Explore the directory

An autonomous agent that scans every commit for vulnerabilities, files triaged Jira tickets, and reacts to Jira updates by suppressing known issues or opening a fix pull request, mapped to Cyber Resilience Act requirements.

• Security

A plugin for Claude Code, GitHub Copilot CLI and VS Code that authors, tests and troubleshoots Microsoft Copilot Studio standard agents as YAML files from the terminal or editor.

• Agent skills

Dive into LangGraph is an open-source tutorial and Claude Code Agent Skill that teaches LangGraph and LangChain by building a ReAct agent through 14 chapters covering state graphs, middleware, memory and MCP.

• Tutorials

A collection of 40 plugins that teach AI coding assistants how to work with SAP development areas such as BTP, CAP, Fiori, ABAP, HANA, Analytics Cloud and Datasphere, each tracked against source or registry evidence.

• Agent skills

A multi-agent development orchestration platform with 39 specialist agents, a lightweight path for simple tasks and a four-phase workflow for larger work, running across Gemini CLI, Claude Code, Codex and Qwen Code.

• Coding agents
• Agent frameworks

A collection of packaged skills that teach AI coding agents how to work with Firebase, installable as a CLI skill package, a Gemini CLI extension or a Claude Code plugin.

• Agent skills

A Java framework for building LLM, RAG, MCP and multi-agent applications, integrated with the Solon ecosystem and embeddable in Spring Boot, Vert.x, Quarkus and other Java frameworks.

• Agent frameworks

A documentation system for AI-agent-built repositories that keeps walkthroughs, concept pages, evidence pages and sync rules updated alongside the code as agents change it.

• Agent skills
• Documentation tools

A governance standard and reference toolset that defines the rules, evidence requirements and decision boundaries for repositories whose content is maintained by LLM agents.

• Agent frameworks

A Model Context Protocol server that gives language models read and write access to Airtable bases, letting them inspect schemas and list, search, read and write records.

• MCP servers

A browser-based system that pools the GPUs of several devices over WebRTC to run one large open language model together, splitting its layers across laptops, desktops and phones.

• Inference

A curated collection of papers, tools and implementations that combine retrieval-augmented generation with reasoning techniques for large language models and agents.

• RAG
• Curated lists

A self-hosted, open-source alternative to Codex, Claude Code and Cursor that a team runs from a browser, including on a phone, with multi-agent collaboration and direct connections to Chinese large language models.

• Coding agents

A cross-platform toolkit for running language models, speech recognition and text-to-speech natively inside apps and games, on Flutter, Swift, Kotlin, Unity or Rust, entirely offline.

• Inference
• Speech

A plug-and-play, training-free retrieval-augmented generation pipeline that adds visually-aligned OCR, ASR and object-detection text to a large video-language model, improving long-video comprehension without extra fine-tuning.

• RAG

Persistent engineering context for coding agents, so an agent retrieves only the decisions, constraints and cross-module contracts a task needs, verifies them against the live repository, and rechecks them as code evolves instead of rereading everything each session.

• Agent skills
• Agent memory

A research project that has an AI agent discover executable code representations of the physical world from video, so a vision-language model can verify and reuse explicit states, dynamics and mechanisms instead of only matching pixels.

• Papers

A Rust SDK that provides every building block of a production coding agent, tool execution, LLM streaming, sub-agent orchestration, persistent memory, skills and MCP integration, as composable library functions rather than a fixed CLI app.

• Agent frameworks

An open-source software factory that runs repeatable AI coding workflows on a developer's own machine, keeping repository access and credentials local while recording each run from request to handoff.

• Coding agents
• Workflow automation

A 66-tool MCP server that gives an AI agent unified access to dark-web and threat-intelligence sources: breach databases, ransomware-leak tracking, Tor .onion access, malware analysis, blockchain forensics and exploit search.

• MCP servers
• Security

A CLI for creating, switching between and deleting Git worktrees through a fuzzy-finder interface, aimed in part at running several AI coding agents on different branches of the same repository in parallel.

• CLI tools
• Git

A three-stage diffusion-based framework, from Tencent ARC, for automatically colorizing black-and-white image sequences, such as cartoon or comic panels, while keeping the same character and object identity across frames.

• Generative media
• Papers

A free, open-source AI coding agent, built with Rust and Tauri, that runs any model provider, OpenAI, Anthropic, Google or local models such as Ollama or LM Studio, and executes projects with four levels of parallelism, entirely on the local machine.

• Coding agents

The JavaScript and TypeScript SDK for the Qdrant vector search engine, published as a main package plus separate lightweight REST and gRPC clients.

• Databases