Explore the directory

An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.

• Agent skills
• AI evals

A skill that enforces a strict process on a coding agent, such as decomposing a request, searching for prior art, designing before writing code, and verifying against runtime evidence, stopping the agent and making it start over when it drifts.

• Agent skills

A strict multi-agent workspace template for the Roo Code editor that splits AI coding responsibilities across five isolated roles communicating through markdown files, meant to keep a project coherent on free-tier AI model quotas.

• Agent skills

An offline static analyzer that turns Spark and Hive SQL into structured, versioned column-lineage and diagnostics files, so AI agents and knowledge bases can reason from addressable, checkable facts instead of guessing from raw SQL.

• Data engineering

Gives each coding agent, such as Claude Code, Cursor or Codex, its own cloud Linux desktop with a running dev server, tests and a signed-in Chrome, so the developer's laptop stays free while several agents work at once.

• Coding agents
• Containers

A hands-on, notebook-first repository that builds six retrieval-augmented-generation architectures step by step with LangChain and LangGraph, from a simple retrieve-then-generate pipeline up to self-correcting, agentic and multimodal systems.

• RAG
• Tutorials

A native terminal coding agent built entirely in Rust, aiming for a small memory footprint and no runtime overhead, with a scriptable extension engine, discoverable skills, and deterministic memory handling for long-running sessions.

• Coding agents
• Terminals

A Claude plugin that runs an always-on SEO and AI-answer-engine growth loop for a WordPress site: it pulls Google Analytics and Search Console signals, proposes fixes with reasoning attached, and applies only the changes a human approves.

• Agent skills
• Workflow automation

A shared delivery loop of 27 skills for Claude Code, Codex and Cursor, plus a deterministic command-line tool, that keeps specifications, stories and tasks as reviewed files in a repository so an agent reads the plan before changing code.

• Agent skills
• Workflow automation

A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.

• Agent frameworks
• Agent memory

A statically-typed, compiled programming language with a from-scratch native backend, designed to be written by AI coding agents and easy for a reviewer, human or model, to check rather than terse to type.

• Languages

A free, open-source desktop app built with Tauri and Rust that brings ChatGPT, Claude, Gemini, Grok, Perplexity, Qwen, DeepSeek and Z.ai into one window, so a written prompt can be sent to a chosen provider automatically.

• Inference
• Desktop

A fully generated C# SDK for the Jina API, covering embeddings, reranking and search, with Microsoft.Extensions.AI integration and support for .NET Framework, .NET Standard and modern .NET features such as trimming and NativeAOT.

• RAG
• Libraries

An unofficial, community-maintained archive that tracks TypeSafe's official Jev documentation, SDKs, agent skill and known model limitations over time, recording sources, hashes and timestamps rather than mirroring the hosted pages wholesale.

• Documentation tools

Turns a DGX Spark GPU cluster into a self-running team of role-specialized AI agents built on the Hermes runtime, dispatching coding work across nodes, reviewing it with a dedicated agent, and restarting anything that crashes.

• Agent frameworks
• Inference

A four-month, hands-on study roadmap for generative AI engineering, moving through large-language-model fundamentals, prompt engineering, retrieval-augmented generation, AI agents and tool calling toward production deployment.

• Tutorials

An extension pack for Gas City, a multi-agent runtime, adding custom agents, formulas and planning workflows that turn a filed unit of work into a pushed branch, a review verdict and a landed pull request with minimal human interruption.

• Agent frameworks

A self-hosted, Java-based knowledge base for small and mid-sized organizations, turning internal documents into a searchable, question-answerable and audit-exportable knowledge asset with hybrid retrieval and Docker deployment.

• RAG
• Databases

A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

• Generative media

A self-hosted dashboard for visualizing Claude Code usage from session transcripts, with time-correct cost accounting, per-project attribution, and support for ingesting Codex and Kimi CLI transcripts as well.

• Coding agents
• Monitoring

A screen-recording and voice tool that turns a spoken walkthrough into separate bug tickets, ideas and to-dos for a coding agent, picking the right frame for each item and writing up expected versus actual behavior with likely code pointers.

• Agent skills
• Debugging

A persistent, cross-tool memory layer for AI coding assistants such as Claude Code, Cursor, OpenCode and Windsurf, reached through the Model Context Protocol and backed by a shared Supabase pgvector database.

• MCP servers
• Agent memory

A full-workflow tutorial and toolchain for training vision, hearing and smell AI algorithms and deploying them, as packaged algorithm modules, onto a specific edge AI platform.

• Models
• Tutorials

A reference OAuth2 authorization server built with Spring Boot 4 and Java, wired up with MariaDB, Redis, OpenTelemetry tracing, and optional AI advisor integrations through Ollama, for developers to run and test locally.

• Backend
• Auth