Explore the directory

A local code search tool for developers and AI agents that combines BM25 keyword search, vector similarity and cross-encoder reranking, returning symbol-bounded results instead of whole files.

• Agent memory
• RAG

Two open 6-billion-parameter models that generate complete visual designs, such as posters and UI mockups, and decompose a flattened design image into separately editable layers.

• Generative media
• Design tools

A Maven plugin, ported from Netflix's DGS Gradle codegen plugin, that generates typed Java or Kotlin classes and client APIs from a project's GraphQL schema during the build.

• APIs

An open, community-maintained handbook covering AI-assisted software development from first steps through architecture, debugging, deployment, and production-ready systems.

• Books

A command-line tool that independently reruns a repository's own test commands after an AI coding change, then reports what actually ran and what remains unverified.

• AI evals
• Testing

A single-file, dependency-free Julia port of Karpathy's microgpt that trains and runs a small GPT model from scratch, written to explore Julia's numerical performance.

• Models
• Tutorials

A wrapper for large MCP servers that shows an AI agent a small compressed set of tools up front, fetching a tool's full schema only when the agent actually selects it.

• MCP servers

A self-hostable agent harness built on Claude Code that runs a team of AI agents with their own chat channels, memory, and scheduled tasks, coordinated from a web dashboard.

• Coding agents
• Agent frameworks

A mobile app for Android and iOS that runs language models directly on the device and turns the phone into a local inference server, with optional cloud model support.

• Inference
• Mobile

A selectively curated list of open-source multi-agent orchestrators, coding-agent workspaces, agent runtimes, and related governance layers for running fleets of AI agents.

• Curated lists

A four-layer DevSecOps framework that wires automated security scanning into CI/CD pipelines as a build gate, alongside multi-track deployment and AI-assisted merge-conflict resolution.

• Security
• CI/CD

A single self-compiling binary that runs an AI assistant at home, with chat, persistent memory, tool use, and end-to-end encrypted remote access, on top of a self-built llama.cpp.

• Inference

A curated, categorized list of over 180 research papers on quantizing Vision-Language-Action and World-Action models so embodied robot policies fit within memory, latency and energy limits.

• Curated lists
• Papers

A security checklist and scanner for AI-generated web apps, combining an AI rules file, an automated external scan, and an AI-run audit prompt with a manual checklist.

• Security

A CPU-first LLM inference server built around ternary weight models, running an 8-billion-parameter model in about 2.2 GB of memory on a free-tier ARM cloud instance.

• Inference

A self-hosted retrieval-augmented search platform that indexes GitHub, Notion, Google Drive, Confluence, and other sources into one AI-searchable knowledge base with cited answers.

• RAG

A local-first AI runtime and studio for macOS and Windows that runs open text, vision, image, and voice models entirely on-device behind one OpenAI-compatible API.

• Inference
• Generative media

A research method that lets an autoregressive video generator retrieve its own earlier generated frames as extra context, reducing drift and error buildup in long videos without retraining.

• RAG
• Generative media

A vision-language model fine-tuned specifically to extract structured text from German business documents such as invoices, receipts, and forms, runnable locally or through a cloud API.

• RAG
• Models

A secure CLI proxy that sits between AI agents and external APIs, running human-written HCL request templates so a model never sees the URL, auth header, or secret it is calling.

• LLM gateways
• Security

A browser-based calculator that finds which hardware limit actually constrains an on-premises LLM deployment, then prices and compares sizing options against it.

• Inference

A curated collection of resources on prompt and context engineering, from basic prompting techniques through agentic patterns, tool use, and production AI system design.

• Curated lists

A key-value cache compression library for MLX on Apple Silicon that quantizes cached keys and values to as low as 3 bits, using mixed precision to keep decode quality unchanged.

• Inference

A native Android IDE for competitive programming, letting a user write, run and submit C++, Java or Python algorithm solutions from a phone.

• Editors
• Mobile