self-hosted

Agentic SDLC with local LLM's.

vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, /v1/responses with separated reasoning, via TheRock ROCm.

🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.

Universal memory layer for AI applications. Self-host in minutes. Open source.

AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices

Turn any NVIDIA GPU into a local AI platform. Inference + fine-tuning in your browser. One command to start, automatic clustering.

Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet

The Continuous Verification and Optimization layer for self-hosted LLMs

An AI-powered search engine to interact with documentation using RAG and local LLMs. Privately deployable with vector search and a modern frontend.

Persistent memory and identity protocol for AI systems with evidence-aware recall and inspectable memory.

Build your own local-first digital lifeform: an AI companion with memory, soul, multimodal perception, proactive dialogue, and auditable execution.

Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.

Self-hosted multimodal AI workspace — chat, vision QA, text-to-image, image-to-image in one conversation

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Containerized self-hosted REST API for vision classification, utilizing Hugging Face transformers.

GLM-5.2 QuantTrio (Unpruned ) on 4xDGX Spark (GB10): 327K-655K context or up to 5 concurrent agents, one receipe. TP4 + DCP + MTP

Complete setup guide for a 2-node NVIDIA DGX Spark cluster — distributed training, CUDA inference with EXO, NCCL tuning for Grace Blackwell, NVMe-TCP shared storage, and 200 Gb/s direct fabric networking.

AI-native NoSQL + vector database with built-in semantic search for RAG, AI agents & LLM memory — the async Python client. Self-hosted Pinecone alternative.

Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine — zero data sent to external services.

VS Code extension to connect to local LLM inference servers (Ollama, llama.cpp, LocalAI) via OpenAI API compatible endpoints.