Observal/Observal
Observal is a local registry and analytics platform for your AI components. Setup Observal, define the scope and share your Skills, MCPs and Agents.
What it solves
Observal provides a centralized control plane and system of record for internal AI components. It addresses the problem of AI components (like agents, MCP servers, and skills) being siloed in repositories with poor documentation, leading to redundant development and low adoption. It also solves the lack of feedback loops by turning silent AI failures and usage patterns into actionable insights for developers.
How it works
Observal consists 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. The system generates the correct configuration files automatically for various supported harnesses (such as Claude Code, Cursor, and Copilot).
Who it’s for
Tech-forward organizations that develop internal AI tools and agents to boost productivity and need a governed registry for discovery, distribution, and optimization of these tools.
Highlights
- Governed Registry: A central place to browse, search, and install versioned AI agents with admin review and version diffs.
- Multi-Harness Support: One-command installation across multiple IDEs and CLIs, including Cursor, Claude Code, and Copilot.
- AI-Powered Insights: Analyzes session data to identify what is working or hindering productivity using LLMs via LiteLLM.
- Session Replay: Full capture of user prompts, thinking blocks, assistant responses, and tool calls for debugging and auditing.
- Enterprise Features: Includes audit logs, SAML SSO, and SCIM provisioning in the open-source distribution.