Explore the directory

A Python library for declaring data transformations, such as pipes, filters, joins, group-bys and window functions, as plain Python expressions that compile at runtime into small, optimized native functions.

• Data engineering

A curated list of frameworks, software and other resources for building autonomous agents that generate and prioritize their own tasks toward a given objective, including entries such as AutoGPT, AgentGPT and babyagi.

• Curated lists

A local LLM chat, image-diffusion and on-device training app for the Xbox Series S and X, built as an architecture exercise under a console's UWP sandbox and 10 GB RAM ceiling.

• Inference
• Generative media

A framework-agnostic, drop-in feedback widget for a website or app that turns each submission into structured email and webhook data an AI agent workflow can classify, group and route.

• UI kits
• Workflow automation

A local context and memory engine that gives a small local LLM a billion-token pool on disk, pulling back only the slice it needs while it reasons instead of enlarging its context window.

• Agent memory
• Inference

A framework for evaluating semantic search across a developer's own datasets, comparing embedding models, BM25 and other backends with metrics such as Accuracy@k and NDCG@k.

• RAG
• AI evals

A POWER8-specific research prototype that replaces some full-matrix attention computation with a hardware AES instruction used as a fast prefilter, so only a subset of attention paths get the full computation.

• Models
• Inference

A self-hosted dashboard for a developer's own machine that manages running apps, orchestrates AI agents, and tracks personal knowledge and health, all reachable from any device over Tailscale.

• Agent frameworks
• Desktop utilities

A tool that indexes a codebase's domain concepts, naming conventions and vocabulary so a coding agent can answer a conceptual question in one MCP call instead of dozens of individual searches.

• MCP servers
• RAG

A single-binary local search CLI for Japanese Markdown notes, combining full-text and optional semantic search, built mainly so an AI coding agent can search a developer's own note archive.

• RAG
• CLI tools

A .NET library that registers Model Context Protocol tools and servers as Microsoft Semantic Kernel functions, including servers already configured in Claude Desktop.

• MCP servers
• Libraries

A distributed AI agent framework where a decorator turns a plain function into a networked agent, and the mesh handles discovery, transport, retries and failover across languages and machines.

• Agent frameworks

An MCP server that lets an AI assistant explore Aura's fully homomorphic encryption tools, running numeric computation on encrypted data without exposing the underlying values.

• MCP servers
• Security

A dual-engine benchmarking pipeline for GGUF and safetensors language models on NVIDIA GPUs, measuring both speed and answer quality with a live dashboard and exportable benchmark cards.

• Inference
• AI evals

A format and runtime that packages organizational knowledge as a single portable, cryptographically verifiable file so it can be mounted, queried and proven rather than trapped inside one application's database.

• Agent memory
• Databases

A small, transparent AI agent framework written in about 1,300 lines of Python, meant to be read and owned rather than treated as a black box.

• Agent frameworks

A Rust rewrite of the Graphify code-graph tool that lets an AI agent ask who calls a symbol, what depends on it, and what might break if it changes, indexed in SQLite for fast repeated queries.

• Code quality

An open local runtime that combines native inference, speculative decoding and agentic caching so useful local AI agents run faster automatically, and can also guard an agent a user already runs elsewhere.

• Agent frameworks
• Inference

A bounded, self-correcting long-term memory layer for LLM agents that distills noisy, contradictory project logs into a capped memory pool instead of letting a vector store fill up with stale, conflicting copies.

• Agent memory

A single executable dialog-flow tool with a drag-and-drop visual editor, intent detection and a local or cloud LLM manager, needing no separate database or search service to install.

• Workflow automation

Setup instructions for a hands-on GitHub Copilot training course, configuring a GitHub Codespaces environment used to run the course's labs.

• Tutorials

A hosted Databricks App that runs Claude Code, Codex, Gemini CLI and other coding agents in the browser, wired to a Databricks workspace with governed model and tool access.

• Coding agents
• Hosting

A tool that reads a repository's own manifests and configures an AI coding assistant for that stack: specialized agents, framework skills, MCP servers and path-scoped rules, across seven different assistants.

• Coding agents
• Agent skills

A local, searchable index of a developer's AI coding-agent history across eleven tools including Claude Code, Codex and Cursor, with hybrid keyword and semantic search, an MCP server and a CLI.

• Coding agents
• Agent memory