Live usage tracking
Tracks Claude usage in real time, including the 5-hour usage window, weekly limits, remaining budget, and reset times.
Recall is a Chrome extension for Claude.ai that tracks context usage, quota limits, and truncation risk in real time to help you summarize or restart chats before replies degrade.
Recall is a Chrome extension for Claude.ai that monitors context window health and usage limits while you chat. It is designed to show how much of your current conversation budget remains, when limits reset, and when a thread is getting close to the point where responses may shorten or truncate.
The extension focuses on practical warning signs rather than after-the-fact reporting. It tracks live usage, estimates context fill, flags prompts that may be too large, and suggests when to summarize or start a fresh chat. The product page says it supports Claude Free, Pro, Max 5x, Max 20x, Team, and Enterprise, and that it runs locally in the browser without servers or accounts.
Tracks Claude usage in real time, including the 5-hour usage window, weekly limits, remaining budget, and reset times.
Estimates how full the current conversation is so you can tell when context is getting close to the limit before response quality drops.
Warns before large prompts are sent when the request is likely to produce a truncated response.
Shows per-turn token information such as input tokens, output tokens, conversation growth, and estimated quota impact.
Suggests when to summarize and move to a new chat as a conversation approaches the context limit.
Predicts whether a prompt is likely to generate a Small, Medium, Large, or XL response based on usage patterns and conversation state.
Keep an eye on session and weekly limits while working in a long Claude thread so you can avoid hitting a warning or cutoff mid-task.
Check whether a prompt is likely to trigger a short or truncated response before sending it, especially when the request is large or complex.
Watch how attachments, tools, models, and projects affect usage so you can understand what is consuming quota inside a conversation.
Decide when to summarize the thread and continue in a new chat as the conversation gets close to the context limit.
Use the local browser-based tracker in environments where keeping processing on-device matters more than sending chat data to a separate service.
Yes. The page says Recall supports Claude Free, Pro, Max 5x, Max 20x, Team, and Enterprise, and it automatically adapts to the limits available on each plan.
The page says Recall runs locally in the browser using lightweight DOM observation and background processing, with no impact on Claude performance or response speed.
No. The product page states that everything runs locally on the device, with no servers, no account, and no tracking.
The page says the estimates are typically within 3–5% of actual usage and that Recall calibrates against observed usage patterns over time.
Yes. The page says project knowledge tokens are tracked separately so users can see how Claude Projects affect overall usage.
Benchspan is an AI agent security platform that discovers agents, blocks prompt injection and data exfiltration in real time, and supports pre-launch red teaming. It is aimed at teams running agents in production and includes Python and TypeScript SDKs.
PromptScout tracks how ChatGPT, Gemini, Google AI Overviews, and Perplexity mention your brand or competitors, then pairs those results with source analysis and website audits. It helps teams decide what to fix in content, positioning, or site readiness next.
Sleek Analytics is a privacy-friendly web analytics tool with real-time visitor tracking, Core Web Vitals, and revenue attribution. It helps site owners understand traffic and conversions without cookie banners or a heavy setup.
MacSpoof is a macOS MAC address changer that lets you change or randomize your Wi‑Fi MAC to reconnect and limit device logging on public Wi‑Fi.
ClawTick is an AI agent automation platform for scheduling jobs from the CLI, dashboard, or REST API. It is aimed at developers and teams running LangChain, CrewAI, webhook, or custom agent workflows that need monitoring, alerts, and logs.
OpenFlags is an open-source, self-hosted feature flag platform for modern JavaScript teams. It supports local evaluation, targeted rollouts, and controlled launches while keeping flag data in your own infrastructure.