An infinite canvas desktop app for visually managing terminals

Curated agent skills by humans. Search, run, install, and keep them current from one CLI.

Lightweight agent orchestration dev tool that lives in your repo

Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

A Neovim plugin to integrate Gemini CLI well (+ Qwen-code now)

Reusable agent skills for end-to-end software delivery, from requirements and implementation to review, testing, and release.

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Orchestrate multiple coding agents from desktop and mobile

Open-source local workbench for multi-agent software development.

A history management extension for codecompanion AI chat plugin that enables saving, browsing and restoring chat sessions.

Connect your agent to the apps you already use - with or without Zapier.

Dynamically expose tools from proxied servers based on an Agent Persona

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7

Composable agent runtime with enforced isolation boundaries

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then audits drift, cycles and fragility in code you already have. Zero import cycles, zero critical anti-patterns - measured against itself.

✨ AI Coding, Vim Style

General-purpose Playwright automation for coding agents

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

An ML engineering plugin for your coding agents.

Bring Your Own Browser — let your AI agent use the Chrome you already have open

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

A curated collection of ready-to-run automation prompts for real-world workflows.

MCP server for managing Tempo worklogs in Jira