asgeirtj/system_prompts_leaks
This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...
Awesome AI Agents › Prompt Libraries
agentcoinorg/evo.ninja
Evo.ninja is a versatile generalist agent designed to adapt dynamically to various tasks by selecting the most appropriate agent persona for the job. It operates through an execution loop that predicts the next best step, selects the best-fit agent persona, contextualizes chat history to focus on relevant information, and evaluates and executes the chosen agent's function to achieve the user's goal. This loop continues until the goal is met. The project features multiple specialized agent personas, including Synthesizer for analyzing and summarizing text files, Csv Analyst for extracting and deriving insights from CSV files, Researcher for internet searching and information gathering, and Developer for software architecture and development, particularly in Python. Evo.ninja can be run via a command-line interface (CLI) or through a user interface (UI) that relies on a Supabase database. The CLI allows users to specify goals, session names, timeouts, and debug options, with session workspaces created to manage files and logs. The UI setup requires Docker Desktop and involves running a local Supabase instance, configuring environment variables, and starting the UI server. The project encourages community engagement through Discord for support and discussions. It requires installation of Git, Node.js, Yarn, and NVM, and uses OpenAI and SERP API keys for functionality. Overall, Evo.ninja is a sophisticated AI agent framework that intelligently delegates tasks to specialized personas, making it a powerful tool for automating complex workflows involving text analysis, data processing, research, and software development.
https://github.com/agentcoinorg/evo.ninja
Also in Prompt Libraries
HKUDS/RAG-Anything
RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.
dzhng/deep-research
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
dottxt-ai/outlines
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
microsoft/RD-Agent
RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
arcee-ai/mergekit
mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
icip-cas/PPTAgent
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
serenakeyitan/awesome-notebookLM-prompts
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.