Explore the directory

A stability-score lookup for npm package versions, backed by GitHub issues and community reactions rather than a database, answering whether it is safe to upgrade to the latest version of a package.

• Code quality

A local-first autonomous coding agent that plans, edits files, runs commands, debugs failures and validates results end-to-end, keeping control, execution and session state on the user's own machine.

• Coding agents

A curated list of links to AI services, vendor prompt-engineering guides and recommended LLM tools, compiled as companion material for a live online training course on prompt engineering.

• Tutorials
• Curated lists

An MCP server that recommends software design patterns from natural-language queries, searching a catalog of 710 patterns across 90-plus categories using blended semantic, keyword and graph-augmented retrieval.

• MCP servers

Context infrastructure for AI coding agents that combines tree-sitter code chunking, LanceDB vector search and SQLite full-text search into hybrid retrieval and persistent project memory, exposed as a CLI, MCP server or library.

• MCP servers
• Agent memory

A self-hosted semantic code-search platform, invoked as cix, that indexes a codebase into a vector store for meaning-based search, combining hybrid BM25 and dense embeddings through an embedded llama.cpp server.

• Agent memory
• RAG

A retrieval-augmented generation framework built on the HippoRAG 2 architecture that turns a static knowledge graph into a query-adaptive navigation structure, reproduced with the prompts and dataset from its ACL 2026 paper.

• RAG
• Papers

A local agent that runs entirely on Apple Silicon, using an on-device model to plan steps and a raw Chrome DevTools Protocol client to drive a real browser and shell for end-to-end tasks such as browsing and running scripts.

• Browser automation

A CLI tool that bridges Claude Code and Gemini CLI in one interactive terminal session, forwarding a response from one assistant to the other so a developer can compare or hand off work without manual copy-paste.

• Coding agents

An integration and governance layer for deployed AI agents that bounds what an agent may do, keeps inspectable evidence of what it did, and connects it to hosted operation or agent-to-agent commerce only when needed.

• Agent frameworks
• AI evals

A Swift package that runs Google's Gemma 4 model on iPhone through the LiteRT-LM runtime on the Metal GPU, with text, image and audio input, and a second mode that plugs the same runtime into Apple's Foundation Models API as a custom backend.

• Inference

A set of standalone example decision apps for the Nextmv optimization platform, showing how to solve knapsack, vehicle routing, shift scheduling and order-fulfillment problems in Go and Python with solvers such as HiGHS, OR-Tools, Gurobi, CPLEX and Xpress.

• Tutorials

An embedded graph database with built-in vector search that runs inside a host process with no server, combining temporal graph edges, GQL queries and HNSW vector similarity in one Rust engine.

• Databases

A Docker image for a self-hosted, real-time speech-to-text server based on faster-whisper, offering WebSocket streaming transcription and an OpenAI-compatible REST API, with optional GPU acceleration.

• Speech
• Containers

A collection of 182 machine-learning model families spanning language, vision, speech and audio, ported as standalone Rust crates on top of the rlx multi-backend compiler and runtime, targeting CPU, Metal, MLX, CUDA and wgpu.

• Inference

A Qwen-specialized fork of MLX adding disk-backed KV-cache checkpointing for hybrid attention models, letting a 122-billion-parameter model stay responsive across long conversations on Apple Silicon.

• Inference

An interactive CLI that interviews a developer about their project's stack and conventions, then generates the guidance files AI coding assistants read, such as CLAUDE.md, .cursorrules and AGENTS.md.

• Agent skills

A platform that turns an AI agent's own production traces into a fine-tuned model, benchmarked against user-defined evaluation metrics and served behind one OpenAI-compatible API, available hosted or self-hosted.

• Models
• AI evals

A multi-layer caching library for AI agent pipelines that sits in front of LLM calls, embeddings and retrieval queries across frameworks such as LangChain, LangGraph, AutoGen, CrewAI and Agno, caching by semantic similarity as well as exact match.

• Agent frameworks
• RAG

A schema-driven UI rendering engine that turns a JSON schema into production React components such as grids, kanban boards, dashboards and Gantt charts, so an AI agent can generate UI as compact JSON instead of hand-written React.

• UI kits

An MCP server that gives coding agents such as Claude Code and Cursor reviewable shared memory, working locally with zero configuration or connecting to Novyx Cloud for governed, approvable actions and audit trails.

• MCP servers
• Agent memory

A Python and JavaScript SDK for the Makra web-extraction API, which reads a URL remotely against a supplied schema and returns the requested data as structured JSON.

• APIs
• Browser automation

A document intelligence engine that parses PDFs, DOCX, PPTX, XLSX and CSV into validated, AI-ready chunks for retrieval-augmented generation, with human review, PII redaction and a production FastAPI server.

• RAG

A VS Code extension that grammar-checks documents with a local or Copilot-backed LLM, chunking text into paragraphs and offering inline correction, rewrite and synonym suggestions.

• Editors