start. Unlike many commercial search engines, Cognito AI Search doesn't build a profile on you, ensuring the results you see are not influenced by past behavior or targeted advertising. Get a broader perspective by seeing results from multiple search engines in one place.

typescript ai llm webapps search selfhosted
autokitteh/kittehub https://github.com/autokitteh/kittehub
Wed 28 May 2025 09:16:52 PM PDT archive.org

AutoKitteh projects: full-fledged solutions, composable templates, and demos of capabilities and features. Full-fledged, ready-to-use solutions for real-life use cases. Composable templates for interoperability between common services. Demonstrations of advanced system capabilities and features. Shows off integration of ChatGPT with Github and Google Sheets, text summary, AWS and Slack, processing the contents of files into SQLite databases, monitoring things until a condition is reached, and more.

exocortex python automation templates demos agents llm
murtaza-nasir/speakr https://github.com/murtaza-nasir/speakr
Tue 06 May 2025 07:51:17 PM PDT archive.org

Speakr is a personal, self-hosted web application designed for transcribing audio recordings (like meetings), generating concise summaries and titles, and interacting with the content through a chat interface. Keep all your meeting notes and insights securely on your own server. This includes self-hosting your own LLM models to do the heavy lifting, so you don't have to use an LLM service provider.

Upload audio files (MP3, WAV, M4A, etc.) via drag-and-drop or file selection. Transcription and summarization happen in the background without blocking the UI. Uses OpenAI-compatible Speech-to-Text (STT) APIs that you can connect to a self-hosted model (like Whisper). Generates concise titles and summaries using configurable LLMs via OpenAI-compatible APIs. Ask questions and interact with the transcription content using an AI model.

python webapps llm transcripts audio exocortex selfhosted audio
appcypher/awesome-mcp-servers https://github.com/appcypher/awesome-mcp-servers
Wed 16 Apr 2025 07:30:36 PM PDT archive.org

A curated list of awesome Model Context Protocol (MCP) servers. MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations. This list focuses on production-ready and experimental MCP servers that extend AI capabilities through file access, database connections, API integrations, and other contextual services.

awesome mcp ai llm clients tasks specializations automation workflows services
punkpeye/awesome-mcp-servers https://github.com/punkpeye/awesome-mcp-servers
Wed 16 Apr 2025 07:29:49 PM PDT archive.org

MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations. This list focuses on production-ready and experimental MCP servers that extend AI capabilities through file access, database connections, API integrations, and other contextual services.

awesome mcp ai llm clients tasks specializations automation workflows services
ollama/ollama-python https://github.com/ollama/ollama-python
Wed 16 Apr 2025 03:19:30 PM PDT archive.org

The Ollama Python library provides the easiest way to integrate Python 3.8+ projects with Ollama. The Ollama Python library's API is designed around the Ollama REST API.

python modules ai llm api exocortex betafork
elder-plinius/L1B3RT4S https://github.com/elder-plinius/L1B3RT4S
Wed 16 Apr 2025 01:16:07 PM PDT archive.org

A repository of jailbreaks and workarounds for popular LLM models.

jailbreaks prompts llm
Ghost X https://ghost-x.org/
Sun 13 Apr 2025 09:09:38 PM PDT archive.org

The Ghost X was developed with the goal of researching and developing artificial intelligence useful to humans.

The large language model was developed with goals including excellent multilingual support, superior knowledge capabilities and efficiency. The organization aims to develop products with openness to support the community and startups. Focus on small and medium sized models instead of giant ones but still ensure efficiency at low cost. The models are developed with the goal of optimal production and high performance. Easily deploy them yourself on your own computer, server, or anywhere with enterprise-level scalability.

Github: https://github.com/ghost-x-ai/ghost-7b-alpha

llm models
basicmachines-co/basic-memory https://github.com/basicmachines-co/basic-memory
Mon 24 Mar 2025 02:14:14 PM PDT archive.org

Basic Memory lets you build persistent knowledge through natural conversations with Large Language Models (LLMs) like Claude, while keeping everything in simple Markdown files on your computer. It uses the Model Context Protocol (MCP) to enable any compatible LLM to read and write to your local knowledge base.

