Shubhamsaboo/awesome-llm-apps
A curated collection of impressive LLM-powered AI applications featuring RAG, AI Agents, Multi-agent Teams, and open-source models from leading AI providers like OpenAI, Anthropic, and Google Gemini.
Awesome AI Agents › AI Agent Ecosystems
Evolver is an open-source, GEP-powered (Genetic Expression Programming) self-evolution engine designed for AI agents. It aims to transform ad-hoc prompt engineering into auditable and reusable evolution assets by encoding agent experience as 'Genes' and 'Capsules' rather than traditional skill documentation or prompts. The project emphasizes a "protocol-constrained evolution" approach, providing an audit trail for agent behavior changes. Key features include a CLI for a quick start, allowing users to evolve agents within any Git-initialized project directory. It supports single evolution runs, review modes, and continuous looping as a background daemon. Evolver selects Genes and Capsules from its asset pool based on logs and signals, generating GEP prompts as artifacts. It also integrates with the broader EvoMap network, which facilitates validated collaboration, skill sharing, and evolution leaderboards among AI agents. The project offers pathways for both end-users wishing to evolve an agent and contributors looking to hack on the engine. The underlying theory is detailed in a research paper, "From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution," which highlights the efficacy of Gene representation over documentation-oriented Skill packages for iterative experience accumulation and robustness. Evolver is built on Node.js (version 18 or higher) and leverages Git for rollback, blast radius calculation, and solidifying changes, ensuring version control and traceability for its evolutionary processes. Future releases will transition to a source-available model to protect the integrity of the work while maintaining commitment to enhancing agent self-evolution capabilities.
https://github.com/EvoMap/evolver
A curated collection of impressive LLM-powered AI applications featuring RAG, AI Agents, Multi-agent Teams, and open-source models from leading AI providers like OpenAI, Anthropic, and Google Gemini.
LobeHub is a platform that enables users to find, build, and collaborate with AI agent teammates that evolve with them, facilitating multi-agent collaboration and transforming productivity through AI-driven workspaces.
MetaGPT is a multi-agent AI framework that simulates a software company by assigning GPT-based roles to collaboratively automate software development from natural language requirements.
This repository provides best practices and implementations for leveraging Claude AI's agentic engineering features, including subagents, commands, skills, workflows, and memory.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows.
CrewAI is a fast, flexible Python framework for orchestrating autonomous, role-playing AI agents that collaborate to solve complex tasks, offering both high-level simplicity and low-level control for enterprise-grade AI automation.
A library of Agent Skills markdown files giving Claude Code, Codex, Cursor and other coding agents marketing know-how: CRO, copywriting, SEO, paid ads, analytics and growth engineering.
nanobot is an open-source, lightweight personal AI agent, providing a WebUI, chat channels, tools, memory, and model routing for long-running workflows and automation.