musharna/jobd
by Various
Self-hostable GPU-aware job broker for your own machines, with native MCP/agent integration
MCP
musharna/jobd
Added 11 June 2026
Overview
jobd is a self-hostable job broker that manages GPU-aware workloads across your own machines. It uses a Python queue system and provides native MCP/agent integration for coordinating distributed tasks.
Best for
Best for
Developers needing a private, GPU-aware job broker that can plug into agent systems
Use cases
- Distribute GPU-intensive jobs across a cluster of local machines
- Integrate job queuing into agent workflows via MCP protocol
- Run batch processing tasks with dynamic resource awareness
Notes
jobd is a self-hostable job broker that manages GPU-aware workloads across your own machines. It uses a Python queue system and provides native MCP/agent integration for coordinating distributed tasks.
0 stars on GitHub. Last updated 2026-06-11. Licensed MIT.
Use cases
- Distribute GPU-intensive jobs across a cluster of local machines
- Integrate job queuing into agent workflows via MCP protocol
- Run batch processing tasks with dynamic resource awareness
Pros
- Self-hosted, keeping data and jobs on your own infrastructure
- GPU-aware scheduling for optimal resource utilization
- MCP integration enables easy agent-based orchestration
Cons
- No public star count suggests limited community adoption or validation
- Python-only codebase may restrict non-Python environments
- Requires manual setup and maintenance of the broker infrastructure
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Self-hosted, keeping data and jobs on your own infrastructure
- GPU-aware scheduling for optimal resource utilization
- MCP integration enables easy agent-based orchestration
Cons
- No public star count suggests limited community adoption or validation
- Python-only codebase may restrict non-Python environments
- Requires manual setup and maintenance of the broker infrastructure
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.