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.
- 6k stars
- 753 forks
- 283 open issues
- Language: Python
- License: MIT
- updated
Install
git clone https://github.com/ModelEngine-Group/nexent && cp nexent/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Editor's note
Nexent is a Python-based, zero-code agent-building platform that lets users describe an agent in plain language and receive a deployable, production-ready result without writing orchestration logic or configuring drag-and-drop workflows. It connects to any OpenAI-compatible LLM provider and covers the full model stack including embedding, vision (VLM), speech-to-text, and text-to-speech. Agents created in Nexent can communicate with one another through an Agent-to-Agent (A2A) protocol for distributed multi-agent workflows, and they draw on a two-tier layered memory system that persists context at both the user level and the user-agent level. A built-in knowledge base supports real-time ingestion and retrieval across more than 20 document formats with fine-grained access control and source citations. The platform integrates with the MCP tool ecosystem for plug-and-play extensions and supports multi-source internet search alongside private data retrieval. Deployment is handled via Docker Compose or Kubernetes Helm charts, making it suited to individual developers as well as enterprise teams needing high availability.
3 items in this repository
Create, refine, and optimize high-quality YAML prompts for AI assistants. Use when working with prompt templates, system prompts, agent prompts, or any prompt engineering tasks. Provides structure guidelines, template patterns, and quality standards for YAML-based prompts.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Subagents overview
What people ask about nexent
What is ModelEngine-Group/nexent?
ModelEngine-Group/nexent is subagents for the Claude AI ecosystem. 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. It has 6k GitHub stars and its last recorded update is dated 2026-10-23.
How do I install nexent?
You can install nexent by cloning the repository (https://github.com/ModelEngine-Group/nexent) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is ModelEngine-Group/nexent safe to use?
Our security agent has analyzed ModelEngine-Group/nexent and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains ModelEngine-Group/nexent?
ModelEngine-Group/nexent is maintained by ModelEngine-Group. The last recorded GitHub activity is dated 2026-10-23, with 283 open issues.
Are there alternatives to nexent?
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.