Nexent
Open-source, zero-code platform for spinning up production-grade AI agents from a single natural-language prompt.
Pick Nexent if you want a self-hosted, MCP-native agent platform you can describe in plain language instead of wiring up in a canvas editor.
Skip it if you want a managed SaaS, a polished low-code UI, or a stable v1 API to build a production product on this quarter.
Nexent is an MIT-licensed agent development platform from ModelEngine-Group that turns a plain-language description into a working multi-agent system, complete with tools, memory, and a knowledge base. It's built around 'Harness Engineering' principles and the Model Context Protocol (MCP), so agents are wired with constraints, feedback loops, and control planes rather than left as a free-firing LLM. Out of the box it ships with a two-tier memory system, an A2A (agent-to-agent) collaboration protocol, multi-modal I/O (voice, text, image, files), and ingestion for 20+ document formats.
Where Nexent differs from drag-and-drop competitors like Dify or Flowise is that there's no canvas: you describe the agent you want and it generates the orchestration for you. It's OpenAI-compatible against any provider and covers LLM, embedding, VLM, STT, and TTS slots, including Chinese domestic models, which makes it interesting for teams that need to swap backends. Self-hosted via Docker or Kubernetes, with multi-tenancy, RBAC, agent version management, and an agent marketplace aimed squarely at enterprise deployment.
It's open source with no managed-SaaS pricing page, so 'cost' is whatever your infra and model-API bills add up to. The project is active (5k+ stars, 200+ contributors, v2.0 shipped) but still young, and serious adopters should expect to operate it themselves.
Nexent is one of the more interesting open-source bets in the post-LangGraph agent wave: prompt-driven generation, MCP-native, and unapologetically aimed at enterprise self-hosters. It's not yet as battle-tested as Dify, but the Harness Engineering framing and the A2A/memory story are worth a serious look if you're building in-house.
— The AI Tool Bible editorial team
Pros
- ✅ MIT-licensed and fully self-hostable on Docker or Kubernetes
- ✅ Prompt-to-agent generation skips drag-and-drop canvas entirely
- ✅ Model-agnostic across LLM, embedding, vision, STT and TTS slots
- ✅ Built-in multi-tenancy, RBAC, A2A protocol, and agent marketplace
- ✅ Knowledge base ingests 20+ document formats out of the box
Cons
- ⚠️ Self-host only; no managed cloud offering to point at
- ⚠️ Young project (v2.0); APIs and abstractions still evolving
- ⚠️ Documentation is partly Chinese-first and uneven in English
Use cases
Explore related
Compare with similar tools
All in Agents →LangGraph
FeaturedStateful, graph-based agent orchestration from LangChain.
CrewAI
FeaturedPython framework for multi-agent orchestration.
Claude Agent SDK
Anthropic's official SDK for building autonomous Claude agents.
Manus
Generalist agent for research, code, and web tasks.
Devin
Cognition Labs' "autonomous software engineer" agent.
AutoGPT
Open-source platform for building autonomous AI agents.