# 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.

Repository: https://github.com/ModelEngine-Group/nexent
Canonical: https://ross.abutalabs.com/products/nexent
Homepage: http://modelengine-group.github.io/nexent/
Language: Python
License: MIT
License Family: permissive
Topics: agent, agentic-ai, agentic-framework, agentic-rag, agentic-workflow, ai, llm, rag, harness, harness-engineering, mcp, multi-agent
Last push: 2026-08-26T11:34:02+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 35
- inputs: {"age_days": 492, "days_push": 7, "days_rel": 28, "gap_med": 7, "n_releases_24m": 50}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5839, forks 723 (observed 2026-08-28T04:09:31.530195+00:00)

## What it is
Nexent is a zero-code, self-hosted platform for auto-generating production-grade AI agents from natural language prompts, built on Harness Engineering principles. It unifies tools, skills, memory, and multi-agent orchestration with built-in constraints, feedback loops, and control planes, deployable via Docker or Kubernetes.

## Use cases
- build ai agents without writing code
- create multi-agent workflows from a single prompt
- self-host an ai agent platform on docker or kubernetes
- build rag-powered chatbots with tools and memory
- orchestrate llm agents with mcp tools
- deploy production-grade agentic ai in private infrastructure

## When to choose
- you want to build AI agents purely through natural language without drag-and-drop editors or code
- you need self-hosted deployment with Docker or Kubernetes on your own infrastructure
- you need unified agent capabilities including tools, skills, memory, and multi-agent orchestration out of the box
- you want built-in guardrails, feedback loops, and control planes for production agents

## When to avoid
- you need a lightweight Python library to embed agent logic in your own codebase rather than a full platform
- you require fine-grained programmatic control over agent internals that a zero-code abstraction hides
- you lack the minimum resources (4 cores, 8 GiB RAM, 40 GiB disk) to run the full stack
- you prefer lightweight frameworks like LangChain or a simple MCP client over an opinionated all-in-one platform

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, mcp, llm-inference, chatbot, self-hosted, workflow-automation
- domain: large-language-models, artificial-intelligence, self-hosted
- platform: self-hosted, python, windows
- tags: zero-code, harness-engineering, multi-agent, agentic-rag, no-code-platform, agent-orchestration, ai-agents, retrieval-augmented-generation, automation, docker, kubernetes, linux, macos

## Member repositories
- ModelEngine-Group/nexent (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:31.530195+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:03.035399+00:00, confidence not recorded.
  - readme: https://github.com/ModelEngine-Group/nexent (fetched 2026-08-28T04:09:31.530195+00:00, sha 77104bfcc600)
  - homepage: http://modelengine-group.github.io/nexent/ (fetched 2026-08-29T08:47:23.787467+00:00, sha c1be661d7c73)
- Data as of 2026-08-30T08:39:29.467469+00:00.