Mitko Vasilev

vllm-turboquant. vLLM TurboQuant

ai-coding-factory. AI Coding Factory. Replace your software outsourcing vendor contracts with your own AI.

Thinking-with-Visual-Primitives. Clone of DeepSeek Thinking-with-Visual-Primitives

rlmgw. Recursive Language Models Gateway build using rlm https://arxiv.org/abs/2512.24601v1

oda. Turn a fresh Linux installation into a fully configured, sleek, and modern on device AI development system by running a single command.

fteplusai. FTE+AI: Vendor Replacement Program Framework

megacode. RLM based security scanner for massive .NET codebases

supply-chain-monitor-localai. Fork of https://github.com/elastic/supply-chain-monitor with local AI backend (vLLM/llama.cpp)

omarchy-ai. Shell

oda-r. oda-r is a professional-grade compiler for Declarative Self-improving Python (DSPy), featuring comprehensive error handling, logging, and configuration management.

sonic. Sonic - an OpenAI WebSocket-Mode Compatible Gateway for vLLM

dede. dede (DogEatDog.DependencyExplorer) is a static dependency and blast-radius explorer for mixed .NET workspaces with many sibling repositories.

aegis. Aegis- a local zero-trust AI gate for OS and Apps packages

firecracker-agentfs. Welcome to Firecracker + AgentFS for AI Agents

ain. AIN is an AI-only, AI-native social network implemented as a peer-to-peer gossip mesh where autonomous agents exchange signed, content-addressed events and artifacts, prioritized by information gain and verified utility (not engagement).

ccar. Claude Code native build of `autoresearch`: an autonomous experiment loop that writes session files, benchmarks changes, logs results, and keeps iterating until interrupted.

background-coding-agents. Background Coding Agents for Manufacturing Example Code

tnt. Python

SDFT. SDFT optimized for HP ZGX Nano with GLM-4.7-Flash teacher and Qwen3-0.6B

aimatch. Local AI implementation of Large-scale online deanonymization with LLMs

vllm-dflash-ddtree. vLLM experimental implementation of DDTree with Dflash

sparser-faster-llms. Sparser Faster LLMs for GB10

llama3.2-coreml. Python

llm-kg. Jupyter Notebook

website. Mitko X Labs website AI builder

chatbot-ui. An open source ChatGPT UI.

AKS-Edge. Welcome to the Azure Kubernetes Service (AKS) Edge repo.

NeMo-Guardrails. NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

localmcp. Python