Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Structured observability for AI agents. See what your agent does, why it decides, and where it fails. MCP server + CLI viewer. Zero dependencies. Works with Claude Code, Cursor, or any MCP client. After install, the CLI and MCP server are available globally. Add to your AI tool config: Your AI agent now has access to structured tracing tools. ------|-------------| | Start a new trace session | |…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Structured observability for AI agents. See what your agent does, why it decides, and where it fails. MCP server + CLI viewer. Zero dependencies. Works with Claude Code, Cursor, or any MCP client. After install, the CLI and MCP server are available globally. Add to your AI tool config: Your AI agent now has access to structured tracing tools. ------|-------------| | Start a new trace session | | Log a step (action, tool used, input/output) | | Log a decision point (options, chosen, reasoning) |…