Explore the directory

A command-line coding agent built entirely in PHP on the Neuron AI framework, with interactive tool-call approval, multi-provider model support and Model Context Protocol integration.

• Coding agents

A local LLM runtime and orchestration layer, positioned as a drop-in Ollama replacement, that pulls models from Hugging Face, serves them, and offers a built-in dashboard, pipelines and structured output.

• Inference

A four-stage multi-agent pipeline, presented at AAAI 2026, that classifies lung adenocarcinoma nodules from CT images and reports through nodule detection, sizing, report generation and a multi-agent clinical debate.

• Models
• Papers

A set of agent skills that turn a directory of markdown notes into a self-updating knowledge base of tagged, backlinked notes and generated wikis, following Andrej Karpathy's llm-wiki pattern.

• Agent skills
• Agent memory

A recomputation-free key-value caching library for large language models that stitches independently precomputed document caches together at serving time with cheap positional realignment instead of recomputing tokens.

• Inference
• Libraries

A memory filter that judges each candidate memory against a query with one calibrated yes-or-no question, so an AI assistant retrieves memories that are actually relevant even when they are not phrased like the request.

• Agent memory
• RAG

An MCP server that gives Claude, Cursor and other MCP clients tools for Google Search Console: search analytics, keyword rankings, URL inspection, sitemap management and indexing health.

• MCP servers

A Rust port of the Python FastMCP framework for building Model Context Protocol servers, adding cooperative-cancellation primitives and async capability contexts on top of MCP's tool, resource and prompt abstractions.

• MCP servers
• Libraries

A browser-only demo that runs Google's EmbeddingGemma model through Transformers.js to rank a set of documents against a search query by semantic similarity, with no server and no data leaving the device.

• RAG
• Tutorials

A research fork that runs a 78.62 GiB DeepSeek V4 Flash GGUF model on a Linux laptop with only 7.7 GiB of RAM and no GPU, using memory-mapped NVMe demand paging instead of loading the full model into memory.

• Inference

A personal memory system that any MCP-compatible AI tool can query through a shared PostgreSQL and pgvector store, filtering raw captured thoughts through a synthesis and review stage before anything is saved.

• MCP servers
• Agent memory

A Rust memory database for AI agents that stores typed memories, entities, statements and relations with provenance and bi-temporal validity, and answers queries by fusing semantic, lexical, graph and temporal retrieval.

• Agent memory
• Databases

A curated, source-linked list of public examples of general AI models used for 3D modeling, industrial design, CAD and robot control, each entry naming its model and linking to the original post.

• Curated lists

A CLI that runs multiple AI coding agents as a scheduled, workflow-driven engineering team, installing a daemon and a set of provider, subject, workflow and queue plugins alongside YAML-defined workflows.

• Coding agents
• Workflow automation

An HTTP gateway that sits between AI clients and the Anthropic and OpenAI APIs, recording token usage, prompts and tool calls per user and optionally injecting a centrally managed set of MCP tools.

• LLM gateways

A multi-provider Go library, split into about fifty per-vendor modules, that covers chat, embeddings, image generation, speech and an agent framework with handoffs, memory and Model Context Protocol tooling.

• Agent frameworks
• Libraries

A TypeScript MCP server that gives AI assistants script analysis, file operations, documentation search and execution tools for AutoHotkey v2 development, including read-only tools that inspect the live UI Automation tree.

• MCP servers
• Debugging

A collection of Claude Code plugins and skills that add expert subagents for agentic-commerce protocols such as UCP, ACP, AP2 and A2A, plus platform integrations for Magento, BigCommerce, WooCommerce and Shopify.

• Agent skills

Course code and notebooks for two O'Reilly live training programs covering agentic RAG, MCP, multi-agent orchestration, long-term memory and evaluation of production AI systems.

• Tutorials

A monorepo of Agent2Agent protocol wrappers that turn AI coding backends such as GitHub Copilot SDK, OpenCode, Claude Code, OpenAI Codex and Google Antigravity into standalone, spec-compliant A2A servers from a JSON configuration file.

• Coding agents
• Agent frameworks

A two-stage benchmark comparing more than twenty optimizers for large language model pre-training at scale, first screening them broadly on a shared architecture and then testing the strongest ones for generalization across several model architectures.

• Models
• Papers

A small Linux driver/module that lets an SR-IOV virtual or physical function from Mellanox CX341, or from Intel X550/X710 NICs, be added to a Linux bridge, for use on OpenWrt or Proxmox VE hosts.

• Networking

An Emacs package that shows AI-generated code completions as inline ghost text at the cursor, built on the gptel package, with configurable context windows and an optional idle-triggered automatic mode.

• Editors

A command-line tool that statically analyzes Go source code and generates an OpenAPI 3.1 spec, auto-detecting the web framework in use and following the call graph from routes to handlers to infer request and response types.

• APIs