#3838th of 52 in Agent platforms
nexent
Generates agents from plain-language prompts, with memory, skills and MCP tools
- Stars
- 6.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
4,077 on 3 Apr 20266,106 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Nexent generates executable agents from a plain-language description instead of a visual flow builder. It bundles two-tier memory, progressively loaded skills, MCP tools, a knowledge base covering 20+ document formats, and A2A agent collaboration. Multi-tenancy with RBAC, agent versioning and a marketplace are included.
Who it is for: Teams self-hosting a multi-tenant agent platform with MCP and knowledge bases
Strengths
- Agents generated from a text prompt, no drag-and-drop orchestration needed
- Multi-tenancy, RBAC and agent version history with rollback
- Supports MCP tools and the A2A agent-to-agent protocol
- Offline image packages and Helm-based Kubernetes deployment documented
Weaknesses
- Heavy stack: Elasticsearch, PostgreSQL, Redis and MinIO; 8 GiB RAM minimum on Docker
- Prompt-only agent creation gives less explicit control than a visual builder
- Needs external model providers or endpoints; no bundled model serving documented
- Kubernetes minimum is 16 GiB RAM and 100 GiB disk
What it needs
- RAM ≥ 8 GB
- Docker + Compose
- Needs Docker 24+, Docker Compose v2+, Elasticsearch, PostgreSQL, Redis, MinIO, Kubernetes 1.24+ and Helm 3+ (optional)
- Models: OpenAI-compatible providers, LLM, Embedding, VLM, STT
Quick answers
Is nexent open source?
Yes. Its code is on GitHub under the MIT license.
Can you run nexent with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |