Explore the directory

An open-source Java toolkit for building, evaluating and deploying AI agents in code, with tight integration into Google Cloud services.

• Agent frameworks

An agent skill that extracts a reference UI's visual identity, its design tokens, qualitative style and visual effects, into a structured Design DNA JSON, then generates matching UI from new content.

• Agent skills
• Design tools

A minimal, memory-efficient coding agent written in Rust, with a terminal UI, session persistence, permission controls and support for many model providers.

• Coding agents
• Terminals

A curated, actively updated list of notable research papers on multi-agent systems built with large language models, compiled by the Swarms research team.

• Curated lists
• Papers

A growing series of blog posts and videos that teach how large language models work internally, step by step from tokenization through attention to inference optimization.

• Tutorials

An educational, end-to-end open-source knowledge base covering LLM fine-tuning, dataset distillation, reinforcement learning and local deployment, with notebooks and guides in four languages.

• Models
• Tutorials

A collection of customized Pi Coding Agent setups showing how to build custom UI, agent orchestration, safety auditing and two-way agent-to-agent communication.

• Coding agents

An AI-assisted penetration-testing workflow that investigates a target application, then uses machine oracles to verify whether a found exploit actually reproduces before reporting it.

• Security

A distributed multi-modal vector database that supports vector queries and upserts through MySQL-compatible unified SQL over both structured and unstructured data.

• Databases

A multi-agent orchestration tool that turns a software change into an explicit graph: one agent implements, independent agents review in parallel, failures route to bounded repair, and delivery through git and CI happens only after checks pass.

• Coding agents

A GitHub App, Action, CLI and coding-agent skill that draws each pull request as an animated architecture and data-flow diagram, posted directly inside the pull request.

• Git
• Code quality

A PHP framework for building generative AI applications and retrieval-augmented search, compatible with Symfony and Laravel and inspired by LangChain.

• Agent frameworks
• RAG

An open-source MCP server that lets an AI coding tool generate product, marketing and ecommerce images and video through GPT Image 2, Seedance, ComfyUI and other models.

• MCP servers
• Generative media

A self-hosted, OpenAI-compatible LLM router with a managed failover safety net, letting a bring-your-own-key setup fall back to another provider automatically during an outage.

• LLM gateways

The official research implementation for training large language models to reason using a continuous latent space instead of generating explicit chain-of-thought text.

• Models

A Google toolkit of skills and an ADK harness that let AI coding agents autonomously find, reproduce and patch vulnerabilities in a codebase, with human review built into the process.

• Agent skills
• Security

Official hosting configurations for self-hosting the n8n workflow-automation platform, with Kubernetes Helm charts, Docker Compose setups and an AWS ECS Fargate example.

• Hosting

A penetration-testing tool that uses a large language model to identify login-form fields on a target page, then runs multi-threaded brute-force or password-spray attacks against it.

• Security

An Agent Skill that helps an AI coding assistant write and revise Japanese business documents so they read naturally, using a style rulebook and morphological-analysis linting.

• Agent skills

An open-source multi-agent simulation where several GPT-4 agents, each with its own memory, collaborate in a simulated world to work toward shared goals.

• Agent frameworks

A patched vLLM serving setup and requantization pipeline that runs a large Qwen model on a single consumer GPU, with an OpenAI-compatible API in single-user or batch modes.

• Inference

A web, desktop and mobile client that lets a developer run and orchestrate coding agents such as Claude Code, Codex and OpenCode in parallel across their own machines.

• Coding agents

A Python library for bulk inference and scalable synthetic-data curation, for preparing post-training datasets and extracting structured data from LLM outputs, with a viewer for monitoring generation.

• Models
• Data engineering

A code-completion and code-comprehension server providing semantic GoTo commands and, for some languages, diagnostics, originally built for the YouCompleteMe Vim plugin and now used by clients for Emacs, Atom, Sublime, VS Code, Kakoune, Geany and nano.

• Editors