Look something up. Then fix what broke.

Manage the conversation: /new, /clear, /reset, /stop, /regenerate, /compact, /export-session, /import-session — start over, stop a response, regenerate, summarize, export, or import a saved JSON conversation.

Lifecycle and persistence controls for the active session: clear context, reset agent state, stop generation, regenerate last response, force-trigger compaction, export Markdown/JSON, or import supported JSON.

Change how the AI responds: /models, /think, /reasoning, /fast, /verbose, /elevated — see what models are available, turn on slow careful thinking, or switch between quick / detailed / expert reply styles.

List runnable/running models, toggle thinking mode, show step-by-step reasoning, or switch response modes (fast, verbose, elevated/expert).

"What's going on right now?": /status, /context, /session, /whoami, /id, /usage — show running models, what the AI's seeing in this chat, who you are, and how much you've spent.

Inspect active model and tasks, effective prompt and policies for the current agent, session/thread binding, identity and channel info, and runtime usage/limits.

One-click prompts and side questions: /summarize, /translate, /code, /explain, /fix, /review, /brainstorm, /proscons, /side, /btw — pre-shape the next turn or ask a side question without interrupting the main task.

Single-shot prompt templates plus two aliases for a side-question turn. Useful before piping a paragraph, snippet, or attached file.

What the AI knows about you: /memory — see the saved facts. Edit them in Knowledge > Memory.

Inspect the assistant's stored memory facts. Extract policy and per-fact controls live under Knowledge > Memory.

Index and maintain local sources: /ingest, /ingested, /forget, /watch, /unwatch — add a file/folder, list indexed sources, remove matching sources, or start/stop folder watching.

Shortcuts into the Documents ingestion and watched-folder pipeline. Use /ingested to verify state before relying on retrieval.

What tools/extensions are available: /tools, /commands, /plugins, /mcp, /hooks, /orders, /tasks — list everything the AI can use right now.

List active-agent tools, all slash commands, installed ClawHub packages, connected MCP servers, active hooks, standing orders, and scheduled tasks.

Find capabilities and protect work: /find, /recommend, /snapshot, /rollback — search Skills/MCP, surface capability gaps, snapshot a directory, or restore the latest snapshot.

Registry discovery and workspace recovery controls for tool-assisted sessions. A snapshot is a safety checkpoint, not a replacement for a normal backup.

Track follow-ups and reuse chat setup: /commitments, /commit, /preset — list inferred commitments, add one manually, or save/apply/list per-chat configuration presets.

Conversation-level follow-up tracking and reusable chat configuration, separate from the app-wide Work Modes hub.

Multi-agent control: /agent, /agents, /subagents, /focus, /unfocus, /steer, /queue, /kill — turn agent mode on, hand off to another agent, focus on one task, or stop a runaway agent.

Toggle agent mode, manage agents and sub-agents, focus/unfocus a task, redirect to another agent or mode, switch queue mode, or terminate a session.

Granting and limiting power: /approve, /exec, /acp, /allowlist, /activation — say yes/no to pending tool approvals, run a shell command, or change who's allowed to DM the assistant.

Resolve pending exec/tool approvals, configure exec policy or run a shell command, edit ACP policies, manage DM/channel allowlists, or change channel activation policy.

Outbound and live audio: /send messages another channel, /vc manages voice chat, /restart restarts what's running.

/send targets a channel; /vc shows or manages voice-channel status; /restart restarts the active runtime or connector.

Run System > Health first. Then switch the backend back to Automatic and remove any custom command-line flags. Most "won't start" issues are missing dependencies or a bad flag.

Check System > Health (Diagnostics + Doctor), instance diagnostics, System > Logs, dependency status, model format vs. backend choice, custom args, and port conflicts. Use Automatic backend and clear custom args to reduce variables.

Make sure at least one instance is running and that whatever app is calling Ai Keeper is using the proxy URL (the one that ends in /v1).

Verify a ready instance, proxy enabled, route exists, API key correct, client targeting the proxy base URL. Inspect endpoint/status/latency in System > Requests.

Bump up the max output tokens setting. Also check if you accidentally turned on /fast mode, which keeps replies brief.

Increase max output tokens; check for active fast/terse modes; inspect stop sequences and structured-output constraints.

The AI is stuck in a loop. Try raising the Repetition Penalty in settings. Don't go too high or it'll start dropping necessary words.

Increase repetition penalty; adjust frequency/presence penalties for loops. For code, avoid excessive penalties — they break required syntax. Lower temperature only if randomness is the actual issue.

The AI tried to use a tool but couldn't. Type /tools to see what's actually available, then check if you've approved the tool and whether the right model family is selected.

Audit tool policy, parser, model family alignment, MCP server state, approval queue, and per-surface web/tool-execution permissions. Use /tools, the MCP tabs, and request logs.

Search for the fact in Documents or Wiki first. If it is there, check Wiki Health: stale snapshots, deleted sources, and broken current-truth pointers are deliberately withheld instead of being returned as current facts.

Separate indexing from eligibility before tuning ranking. Verify an Embedding-role runtime and manual search; run Wiki Health lint; resolve missing dates, stale observations, invalid pointers, and retired/deleted sources. Only then tune Top-K or chunk size/overlap and re-index the affected corpus.

Open the affected claim and check its source. Re-observe it if it is still true, point it at a reliable current source, or retire it if it should no longer be used.

Knowledge > Wiki > Health reports volatile claims without time semantics, snapshots without dates, observations older than their freshness window, and unresolved pointers. Use Re-observe now, Use source pointer, or Retire; each correction preserves the prior revision.

The original note changed after Ai Keeper last read it. Reconcile the vault, compare the newer note with your Wiki edit, then try again only after deciding which content should win.

Write-back compares the current note hash with the last imported source hash and fails closed on a mismatch. Use Reconcile Wiki Now or wait for Watch and schedule, review the refreshed page, and make a new deliberate edit; do not bypass the conflict check.

Stop any models you're not using right now. Don't keep three big models warm if you only need one.

Stop unused instances, lower context window, reduce cache budgets, enable KV cache quantization, lower idle threshold, or enable auto-unload on critical pressure.

Pause it. Open the Audit Trail to see what it actually did. Re-test the same task manually before turning it back on.

Pause the job, inspect Audit Trail, review standing orders/hooks, check workspace safety settings, require approvals for external side effects. Prototype manually before re-enabling.

A connector (Slack, Telegram, etc.) isn't getting messages. Check that the connector is on, the URL/token is right, and look at Channel Health.

Verify connector enabled state, transport, webhook URL, verify token, server URL, workspace/channel IDs, and Channel Health Monitor state. Cross-check inbound traffic in shared Inbox.

Another Mac can't reach this one. Make sure Server mode is on, the API key matches, and your firewall isn't blocking the port.

Confirm Server mode, management URL, Allow Client Access toggle, matching API key, firewall/network reachability, and port. Keep Web Tool Execution off unless explicitly required.