Explore the directory

A terminal-first, Go and Charm-stack orchestrator for issue-driven AI coding agent runs, reimplementing an existing multi-agent orchestration design to manage work across git worktrees rather than managing individual agent conversations.

• Coding agents
• Terminals

A multi-agent chat application that builds a crew of specialist agents, an architect, coder, reviewer, researcher, and browser operator, who hand off work to each other from a single orchestrated interface, usable from a desktop app, terminal, HTTP API, or CI pipeline.

• Coding agents
• Agent frameworks

A PHP library that maps one object to another automatically using on-the-fly generated code, avoiding both hand-written mapping code and slower reflection-based alternatives.

• Libraries

A fully local, GUI and API platform for Retrieval-Centric Generation that lets a user build a private chat tool over their own documents and a locally hosted open-source language model, with a retrieval-tuning module for prompts and analysis.

• RAG

A free, open-source coding pipeline that turns a ticket into a reviewed pull request on your machine: it plans before writing code, has a second model adversarially review the result, and will not claim a fix works unless its tests fail on the old code and pass on the new one.

• Coding agents
• Testing

A notebook-first course of 26 runnable Jupyter notebooks that builds a modern LLM system from scratch in PyTorch, covering tokenizers, attention, mixture-of-experts, training, RLHF, quantization, speculative decoding, and deployment.

• Tutorials

A source-available, local-first Memory OS for personal AI assistants that remembers user preferences and past work, learns from imported knowledge through a linked wiki and graph, routes to skills and external AI apps, and compresses context to spend fewer tokens.

• Agent memory

A memory-enhanced GraphRAG framework accepted at a 2026 data-mining conference that organizes retrieval into three connected layers, an abstract schema, extracted facts, and source passages, with conflict detection between facts and their supporting evidence.

• Agent memory
• RAG

An open-source design MCP server and shadcn/ui component registry that gives AI coding agents design tokens, production component code, and accessibility review rules for more than 30 brand-grade design systems such as Linear, Stripe, and Notion.

• MCP servers
• UI kits
• Design tools

A step-by-step blog and video series explaining the Transformer architecture, covering tokenization, embeddings, every attention variant, feed-forward layers, and how the encoder and decoder fit together.

• Tutorials

An MCP server that gives AI agents Roslyn-powered static analysis and precise code manipulation for C# solutions, generating a project structure map, call graphs, and dependency trees instead of relying on plain text edits.

• MCP servers
• Code quality

A simple, read-only MCP server for NetBox that lets LLM clients query core network-infrastructure objects, object details, and audit-trail change logs, deliberately kept small and easy to fork rather than covering NetBox's full API.

• MCP servers
• Networking

An MIT-licensed MCP server that lets AI assistants like Claude Code, Cursor, and GitHub Copilot operate directly inside a running Unity Editor project, creating scenes, generating scripts, and driving play-mode testing from a single prompt.

• MCP servers
• Testing

A confidence-aware context graph for long-horizon AI agents that tracks not just what was said or retrieved but what an agent should believe, at what confidence, from which evidence, and whether it should act on it.

• Agent memory

A collection of end-to-end SageMaker notebooks and config-driven recipes covering generative-AI model training, fine-tuning, inference optimization, MLOps automation, distributed training, RAG, and agent-based applications.

• Models
• Tutorials

An Agent Skill that inspects a repository's context, tests, CI, and pull-request patterns, then generates the configuration files coding agents need to contribute correctly, such as AGENTS.md, Copilot instructions, CI checks, and issue templates.

• Agent skills
• CI/CD

A Swift package for running local large language models on iOS, macOS, and Linux, supporting GGUF and MLX model formats and Apple's FoundationModels framework behind one streaming API, with experimental multimodal input and tool calling.

• Inference
• Mobile

A minimal, standalone terminal coding agent that works through four tools, bash, read_file, write_file, and edit_file, connecting to any local model server or API provider with no project account or subscription required.

• Coding agents
• Terminals

A self-hosted tool that turns any document, URL, or zip of files into an interactive knowledge graph, extracting subject-predicate-object facts with a locally-run LLM.

• Agent memory
• RAG

An AI QA agent for VS Code that reads a pull request's diff, generates a test plan, opens a real browser to click through the app, and reports whether the change is safe to merge.

• Testing

An open-source red-teaming and evaluation framework for AI agents that fires 300 curated adversarial prompts across an OWASP-inspired ten-category agent-security taxonomy at any HTTP endpoint or Python callable, scoring responses without further LLM calls.

• AI evals
• Security

A model-agnostic AI coding agent that runs inside self-building Docker containers by default, so it can act on a project without approval interruptions while staying confined to the current working directory.

• Coding agents
• Containers

Chinese-language study notes that walk through the MiniMind LLM codebase line by line, then extend each concept into the wider techniques used across modern large language models.

• Tutorials

An open-source runtime for Anthropic's Agent Skills standard that compiles a SKILL.md into a portable, hardened agent you can deploy on Kubernetes, on-prem, air-gapped, in CI, or as an A2A endpoint.

• Agent frameworks
• Agent skills