Explore the directory

A persistent memory and audit-trail layer for AI trading agents, recording every trade and its outcome with a tamper-evident hash chain so an agent can recall what happened last time and why.

• Agent memory

An Unsloth-compatible fine-tuning library, for large language, vision, speech and OCR models, that runs natively on Apple Silicon through Apple's MLX framework.

• Models

A universal Claude Code workflow plugin with specialized agents, skills, hooks and slash commands for architecture-first or ship-fast development, compatible with Claude Code, Cursor, Codex and more than 35 other AI agents.

• Agent skills

A local-first codebase intelligence tool that gives coding agents and teams cited context from current code, git history and technical web research before they edit, review or debug.

• Agent memory
• RAG

A multi-agent security platform that automates finding, verifying and reporting CVEs in a project's source code, from importing a repository through to a ready-to-submit CVE report.

• Security

The legacy repository for OWASP's Top 10 list of security risks in large language model applications, kept as a historical archive now that active development has moved to a successor repository.

• Security

A CLI tool that rewrites an entire git commit history into better, conventional-format messages using a local Ollama model or a remote AI provider.

• CLI tools
• Git

A CNCF open-source DevOps tool that packages and versions AI/ML models, datasets, code and configuration as a single OCI artifact, storable in any existing container registry.

• CI/CD
• Containers

An MCP server plugin for the Cocos Creator game engine that lets an AI assistant such as Claude or Cursor control the editor directly, covering scene, node, component, prefab, asset and animation operations.

• MCP servers

An on-device inference engine for running LLMs locally and efficiently on any device, with bindings for Godot, Kotlin, Swift, React Native, Flutter and Python.

• Inference
• Libraries

A samurai-themed orchestration system that runs up to ten AI coding CLI agents, such as Claude Code, Codex and Copilot, in parallel through tmux, coordinated in a manager and worker hierarchy.

• Coding agents
• Terminals

A family of autoregressive vision models from Apple's AI/ML research team, with released code and pre-trained checkpoints for AIMv1 and AIMv2, aimed at large-scale visual and multimodal representation learning.

• Models

A continuously updated, curated index of research papers, projects and agent skills on using large language models to detect software vulnerabilities, spanning function-level, repository-level, agentic and smart-contract detection.

• Security
• Curated lists

A CLI harness that lets any agent that can run a shell command reach real services, such as Gmail, a persistent browser and messaging apps, without needing its own OAuth app or SDK per service.

• Agent frameworks
• CLI tools

A marketplace of production-ready Claude Code skills for development workflows, centered on skill-creator, a meta-skill for building, validating and packaging a user's own Claude Code skills.

• Agent skills

A verified prompt library for the Seedance AI video model, with hundreds of cases checked against their original posts, reusable prompt templates by category, and installable AI-video skills for coding agents.

• Generative media
• Curated lists

A short, blog-style textbook from Google DeepMind researchers that explains how TPUs work, how large language models run at scale, and how to choose parallelism strategies that avoid communication bottlenecks.

• Books

A community-maintained, regularly updated overview of publicly available Japanese large language models and their benchmarks, listing each model's architecture, training data, publisher and license.

• Models
• Curated lists

A modified version of RAGFlow that adds an administrative backend for managing users, teams, files and knowledge bases, with document parsing switched to MinerU for better layout and image handling.

• RAG

A Claude Code skill that lets Claude delegate a task to the Codex CLI for automated code analysis, refactoring or editing, then summarize what Codex found.

• Coding agents
• Agent skills

An open-source, multi-agent alternative to Claude Tag that brings AI agents such as Claude Code, Codex and Grok Build into a team's existing Slack, Telegram, Discord, GitHub or Linear conversations.

• Agent frameworks
• Workflow automation

An open-source platform for building AI agents either in a no-code visual builder or a TypeScript SDK, with the two kept in two-way sync so technical and non-technical teams can edit the same agents.

• Agent frameworks

The official Kotlin Multiplatform SDK for the Model Context Protocol, maintained with JetBrains, letting Kotlin code targeting JVM, Native, JS and Wasm implement MCP clients and servers.

• MCP servers

A Home Assistant integration and family of small fine-tuned models that let a completely local language model understand voice or chat requests and control a smart home, without cloud services.

• Models