Suvadu 0.5.3: Mask the Secrets Your AI Agents Typed, Including the Ones Already Stored
What agent commands leaked past pattern-based redaction, what 0.5.3 now masks, how suv redact cleans history you already have and what it cannot reach, and the Linux glibc fix.
Claude Code Said "Ran 3 Commands": How to See Which Ones
Three ways to see the commands behind Claude Code's "Ran N commands" summary: Ctrl+O, the session transcript, and recording them as they run.
Suvadu 0.5.1: Forgiving Search, Smarter Recall, and What Your AI Agents Actually Changed
Separator-insensitive search, frecency and next-command ranking, opt-in failure output, Cursor sessions, and git snapshots of what each agent session changed, with their costs and limits.
Claude Code Audit Log: Record Every Shell Command It Runs
Walk through a failed Claude Code run with suv agent report, history, Prompt Explorer, and sessions, and learn what agent integrations do and do not capture.
Suvadu vs mem0: Which AI Memory Does Your Coding Agent Need?
Why general-purpose AI memory and shell-history memory are complementary, not competitive — and when to use each.
How AI Agents Query Your Shell History via MCP
Suvadu's built-in MCP server turns your shell history into a queryable resource for AI agents. Here's what it does and how to set it up.
How to Set Up AI Agent Tracking with Suvadu
Run suv init for your agent, restart it, verify with suv doctor, and record a test session you can inspect end to end.
See Every Command Your AI Agent Ran: Claude Code, Codex, Cursor
AI coding assistants run shell commands you may never review. Why that matters, and how to record and review what supported integrations capture.