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...
inclusionAI/AEnvironment
AEnvironment is an environment platform for agentic reinforcement learning and agent development, built around the idea of treating everything as an environment. It extends the Model Context Protocol so that anything from a single tool function to a complex multi-agent system is reachable through a uniform Environment interface, with MCP as the transport for tool discovery and invocation. Inside Ant Group it serves as an environment layer integrated with the AReaL reinforcement learning framework and used for large-scale agentic RL training and agent service deployment. The Python API is context-manager based: code opens an Environment by name and version, calls list_tools to see what it offers, and call_tool to invoke one, which means environments can be registered, composed and swapped like building blocks. Because agents themselves can be published as environments, one agent can call another as if it were a tool, which supports multi-agent orchestration, hierarchical agent systems and adversarial testing. Compatibility with the OpenAI Agents SDK is stated, and the project aims to let benchmark integration, RL training and agent deployment share the same infrastructure. Built-in environments ship ready to run: TAU2 for benchmark-based RL experiments, a lightweight Mini Terminal with bash execution, and TerminalBench for Terminal Bench evaluation, with SWE-Bench also listed among supported benchmarks. Examples include a mini-program IDE where an agent uses MCP file, code execution and validation tools with live preview, and a TAU2 RL example that exposes a reward function and an episode runner for turn-by-turn agent execution under AReaL. An AEnv CLI manages instances and services, and a Claude Code deploy skill automates deployment across three workflows: local Docker build, an already-registered image, or a previously registered environment. Python 3.12 or newer is required. Apache 2.0 licensed.
https://github.com/inclusionAI/AEnvironment
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.