by TadMSTR · Agent Tool · ★ 26
homelab-agent A platform for running a team of AI agents on a single server. Five agents — sysadmin, developer, researcher, writer, security — work semi-autonomously or fully unattended, coordinating through a task queue and communicating over Matrix. Each agent gets a scoped tool surface controlled by a manifest, persistent multi-tier memory backed by open-source infrastructure (Milvus for vector search, OpenSearch for full-text, Neo4j for knowledge graph), and an event ledger that tracks every cross-agent handoff. The agents build the platform.
| Stars | 26 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.9675021106206/100 |
| Last Updated | 2026-06-26 |
| Created | 2026-03-08 |
| Platforms | claude-code, docker, python |
| Est. Tokens | ~15k |
Explore other popular agent tool tools:
homelab-agent is Reference build for a self-hosted AI platform — persistent context, multi-agent workflows, and purpose-built agents on your own hardware. It is categorized as a Agent Tool with 26 GitHub stars.
homelab-agent is primarily written in Python. It covers topics such as ai, claude, claude-code.
You can find installation instructions and usage details in the homelab-agent GitHub repository at github.com/TadMSTR/homelab-agent. The project has 26 stars and 3 forks, indicating an active community.
homelab-agent is released under the MIT license, making it free to use and modify according to the license terms.