AI assistants can load context from local files in a new conversation. Notes are saved locally as Markdown files in real time. No project knowledge or special prompting required.

Most LLM interactions are ephemeral - you ask a question, get an answer, and everything is forgotten. Each conversation starts fresh, without the context or knowledge from previous ones. Basic Memory addresses these problems with a simple approach: structured Markdown files that both humans and LLMs can read and write to. All knowledge stays in files you control. Both you and the LLM read and write to the same files. LLMs can follow links between topics. Indexed in a local SQLite database.

python llm ml memory markdown conversations archive graphs
TecharoHQ/anubis https://github.com/TecharoHQ/anubis
Mon 24 Mar 2025 01:50:33 PM PDT archive.org

Anubis weighs the soul of your connection using a sha256 proof-of-work challenge in order to protect upstream resources from scraper bots.

Installing and using this will likely result in your website not being indexed by some search engines. This is considered a feature of Anubis, not a bug.

This is a bit of a nuclear response, but AI scraper bots scraping so aggressively have forced my hand. I hate that I have to do this, but this is what we get for the modern Internet because bots don't conform to standards like robots.txt, even when they claim to.

In most cases, you should not need this and can probably get by using Cloudflare to protect a given origin. However, for circumstances where you can't or won't use Cloudflare, Anubis is there for you.

golang captcha llm hashing scraping
huggingface/smolagents https://github.com/huggingface/smolagents
Sun 16 Mar 2025 04:52:09 PM PDT archive.org

smolagents is a library that enables you to run powerful agents in a few lines of code. The logic for agents fits in about 1,000 lines of code. Our CodeAgent writes its actions in code (as opposed to "agents being used to write code"). To make it secure, we support executing in sandboxed environments via E2B or via Docker. Supports any LLM. It can be a local transformers or ollama model, one of many providers on the Hub, or any model from OpenAI, Anthropic and many others via our LiteLLM integration. Agents support text, vision, video, even audio inputs!

python ai llm agents framework modules exocortex
evilsocket/nerve https://github.com/evilsocket/nerve
Fri 14 Mar 2025 02:28:24 PM PDT archive.org

Nerve is an ADK (Agent Development Kit) designed to be a simple yet powerful platform for creating and executing LLM-based agents. Agents are simple YAML files that can use a set of built-in tools such as a bash shell, file system primitives and other things (like APIs).

(archived) https://www.evilsocket.net/2025/03/13/How-To-Write-An-Agent/

python llm agents exocortex yaml
FareedKhan-dev/all-rag-techniques https://github.com/FareedKhan-dev/all-rag-techniques
Wed 12 Mar 2025 01:58:39 PM PDT archive.org

This repository takes a clear, hands-on approach to Retrieval-Augmented Generation (RAG), breaking down advanced techniques into straightforward, understandable implementations. Instead of relying on frameworks like LangChain or FAISS, everything here is built using familiar Python libraries openai, numpy, matplotlib, and a few others.

The goal is simple: provide code that is readable, modifiable, and educational. By focusing on the fundamentals, this project helps demystify RAG and makes it easier to understand how it really works.

python ai llm poc rag
autokitteh/autokitteh https://github.com/autokitteh/autokitteh
Thu 27 Feb 2025 12:02:29 PM PST archive.org

AutoKitteh is a developer platform for workflow automation and orchestration. It is an easy-to-use, code-based alternative to no/low-code platforms (such as Zapier, Workato, Make.com, n8n) with unlimited flexibility. You write in vanilla Python, we make it durable. Once installed, AutoKitteh is a scalable "serverless" platform (with batteries included) for DevOps, FinOps, MLOps, SOAR, productivity tasks, critical backend business processes, and more.

Provides interfaces for building projects (workflows), deploying them, triggering the code with webhooks or schedulers, executing the code as durable workflows, and managing these workflows. All services are available via gRPC / HTTP. Has a CLI and a built-in MCP server as well.

golang python automation exocortex rest api rpc llm mcp
troed/summarize.sh https://codeberg.org/troed/summarize.sh
Sun 23 Feb 2025 09:46:58 PM PST archive.org

A bit of glue between components that is able to textually summarize videos and podcasts - offline. The script takes a URL as argument, downloads and extracts the audio, transcribes the spoken words to text and then finally prints a summary of the content. No external services are used by this script except for the initial audio download. Examples of URLs that work are Youtube videos and Apple podcasts, see the yt-dlp project for the full list.

This script doesn't do anything clever, it just makes use of the great work done by other projects. Since the purpose is to not have to sit through 8-12 minutes of someone explaining what should've just been a short blog post. The default model used is LLaMa-3 to support medium spec hardware. If you have a large system, Mixtral 8x7b is another great option with a much larger context window (= able to work with longer transcriptions).

The script saves transcriptions to a folder in the same directory, and if the same URL is later used again it will not re-download the audio and create a new transcription but use the existing one. This means it's possible to later use the conversational mode to ask questions on the content, even if not done the first time.

Relies upon a locally hosted LLM to do the heavy lifting so you don't have to ship the data off to another service. Entirely self hosted.

scripts utility cli transcripts llm video audio
Nepenthes https://zadzmo.org/code/nepenthes/
Sat 18 Jan 2025 08:48:42 PM PST archive.org

This is a tarpit intended to catch web crawlers. Specifically, it's targetting crawlers that scrape data for LLM's - but really, like the plants it is named after, it'll eat just about anything that finds it's way inside.

It works by generating an endless sequences of pages, each of which with dozens of links, that simply go back into a the tarpit. Pages are randomly generated, but in a deterministic way, causing them to appear to be flat files that never change. Intentional delay is added to prevent crawlers from bogging down your server, in addition to wasting their time. Lastly, optional Markov-babble can be added to the pages, to give the crawlers something to scrape up and train their LLMs on, hopefully accelerating model collapse.

WARNING: THIS IS DELIBERATELY MALICIOUS SOFTWARE INTENDED TO CAUSE HARMFUL ACTIVITY. DO NOT DEPLOY IF YOU AREN'T FULLY COMFORTABLE WITH WHAT YOU ARE DOING.

lua llm spiders tarpit random generator
ai-robots-txt/ai.robots.txt https://github.com/ai-robots-txt/ai.robots.txt
Wed 01 Jan 2025 05:05:19 PM PST archive.org

This is an open list of web crawlers associated with AI companies and the training of LLMs to block. We encourage you to contribute to and implement this list on your own site.

You can subscribe to updates the releases feed: https://github.com/ai-robots-txt/ai.robots.txt/releases.atom

If you just want to pull a robots.txt file: https://raw.githubusercontent.com/ai-robots-txt/ai.robots.txt/refs/heads/main/robots.txt

ai llm blocklists privacy
getomni-ai/zerox https://github.com/getomni-ai/zerox
Tue 22 Oct 2024 01:14:00 PM PDT archive.org

A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense! Uses gpt-4o-mini to look at and figure out what's in the images, but so far it doesn't seem to support self-hosted models.

The general logic:

  • Pass in a file (pdf, docx, image, etc.)
  • Convert that file into a series of images
  • Pass each image to GPT and ask nicely for Markdown
  • Aggregate the responses and return Markdown
python nodejs exocortex ocr ai llm documents
Fight Your Health Insurance Denial -- Use AI to Generate Your Health Insurance Appeal https://fighthealthinsurance.com/
Mon 02 Sep 2024 11:51:31 AM PDT archive.org

"Make your insurance company cry too!"

We'll help you to write an appeal to fight your health insurance denial. While an appeal is not always the first step in the health insurance appeal process we'll guide you through the options to fight back against health insurance denials. Almost all health plans are required to offer internal and external appeals and while they often make it confusing we can help.

Github: https://github.com/orgs/totallylegitco/repositories

ai llm insurance
page 1 / 2
6420 links, including 414 private
Shaarli - The personal, minimalist, super-fast, database free, bookmarking service by the Shaarli community - Theme by kalvn