Explore the directory

This is a PowerToys Run plugin that lets a Windows user query a local Ollama model directly from the PowerToys Run launcher, choosing which pulled model to ask on the fly.

• Inference
• Desktop utilities

OpenLens is an iOS and iPadOS companion app for the OpenCode coding agent, letting a developer chat with an OpenCode server running on their Mac, review agent changes and manage sessions from their phone.

• Coding agents

NITR is a repository-level benchmark that checks whether an AI agent's code edits stay maintainable, not just behaviorally correct, pairing multi-file change requests with hidden functional tests and structural oracles across nine maintainability dimensions.

• AI evals
• Code quality

Napaxi is a mobile-native SDK for embedding on-device AI agent experiences directly into an app, giving Android, iOS and Flutter teams a shared Rust agent runtime with sandboxed tool execution while the host app keeps its own UI, accounts and model configuration.

• Agent frameworks
• Mobile

n8n-claude-skills is a set of Claude Code skills, distilled from more than a hundred production n8n workflows by a verified n8n creator, that teach Claude the node types, expression syntax and patterns needed to build real, working n8n automations instead of broken demos.

• Agent skills
• Workflow automation

MASB is a FastAPI application that orchestrates a multi-agent system to answer questions by combining live web search with a FAISS-backed retrieval-augmented knowledge base, streaming its answer back over server-sent events.

• Agent frameworks
• RAG

Macaw is a private, on-device AI agent for macOS built around a small fine-tuned model that can call ninety-seven verified tools to control mail, files, calendar, music and system settings from a floating prompt bar, with no cloud calls or accounts.

• Agent frameworks

Gomaa is a local-first, hierarchical memory engine for autonomous AI agents that stores memories as human-readable Markdown notes in an Obsidian vault, backed by PostgreSQL with pgvector or zero-config SQLite, so a person can audit and edit what an agent has learned.

• Agent memory

git-semantic is a Rust command-line tool that searches a repository's commit history by meaning instead of exact keywords, so a query like "race condition" can find a commit described as a synchronization bug even without matching words.

• CLI tools
• Git

Cursor History MCP is an MCP server that lets an AI assistant search, inspect and export a user's existing Cursor chat history, turning months of past decisions, bug fixes and architecture discussions into context the assistant can query.

• MCP servers
• Agent memory

ComfyUI-Muse embeds a persistent, multi-session local LLM chat panel directly inside a ComfyUI node, so a user can brainstorm image or video prompts against Ollama, LM Studio or a directly loaded GGUF model without leaving their generation workflow.

• Inference
• Generative media

ArxivExplorer is a semantic search engine for arXiv papers that combines keyword and vector search, generates AI summaries and entity extraction for each paper, and tracks citations, without requiring a login.

• RAG
• Papers

This repository holds the code samples, Jupyter notebooks and reference material for a Udemy course on agentic AI concepts, aimed at practical, hands-on learning for beginners.

• Tutorials

A reference implementation of an optimizer for budget-constrained discrete model compression, which relaxes a per-layer choice of compression option onto a Riemannian manifold so a fixed overall budget, such as total bits, is satisfied exactly rather than only approximately.

• Models

An annotation-driven bash framework for building command-line tools, generating help text, flag parsing and tab completion from a small set of comment annotations on ordinary bash functions.

• CLI tools

A small library that provides an abstract syntax tree for Python, used to generate structured Python source code programmatically instead of assembling strings by hand.

• Libraries

A tool that scrapes Autodesk Maya's API help documentation to generate Python IDE code-completion stubs for the maya.cmds module, whose commands are otherwise registered at runtime and invisible to static analysis.

• Editors

A command-line tool that converts images into palette-quantized source code, primarily for the TI-84+CE calculator series, driven by a YAML file describing palettes, image conversions and output formats.

• CLI tools

An in-memory vector database written in Go, using arena-based memory allocation to avoid garbage-collection overhead and HNSW indexing for fast approximate nearest-neighbor search, with an optional distributed consensus mode.

• Databases

A PHP client for the Milvus vector database's REST v2 API, built on Saloon, with an optional Laravel service provider and facade.

• Databases

Trustabl is a GitHub Action that scans an agent codebase across frameworks such as the Claude Agent SDK, OpenAI Agents SDK, Google ADK, MCP, LangChain, LangGraph, CrewAI, AutoGen and Pydantic AI, and reports production reliability findings directly in the pull request.

• Code quality
• CI/CD

Synaptic Memory is a knowledge-graph and MCP tool server for LLM agents that builds a graph of documents, chunks, database rows and their relations instead of only chunk embeddings, so an agent can follow relations rather than rely on similarity search alone.

• MCP servers
• Agent memory

RASPUTIN is an archived research codebase exploring long-term conversational memory for LLM agents, partitioning retrieval across four fact-type lanes and reranking with a cross-encoder, published for its architectural findings rather than as a production system.

• Agent memory

This Azure sample demonstrates building an AI agent integration end to end: a serverless pizza-ordering API, an MCP server exposing that API to agents such as GitHub Copilot and Claude, and a live dashboard, all runnable locally without any cloud cost.

• MCP servers
• Tutorials