Web appAI and agent development
unsloth
Run, fine-tune, and export open models on your own hardware.
- Stars
- 68,200
- Forks
- 6,136
- Updated
- Updated Jul 14, 2026
Apache-2.0
Run, fine-tune, and export open models on your own hardware.
Unsloth combines a web interface and a code-based package for downloading, running, training, and exporting text, audio, vision, and embedding models. It also supports dataset preparation, training monitoring, local inference endpoints, and formats such as GGUF and safetensors. Availability varies by hardware: some CPU setups are limited to chat and data workflows, while training support depends on the platform and accelerator.
Resource types
Use cases
Platforms
Design agent workflows visually and expose them as APIs or MCP tools.
Build LLM apps with visual workflows, RAG, agents, and APIs.
Operating systems
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Build and self-host AI agents through a visual workflow editor.
Compare agent skills, MCP servers, and tools by quality, security, and trends.