ModelEngine-Group/nexent
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
What it solves
Nexent is a zero-code platform designed to simplify the creation of production-grade AI agents. It removes the need for complex orchestration or drag-and-drop interfaces, allowing users to generate executable agents using only natural language prompts.
How it works
The platform uses a "one prompt" approach to translate user requirements into functional agents. It integrates a comprehensive suite of tools, including a layered memory mechanism (user-level and user-agent-level) for persistent context, a progressive skill disclosure system to optimize the context window, and an MCP tool ecosystem for plug-and-play extensions. It also supports Agent-to-Agent (A2A) protocols for multi-agent collaboration and distributed workflows.
Who it’s for
Nexent is aimed at individuals, small teams, and enterprises who want to deploy AI agents without writing code or managing complex orchestration logic, with support for both Docker and Kubernetes for flexible deployment options.
Highlights
- Zero-Code Generation: Create agents instantly from natural language descriptions.
- A2A Collaboration: Seamless cooperation between multiple agents via a dedicated protocol.
- Layered Memory: Persistent context across conversations using a two-tier memory system.
- Personal Knowledge Base: Real-time import and retrieval for over 20 document formats with precise citations.
- Multimodal Interaction: Support for voice, text, images, and files.
- Multi-Model Integration: OpenAI-compatible integration with LLMs, VLMs, STT, and TTS providers.
- Agent Marketplace: Access to official and community-curated agents for one-click installation.