Starred repositories
Onion Monero Blockchain Explorer
Local runner for Microsoft VibeVoice Realtime TTS Fully compatible with Open-Webui Plug and Play. Run the Colab notebook experience locally with uv package management.
A UI for the A2A protocol built with Next.js and Material UI
A statusline for Claude Code showing real-time usage limits and weekly tracking
A curated list of self-hostable LLM services
self-hosted local AI platform based on Ollama + Spring AI
My personal repository. Calculates my repositories, commits, stars, followers, and total lines of code contributed by me
LLM chat client managing a rolling context to allow for unlimited chat length
InfraMind: Fine-tuning toolkit for training SLMs on Infrastructure-as-Code using GRPO/DAPO. Achieves 97.3% accuracy on IaC generation.
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval
Terminal client for HTTP/GraphQL/gRPC with support for SSH tunnels, WebSockets, SSE, workflows, profiling, OpenAPI and response diffs.
Examples showing how to interact with the WoT-MCP server
WoT-MCP is a server that exposes WoT devices to AI assistants via MCP
# OpenQode Preview Edition > 🚀 **Professional AI Coding Assistant** - Combining OpenCode's TUI with Qwen's generous free tier
Open-source general AI agent powered by Claude Agent SDK — sandboxed code execution, in-browser VS Code, terminal, custom skills, MCP support, and multi-provider integration
40+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script, cutting the system prompt in half, using Gemini CLI as Claude Code's minion, and Cl…
Effortlessly run LLM backends, APIs, frontends, and services with one command.
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Proof-of-Concept Research Artifact: Un-concealing Llama 3.2 capabilities