Explore the directory

A self-hostable WhatsApp AI agent framework with 13 built-in industry-specific 'brains' -- restaurants, clinics, salons, gyms and more -- covering function calling, RAG and multiple languages.

• Agent frameworks

A self-contained C++ inference engine for the Qwen and Gemma model families on ggml, built around auditable answers that cite which parts of the input they used and which they never read.

• Inference

A small, educational Python package for fine-tuning Vision Transformer models with PyTorch, reaching 97.65% accuracy on CIFAR-10 with a simpler API than general model-zoo libraries.

• Models

An IDE extension that gives the Pi coding agent a unified, semantic interface for reading, searching, editing, running, debugging and observing code, instead of a separate tool for each task.

• Coding agents

A model-agnostic agent harness that plans a long task first, self-corrects at every step, and checkpoints its whole run, so a crash is just a pause instead of a restart from zero.

• Agent frameworks

A local-first knowledge base with semantic search built for AI coding assistants, so they can query project knowledge directly instead of re-scanning files or being re-explained the codebase every session.

• Agent memory

A self-hosted, durable memory and retrieval layer for AI agents and apps, combining vector, keyword, temporal and graph recall over your own Qdrant and Memgraph.

• Agent memory

A biomimetic, symbolic cognitive memory architecture for AI agents that gives them persistent cross-session memory using neurobiology-inspired structures and linear algebra instead of dense embeddings.

• Agent memory

A browser-based drag-and-drop tool for designing interactive Material 3 Expressive screens, which turns the finished layout into a prompt for AI coding assistants to implement.

• Design tools

An MCP server that gives Microsoft 365 Copilot hands on your own PC: it can read and write files, run Python, work with Office documents, OCR images, and query internal databases through a small local server.

• MCP servers

A single-binary LLM inference engine written in Rust for Apple Silicon and NVIDIA CUDA, built from scratch with native CUDA and Metal kernels, a native tokenizer and its own model format.

• Inference

A standalone, Bun-native coding-agent harness that runs from any repository and drives the agent through a structured plan, build, audit and verify workflow across dozens of model providers.

• Coding agents

An MCP server for hybrid semantic and full-text search over a Markdown knowledge base, with optional support for plain text, PDF, Office documents and source code.

• MCP servers
• RAG

A small desktop git client built for running AI coding agents in parallel worktrees, watching their diffs land live, and testing and committing the results without switching between an editor, GitHub Desktop and a pile of terminals.

• Coding agents
• Git

A protocol and Rust node that gives AI agents a rail-neutral, signed evidence layer for economic transactions, so bots can publish, discover, buy, sell and compose paid services and data.

• Agent frameworks

A .NET 10 RAG library for building semantic search and retrieval systems, combining vector and keyword hybrid search with pluggable storage backends.

• RAG

An open-source spatial AI memory system that stores agent memories as tetrahedrons in 3D space, builds a knowledge graph from them, and serves persistent cross-session memory to AI agents over MCP.

• Agent memory

An open-source, self-hosted, multi-tenant SaaS boilerplate built on Nous Research's Hermes Agent, providing authentication, billing, a dedicated agent per paying user, and 14 working chat-time tools out of the box.

• Agent frameworks

A local privacy layer for Arabic and Gulf text that finds personal data such as names, national IDs, IBANs and phone numbers, replaces each value with a reversible token before it reaches an AI model, and restores the real values locally when the reply comes back.

• Security

An open, federated, self-hosted platform that gives AI agents and humans shared identity, memory, workspaces, scheduling and a metered messaging economy on nodes the operator controls.

• Agent frameworks

A background service that runs AI coding-agent CLIs against a developer's own git repositories, giving each task an isolated worktree, a terminal session, a recorded outcome, and a policy-driven path toward the default branch.

• Coding agents

A 1,350-image benchmark for evaluating document-parsing robustness against real-world captured pages, derived from OmniDocBench with physical printing, deformation and photography.

• RAG
• AI evals

Runs the same document corpus and question set through 19 retrieval architectures and reports citable, statistically tested evidence for which one fits a given dataset best.

• RAG
• AI evals

The companion repository for a Udemy course on outlier detection, with lecture notebooks plus reusable Python utilities, tests, exercises and benchmarks.

• Tutorials