Observal/Observal

Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.

What it solves

Observal provides a centralized control plane and system of record for internal coding agent resources. It solves the problem of fragmented, siloed resources (like MCP clients, Skills, and Agent files) that are often recreated by different developers due to a lack of discoverability and a missing feedback loop regarding how these resources are actually used.

How it works

Observal consists of a self-hosted server (API, web UI, and databases) and a CLI installed on developer machines. It acts as a registry where admins can review and approve resources. The CLI allows developers to install these approved agents into various supported harnesses (such as Claude Code, Cursor, and Copilot) with automatically generated configurations. It also captures session telemetry, which is then analyzed by AI-powered insight reports to identify usage patterns and areas for improvement.

Who it’s for

It is designed for tech-forward organizations that develop internal AI coding agents and tools, requiring a governed registry for distribution, discovery, and performance monitoring.

Highlights

  • Multi-harness Support: One command to install agents into various IDEs and CLIs including Claude Code, Cursor, and GitHub Copilot.
  • Agent Delegation: Implements ARD (Agentic Resource Discovery) and A2A (Agent2Agent) protocols, allowing agents to find and delegate tasks to other approved agents.
  • Governance: Includes an admin review queue with version diffs and approval workflows to ensure trusted internal resources.
  • Observability: Provides full session replay with turn-by-turn timelines, token counts, and tool-call inspection.
  • AI-powered Insights: Uses LLMs to analyze session data and generate reports on what is working and what is hindering development workflows.

Related

  • Project
    agentic-community/mcp-gateway-registry

    A governed control plane and gateway for AI assets, providing centralized discovery, access control, and audit trails for MCP servers, agents, and model inference endpoints.

  • Project
    builderz-labs/mission-control

    A self-hosted control plane for operating AI agents, allowing users to dispatch tasks, track spend, and coordinate multiple agent runtimes from a single dashboard.

  • Project
    paperclipai/paperclip

    Paperclip is an open-source orchestration platform that manages teams of AI agents like a company, providing a centralized dashboard for task management, budget tracking, and governance.

  • Project
    comet-ml/opik

    An open-source LLM observability and evaluation platform for AI agent tracing, prompt management, and production monitoring.

  • Project
    zqiren/Orbital

    A project-centric agent coordinator that stores project context as local files, allowing users to switch between different AI agents without re-explaining the project.