Explore the directory

A sample Azure solution that deploys a web-based chat application backed by Microsoft Foundry's Agent Service, using file search over uploaded documents for cited, retrieval-grounded answers with built-in monitoring.

• Tutorials

A Claude/Codex skill that configures DeepSeek as a native sub-agent inside a desktop coding app, letting the primary agent delegate text-only coding tasks to a chosen DeepSeek model using an official DeepSeek API key.

• Agent skills

An AI coding assistant platform built on Cloudflare Workers and Durable Objects, giving teams persistent coding workspaces with connected data, deployable applications, and organization-level administration.

• Coding agents

A community-maintained guide to OpenCode, the open-source terminal AI coding agent, covering setup, custom commands, skills, plugins, MCP integrations, and headless CI use.

• Books

A local-first observability tool that reads Claude Code and Codex session transcripts to show token usage, cache performance, model choice, and cost across every machine a developer connects to a self-hosted team hub.

• Coding agents
• AI evals

Magento Coding Standard is a set of PHP_CodeSniffer rules that check Magento 2 code against Magento's coding conventions, usable via Composer in a Magento project or as a standalone tool.

• Code quality

A local dashboard for inspecting and editing the configuration of multiple AI coding harnesses at once, including Claude Code, Codex CLI, OpenCode, and DeepSeek Harness, covering memories, skills, agents, MCP servers, sessions, and security scanning.

• Coding agents

mlx-rs provides Rust bindings for Apple's MLX array framework, giving Rust programs access to MLX's lazy evaluation, dynamic computation graphs and unified memory for machine learning on Apple Silicon.

• Libraries

A VS Code extension that gives AI coding assistants live, tool-based access to an SAP ABAP system, letting them read real code, query tables, run tests, and debug alongside a full manual ABAP development workflow.

• Editors

A framework that automatically selects the best text-chunking method for each document in a retrieval-augmented generation pipeline, using intrinsic quality metrics instead of one fixed strategy for every document.

• RAG

Keystone is a clinical decision-evidence benchmark, built on HealthBench, that tests whether a chat assistant's recommended action changes correctly when the one fact it depends on is removed, contradicted or altered.

• AI evals

A desktop AI coding chat application, forked from TOKENICODE, that focuses on using DeepSeek as a provider alongside Claude, with session history, skills, and configurable model routing.

• Coding agents

An open, compact language model series (4B and 1.7B parameters) tuned for coding, agentic tool use, and everyday tasks, with a native context window of up to one million tokens and broad hardware and framework support.

• Models

A research framework for in-context reinforcement learning that internalizes reusable skills into an agent's policy, evaluated on tasks such as ALFWorld and Search-QA.

• Models
• Papers

A stateful graph workflow framework for building complex, resumable AI agent systems in Rust, combining a LangGraph-style execution engine with optional native LLM integration.

• Agent frameworks

A local, automatic memory system for AI coding agents that captures relevant facts from conversations, resolves contradictions over time, and injects the right memories into later sessions, storing everything in a single local SQLite file.

• Agent memory

A library that wraps existing stdio-based MCP servers so they run as AWS Lambda functions, letting distributed or cloud applications reach them over short-lived HTTPS connections instead of a local child process.

• MCP servers
• Hosting

An Emacs package that adds as-you-type code completion from LLMs, supporting chat-based completion prompts and fill-in-the-middle completion across providers including OpenAI, Claude, Gemini, Ollama, Llama.cpp, and Codestral.

• Editors

An MCP toolkit that lets an AI coding agent inspect and drive a running Flutter app, reading state, tapping widgets, typing into forms, hot-reloading, and reading logs, and lets the app register its own tools back to the agent.

• MCP servers
• Mobile

A local-first, self-hosted retrieval-augmented question-answering system that indexes local documents into a vector database and answers questions through Ollama or an OpenAI-compatible model, with a built-in MCP server.

• RAG

A config-driven, multi-agent orchestration middleware for conversational AI that routes between more than a dozen LLM providers, coordinates business systems through APIs, and supports the MCP and Agent-to-Agent protocols with persistent memory.

• Agent frameworks

A single-binary terminal coding agent built natively around DeepSeek's API, with a built-in code graph for symbol-level navigation, local OCR for reading screenshots, and configurable working-mode methodologies.

• Coding agents

A curated, taxonomy-organized reading list of papers on system-aware KV-cache optimization for efficient large language model serving, accompanying an ACL 2026 survey.

• Curated lists
• Papers

This is a community-maintained Model Context Protocol server for Azure DevOps that lets AI assistants access and manage projects, work items, repositories, branches, pull requests and pipelines through a standardized protocol.

• MCP servers