Explore the directory

A curated collection of prompt-engineering patterns, multi-step workflow blueprints and evaluation methods for working with large language models such as Claude.

• Curated lists

An open-source CLI that scaffolds production-ready FastAPI applications and lets developers add, remove or update components such as auth, workers, caching and local AI inference without rewriting the project.

• Backend

A Rust crate that calls the FlatBuffers flatc compiler from a build script to generate Rust, or other language, code from .fbs schema files.

• Libraries

A structured interview-preparation resource for AI, LLM and applied-AI engineering roles, with worked questions, system-design case studies, coding challenges and company-specific question banks.

• Tutorials

A reproducible, self-hosted platform for benchmarking local large language models with versioned question sets, containerized programming tests, rule-based and optional AI-judge scoring, and auditable reports.

• AI evals

An open-source, bring-your-own-key AI agent for Android that controls the phone, runs Shell and Python natively, and connects to remote machines over SSH.

• Coding agents
• Mobile

A browser extension and local server that lets developers annotate elements on a localhost web page and hand the feedback to an AI coding agent to implement automatically.

• Coding agents
• Design tools

An MCP server that adds real-time, markdown-formatted web search to an AI assistant using the Exa API, with basic and filtered advanced search modes.

• MCP servers

An open-source omnimodal large language model that combines image, speech and text understanding with real-time, emotionally expressive speech generation.

• Models
• Speech

An evidence-gated terminal coding agent that lets a developer switch models mid-session and routes tasks into scoped, replayable workflows across Codex, Claude Code, OpenCode and local models.

• Coding agents

An autonomous agentic software development tool that triages issues, implements solutions, reviews code and merges changes to production for Git-hosted organizations on GitHub, GitLab or Forgejo.

• Coding agents

A survey and curated catalog of more than 500 papers on safety risks, attacks and defenses in embodied AI, spanning perception, cognition, planning, interaction and agentic systems.

• Papers

An RL post-training framework for retrieval-augmented reasoning that adds explicit knowledge-refinement steps between search calls, from a NeurIPS 2025 paper.

• RAG
• Models

An alpha-stage TypeScript framework for fine-tuning open-weight LLMs with type-safe configs, a local Studio web UI, and managed GPUs.

• Models

A Python tool for exploring and iterating on computer vision datasets with SQL filters, vector similarity search and a GUI dashboard, built for Ultralytics YOLO and related models.

• Databases
• Data engineering

A lightweight Rust gateway that unifies OpenAI-compatible, Anthropic Messages and Gemini protocols behind one control plane, with policy-based routing, failover and request logging across multiple LLM providers.

• LLM gateways

A Blazor web app and minimal API that performs retrieval-augmented generation and vector search using the native VECTOR type in Azure SQL Database or SQL Server 2025, with Azure OpenAI and Microsoft Agent Framework.

• RAG
• Databases

A CLI-first, open-source AI coding agent runtime distributed as one Rust binary that runs interactively, piped, as a background daemon, over WebSocket, or embedded as a sub-agent.

• Coding agents

An open-source multi-agent orchestration runtime and governed MCP server that runs AI agent teams against a repository under a maintainer-defined policy-as-code layer.

• Agent frameworks
• MCP servers

A production-tested knowledge base for deploying OpenClaw with Claude Code, covering server deployment, messaging-app integration, model configuration and security hardening, plus example AI agent business workflows.

• Hosting
• Tutorials

A tree-based speculative decoding method for Apple Silicon that extends the DFlash draft model with a draft tree, verifying several candidate continuations in one pass.

• Inference

A simulation research repository providing reinforcement- and imitation-learning environments for ROBOTIS robots, built on NVIDIA Isaac Lab, with sim-to-real deployment support.

• Tutorials

A context harness for AI agents that presents code, memory, docs, chats and databases from many sources as one searchable, browsable file-like tree.

• Agent memory
• RAG

A general-purpose Python AI assistant that combines voice recognition, web scraping, OCR, image generation and machine learning behind one interface for automating everyday tasks.

• Agent frameworks