affaan-m/ECC
ECC is a comprehensive agent harness performance optimization system providing skills, instincts, memory, security, and research-first development for various AI agent harnesses including Claude Co...
EvoMap/evolver
Evolver is an innovative self-evolution engine designed for AI agents, leveraging the Gene-Expression Programming (GEP) protocol to facilitate auditable and reusable agent intelligence. It addresses the common challenge of ad hoc prompt engineering by converting agent experiences into structured, evolvable assets known as Genes and Capsules, rather than relying on unstructured prompts or documentation. The core of Evolver's functionality is to enable AI agents to learn and adapt over time, with a focus on experience-driven test-time evolution. It provides a mechanism for audit trails, allowing for transparent tracking of an agent's evolutionary path. The project is backed by research demonstrating that a compact Gene representation significantly outperforms documentation-oriented 'Skill' packages in terms of performance and robustness under structural perturbation, serving as a superior carrier for iterative experience accumulation. Evolver operates as an offline-first CLI tool for local agent evolution, but can optionally connect to the EvoMap network for shared intelligence, skill libraries, and collaborative evolution. It integrates with various agent runtimes, offering hooks for platforms like Cursor, and emphasizes prompt governance. The system requires Node.js and Git, using Git for version control, rollback capabilities, and blast radius calculations, ensuring that evolution is both powerful and controlled. While initially open-source, Evolver is transitioning to a source-available model to protect its intellectual integrity, maintaining its commitment to delivering advanced agent self-evolution capabilities.
https://github.com/EvoMap/evolver
Also in Agent Platforms
open-webui/open-webui
Open WebUI is a self-hosted, extensible AI platform supporting multiple LLM runners and OpenAI-compatible APIs with advanced features like Retrieval Augmented Generation, model building, and offline deployment.
Mintplex-Labs/anything-llm
AnythingLLM is an all-in-one AI application with full MCP compatibility that enables intelligent chat interactions with documents using various LLMs, multi-user support, and no-code AI agent building capabilities.
aaif-goose/goose
goose is an open-source, extensible AI agent providing desktop, CLI, and API interfaces for code, workflows, and general tasks, featuring broad LLM provider compatibility and connection to MCP exte...
HKUDS/nanobot
nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework in Python, offering a WebUI, tools, memory, MCP integration, multi-agent workflows, automation, and chat app co...
zhayujie/CowAgent
CowAgent is an open-source, multi-model AI assistant and Agent Harness designed for autonomous task planning, tool execution, and continuous learning, featuring native Model Context Protocol (MCP) ...
sickn33/agentic-awesome-skills
This project provides an installable GitHub library and npm installer for over 1,900 agentic skills and playbooks, designed to enhance AI coding assistants like Claude Code, Gemini CLI, Cursor, and...
danny-avila/LibreChat
LibreChat is an open-source enhanced ChatGPT clone that integrates multiple AI models and supports the Model Context Protocol (MCP) for advanced AI assistant features including no-code agents, secure code execution, multimodal interactions, and customizable conversation management.