AgenticResourceRegistry

Share and discover coding agent resources across your team. Self-hosted, Apache 2.0, works with Claude Code, Kiro, Cursor, Codex, Pi and more.

What is AgenticResourceRegistry?

Share and discover coding agent resources across your team. Self-hosted, Apache 2.0, works with Claude Code, Kiro, Cursor, Codex, Pi and more.

Overview of AgenticResourceRegistry

What it is

Observal is a self-hosted registry for coding agent extensions with a built-in insight engine. It is described as the control plane and system of record for internal coding agent resources. It allows teams to set up a centralized platform to share Skills, MCPs, and Agents with peers, and provides visibility into usage patterns.

Key features

  • Centralize resources into one platform: Store Skills, MCP clients, hooks, prompts, agent files, and sandboxes in one registry.
  • Run a governed registry: Review submissions, approve internal agents, inspect version diffs, and provide a single trusted installation source.
  • Render across multiple Coding IDE/CLI: Generate the correct configuration for each supported harness automatically.
  • Let agents use each other: Approved resources are discoverable over the open ARD standard; agents can hand off tasks to other approved agents.
  • Learn what works: Use real adoption and session data to find which agents, tools, prompts, and workflows are helping teams.
  • Replay sessions when needed: Use traces as evidence for debugging, review, audits, and deeper analysis.

Use cases

  • Organizations that create internal Skills, Agent files, and MCP clients but face low peer adoption due to lack of discoverability.
  • Teams needing a feedback loop to understand how coding agent resources are actually used and to turn silent failures into actionable feedback.
  • Centralizing coding agent resources that are currently stored in siloed git repositories with little documentation.
  • Supporting multiple coding harnesses (Claude Code, Cursor, Kiro, Pi, Copilot, Codex, OpenCode, and others) with a single registry.

Getting started

Observal has two parts: a server (API + web UI + databases) you self-host, and a CLI you install on each developer machine. 1. Deploy the server One-line install (requires Docker Engine ≥ 24.0 with Compose v2): bash curl -fsSL https://raw.githubusercontent.com/Observal/Observal/main/install-server.sh | bash From source (for contributors): bash git clone https://github.com/Observal/Observal.git && cd Observal cp .env.example .env make up 2. Install the CLI Standalone binary (no Python required): bash # macOS / Linux curl -fsSL https://raw.githubusercontent.com/Observal/Observal/main/install.sh | bash powershell # Windows (PowerShell) irm https://raw.githubusercontent.com/Observal/Observal/main/install.ps1 | iex Python (3.11+): bash uv tool install observal-cli # or: pipx install observal-cli 3. Connect your harness bash observal auth login observal doctor --patch

License and pricing

The project is open source under the Apache-2.0 license. No pricing information is stated beyond being open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/agenticresourceregistryagenticresourceregistry.svg)](https://yunodb.com/tools/agenticresourceregistryagenticresourceregistry?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/agenticresourceregistryagenticresourceregistry?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/agenticresourceregistryagenticresourceregistry.svg" alt="Featured on YunoDB" height="20"></a>