Explore the directory

A single-binary local inference server for coding agents, written in Rust, that keeps a request's KV cache resident across turns so later turns in a long conversation start as fast as the first.

• Inference

Turns an Android phone into a private, local inference server, running Google's Gemma 4 models through LiteRT and exposing them over an OpenAI-compatible API on the local network.

• Inference

A local, single-user permission gateway that lets AI assistants operate developer-owned systems through scoped, credentialed connector actions instead of handing over raw credentials.

• MCP servers
• Security

A bilingual, Chinese-first hands-on course that teaches AI agent development from zero to full-stack deployment, covering more than ten agent frameworks across 23-plus chapters with runnable examples.

• Tutorials

An independent, type-safe async Rust SDK implementing the Agent2Agent (A2A) protocol's v1.0.1 spec across JSON-RPC, REST, WebSocket, and gRPC, for building interoperable AI agent clients and servers.

• Agent frameworks

A zero-dependency TypeScript implementation of Google's TurboQuant vector quantization algorithm that runs in both Node.js and browsers, for compressing embeddings used in search, retrieval-augmented generation and LLM key-value caches.

• RAG
• Libraries

A Python library and command-line tool that generates SQLModel model classes from CREATE TABLE statements, a SQLite file, or a Postgres or MySQL connection, optionally inferring relationships from foreign keys.

• Databases

A Dart code generator that regenerates class members such as copyWith, equality, hashCode and typed JSON inside the same file on every save, using team-owned Mustache templates instead of build_runner part files.

• CLI tools
• Languages

An editor-independent language server for HLSL shaders, built on DXC's IntelliSense API, providing compiler-accurate diagnostics, completion, hover, semantic colouring and shader compilation inspection for Visual Studio and VS Code.

• Editors

An on-premise, Docker-distributed face liveness detection (anti-spoofing) server SDK that a developer runs on their own infrastructure and calls over a local HTTP API to check whether a submitted face image is a real, live person.

• APIs
• Containers

A free Turkish-language reference book on SQL Server 2025 covering vector search, DiskANN indexing, and the SQL MCP Server, with code examples tested against a real instance and role-based reading paths for 11 kinds of readers.

• Databases
• Books

A Claude Code plugin that acts as a database expert: it designs schemas, audits them on separate design-and-integrity and performance-and-scale scores, and can plan safe migrations.

• Agent skills
• Databases

A VS Code extension that installs a curated open-source AI development stack on HP Z devices and automatically discovers them on the local network.

• Inference
• Editors

A production-grade Python framework for a team's own AI agent that lives inside chat platforms such as Feishu, with tiered persistent memory, a hook-driven architecture, and separated compute and storage.

• Agent frameworks
• Agent memory

An in-browser model manager for local, on-device AI that handles download progress, cache detection, and deduplication of concurrent model loads, with React hooks and a worker bridge, working out of the box with Transformers.js.

• Inference
• Libraries

A constitutional governance runtime for autonomous AI agents that enforces defined rules, verified agent identities, and bounded permissions, working with any agent framework and halting or escalating automatically on a violation.

• AI evals
• Security

A template repository for creating custom Model Context Protocol tools for the Unity game engine, letting a developer build and package their own Unity MCP tools as a distributable Unity package in about 30 minutes.

• MCP servers

A deterministic AI defense framework that filters and validates inputs and outputs for an autonomous agent, combining keyword and pattern detection, a self-learning adaptive ruleset, and optional multi-model cryptographic consensus for high-assurance verdicts.

• AI evals
• Security

A hybrid semantic search engine, built during an internship, that combines dense embedding search with sparse keyword matching, cross-encoder reranking, and Redis caching, served through a FastAPI backend.

• RAG
• Databases

A short, guided Google Colab walkthrough for trying retrieval-augmented generation using NVIDIA's NIM cloud API, which offers free large language model inference on a T4 GPU runtime.

• RAG
• Tutorials

A plugin for the pi coding agent that indexes and semantically searches a developer's own past coding sessions, working immediately with zero-configuration keyword search and adding hybrid semantic search once an embedding provider is configured.

• Agent skills
• Agent memory

The reference Java and Spring implementation of the Open Ingestion Standard, a vendor-neutral enterprise data-integration platform that orchestrates connectors, embedding, and vector search output using modern Java concurrency features.

• RAG
• Data engineering

An open-source native iOS, iPadOS, and macOS chat client, built with SwiftUI, that connects directly to a user's own LiteLLM, Ollama, or OpenAI-compatible server with no OpenClient-hosted proxy or subscription in between.

• Inference

A coding-agent workspace, forked from Kimi Code CLI, that hands off work to standing multi-agent departments rather than disposable sub-agents, available as a terminal CLI and TUI called Nori Code and an Electron desktop app called Nori Work.

• Coding agents