Explore the directory

senpi is an experimental, opinionated fork of pi-mono that rebrands its coding-agent runtime and adds a curated set of built-in extensions, serving as the coding-agent runtime behind the Dori AI assistant.

• Coding agents
• Agent frameworks

A hands-on, open-source guide to building practical AI applications with open-source models, covering model selection, inference, fine-tuning, evaluation, and retrieval-augmented and agent workflows.

• Tutorials

A persistent, embedded graph database for Python that stores data as a triple store and is queried through a chainable Python query language called Torque, with no server to run.

• Databases

A pytest-native framework for writing and running safety and security tests against agentic AI applications, covering adversarial attacks, benign failures, and a range of harm categories with evaluation-driven assertions.

• Testing
• Security

A multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI that coordinates specialized agent personas through a structured software development lifecycle, from research to a merged pull request, with mandatory review gates and test-driven development.

• Agent frameworks
• CI/CD

A linter and language server for AI agent configuration files, validating CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP configs against hundreds of rules, with autofixes and editor integrations.

• Code quality

A terminal UI that finds locally installed LLM inference backends and model files, then lets a user launch and monitor local model servers without writing config files or CLI flags.

• Inference

A Windows desktop app that shows a DeepSeek API account's balance, monthly spend, and token usage by model, adapted from a macOS menu-bar tool of the same purpose.

• Desktop utilities

A self-hostable, local-first platform that compiles natural-language descriptions into working AI agents, complete with tools, MCP connectors, a RAG knowledge base, and multi-agent teams, then lets users edit them by talking to them.

• Agent frameworks

A native Swift engine that streams a 125-billion-parameter mixture-of-experts model from SSD and caches its busiest experts in memory, so it can run on Apple Silicon Macs that cannot hold the whole model in RAM.

• Inference

A zero-dependency C implementation for running local LLM inference with lossless KV-cache compression, letting full documents fit in context on consumer hardware instead of relying on chunked retrieval.

• Inference

An OpenCode plugin and framework for coordinating specialist AI agents, repository knowledge, safe Git workflows, and model routing across software, infrastructure, and business tasks, from intent through to a verified outcome.

• Agent frameworks
• CI/CD

An admin panel for the RuoYi-AI platform, used to manage AI models, knowledge bases, and workflow orchestration alongside a separate backend and user-facing frontend.

• Backend

A demo implementation of Vision RAG, which embeds PDF pages directly as images with a vision-language model instead of chunking text, then retrieves and answers over the best-matching pages.

• RAG

A reinforcement fine-tuning framework for large language and vision-language models, covering reinforcement learning with verifiable rewards, RLHF, and reward-model-driven policy optimization on top of PyTorch distributed training and rollout backends.

• Models

A platform-agnostic declarative language for describing agents and structured agentic workflows, defining the components, properties, and semantics needed to compose multi-agent systems.

• Agent frameworks

qr.dart is a Dart library for generating QR codes, supporting versions 1 through 40, adjustable error-correction levels, and Extended Channel Interpretation for multi-part or non-ASCII payloads.

• Libraries

An Agent Plugins package that adds Windows app development skills to GitHub Copilot, Claude Code, and OpenAI Codex, covering the full WinUI 3 and Windows App SDK workflow from scaffolding to shipping.

• Agent skills
• Desktop

A self-learning memory plugin for AI coding agents that turns finished work into structured, searchable memory and injects only the evidence relevant to the current query, with native hooks for Codex, Claude Code, and OpenClaw.

• Agent memory

ds4-on-spark packages a Blackwell-CUDA performance fork of the ds4 engine to serve DeepSeek-V4-Flash entirely on-device on an NVIDIA DGX Spark, with large prefill and decode speedups over the upstream engine.

• Inference

A collection of example projects and reference architectures showing how to build AI agent workflows with Swytchcode, including LangGraph, OpenAI Agents SDK, and Vercel AI SDK integrations for tasks like onboarding, payments, and issue triage.

• Tutorials

An open-source, MCP-connected library of tax guides for AI agents, each reviewed and credited to a named accountant, covering over 200 jurisdictions.

• MCP servers

A collection of Model Context Protocol servers, clients, and developer tools from IBM that connect IBM products such as MQ, Business Automation Workflow, and Decision Services to AI agents and applications.

• MCP servers

Course materials and code for a Chinese-language course covering Python, LangChain, LangGraph, and AI-assisted coding, published as a documentation site alongside video lectures.

• Tutorials