Building local AI systems, LLM tools, RAG infrastructure, and MLX model deployments.
Highlights
- Pro
Pinned Loading
-
-
Self-Hosted-edge-server
Self-Hosted-edge-server PublicThis project is a self-hosted Retrieval-Augmented Generation (RAG) server built to run fully offline on a small x86 edge device such as the LattePanda 3 Delta.
Python
-
dograh
dograh PublicForked from dograh-hq/dograh
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
