Understand and reduce token usage with ContextSpy context profiler
Most devs using AI coding tools don't even imagine how much information they put in the context window - tools, MCPs, tool responses, active skills - all of which take up some real estate. Sometimes updating a tool description or trimming api response can give significant savings - and profiler helps to measure that
Understand and reduce token usage with ContextSpy context profiler launched on June 15, 2026 with 6 votes, #2,066 of 22,647 launches that month and more than 75% of that year's launches.
What it does
Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs - RimantasZ/contextspy
ContextSpy is a context window profiler for large language models and common agentic AI coding tools. It is used to intercept requests to an LLM API, analyze and visualize prompt composition, and track context changes between multiple requests in the same session. Modern AI coding agents (GitHub Copilot, Claude Code, opencode, etc.) pack a lot into each LLM request: system prompts, tool definitions and results, file contents, conversation history. It's often unclear why a session is slow, expensive, or hitting the context limit. ContextSpy makes the invisible visible - you see a live breakdown of every token category for every request, across sessions, over time. Think of your favorite CPU…from github.com
Does a similar job
all alternatives →
Context GatewayMar 2026 · github.com · ▲220We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window. Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s. Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M…
- IBI built a more productive way to manage AI chats2025 · contextch.at · ▲162
I released ContextChat, an AI chat designed to be context-centric, helping you stay focused and productive by giving you control over the information your AI sees. You can import websites, files, and public/private GitHub repos to give the AI full knowledge of your projects. Unlike other chatbots, ContextChat lets you easily switch between project contexts, so you get relevant answers and avoid the noise. It's pay-per-use, giving you flexibility and control over costs and free models are available so you can try it for free with no monthly subscriptions. Let me know your feedback!
OpenBrowser-AIApr 2026 · openbrowser.me · ▲76Your AI agent is burning 6x more tokens than it needs to just to browse the web. We built OpenBrowser MCP to fix that. Most browser MCPs give the LLM dozens of tools: click, scroll, type, extract, navigate. Each call dumps the entire page accessibility tree into the context window. One Wikipedia page? 124K+ tokens. Every. Single. Call. OpenBrowser works differently. It exposes one tool. Your agent writes Python code, and OpenBrowser executes it in a persistent runtime with full browser access. The agent controls what comes back. No bloated page dumps. No wasted tokens. Just the data your…
Context Compass2025 · chromewebstore.google.com · ▲16I built a small Chrome extension for people who write long conversations in Claude and don’t want to unexpectedly hit the 200,000-token limit. Context Compass automatically counts words and estimates token usage as you write. It updates in real time, gives you a visible percentage bar, and helps power users manage sprawling chats without losing work or flow. I built it because I kept getting the “max context” error and realized there was no way to track usage in Claude. No signups, no tracking, just a simple install. Would love any feedback or ideas for improvements. Thanks!
Context Mode InsightJun 2026 · context-mode.com · ▲24An open-source MCP plugin (300,000+ developers) and a commercial Platform that builds Solutions on top. context-mode keeps raw data out of the LLM context window. Insight surfaces what your team is doing with the saved tokens.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com