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 addresses the fragmentation and lack of discoverability of internal AI components (such as Agents, MCP servers, and Skills) within organizations. It prevents developers from redundantly recreating similar tools by providing a centralized system of record and discovery layer. Additionally, it solves the "silent failure" problem of AI by capturing usage patterns and session traces, turning hallucinations or subtle errors into actionable feedback for continuous optimization.

How it works

Observal operates as a control plane consisting of a self-hosted server (API, web UI, and databases) and a CLI installed on developer machines. It treats agents as portable context packages that bundle MCP servers, skills, hooks, prompts, and sandboxes into a single versioned unit. The system automatically generates the necessary configuration files for various supported AI harnesses (like Cursor, Claude Code, and Copilot), allowing users to install agents with a single command. Telemetry hooks capture session data, which is then analyzed via LLMs to generate insight reports on what is working and where tools are hindering users.

Who it’s for

It is designed for tech-forward organizations that develop internal AI tools and need a governed way to distribute, manage, and monitor the effectiveness of these components across different coding IDEs and CLIs.

Highlights

  • Multi-Harness Support: Automatically generates configs for tools like Claude Code, Cursor, Copilot, and Goose.
  • Governed Registry: Provides a centralized place to review, approve, and version-control internal AI agents.
  • Session Replay: Captures full turn-by-turn timelines, including thinking blocks, tool calls, and exact inputs/outputs for debugging and auditing.
  • AI-Powered Insights: Uses LLMs to analyze session data and identify "Quick Wins" and usage patterns.
  • Enterprise-Ready: Includes audit logs, SAML SSO, and SCIM provisioning in the open-source distribution.

Related

  • Project
    agentic-community/mcp-gateway-registry

    A unified control plane and gateway for AI assets, providing centralized discovery, governance, and secure access to MCP servers, agents, and model inference endpoints.

  • Project
    obot-platform/obot

    An open-source platform for organizations to manage, secure, and govern their AI ecosystems, providing centralized control over LLM access, MCP servers, and AI activity auditing.

  • Project
    codeaholicguy/ai-devkit

    AI DevKit is a local npm‑based control plane that unifies configuration, monitoring, cross‑agent messaging, searchable SQLite memory, and composable engineering “skills” (requirements, design, testing, review, etc.) for many AI coding assistants such as Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot. It lets teams manage multiple agents from a single console, keep project conventions in a searchable store, and enforce a senior‑engineer workflow without modifying the underlying LLMs.

  • 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
    lmnr-ai/lmnr

    An open-source observability platform for AI agents that provides tracing, monitoring, and evaluation tools to debug and optimize agentic workflows.