cache-assembler

What it does

cache-assembler fixes prompt-cache invalidation for Claude Code and the Anthropic API. The cache only hits on byte-identical requests, but real traffic breaks that: inconsistent tool-schema ordering, session data leaking into prompts, concurrent requests racing to write the same entry. This proxy fixes all three, with a dedicated Claude Code preset. Measured against the real API (not synthetic): 8.2x cost reduction, $1.33 to $0.16 per 100-turn session. MIT licensed, zero dependencies.

Fixes broken prompt-caching for Claude Code and the Anthropic API - 8.2x cheaper - nash-software/cache-assembler

Rewrites Anthropic Messages API requests for maximal prompt-cache reuse - a small, dependency-free library and standalone proxy that makes your requests' cacheable prefix stay byte-identical across turns, so Anthropic's prompt cache actually hits. TL;DR: Claude's API can serve part of a request from a cheap cache instead of full price - but only if the request bytes match exactly, every time. Most real usage doesn't hit that bar without help. This tool sits in front of the API, fixes the things that normally break the match, and measurably cut one real workload's cost by 8.2x. MIT licensed, no dependencies, and every number in the linked report is reproducible with your own API key.…from github.com

• 
  Send Claude Code tasks to the Batch API at 50% offFeb 2026 · github.com · ▲23

  Hey HN. I built this because my Anthropic API bills were getting out of hand (spoiler: they remain high even with this, batch is not a magic bullet). I use Claude Code daily for software design and infra work (terraform, code reviews, docs). Many Terminal tabs, many questions. I realised some questions are ok to wait on and with that comes some cost savings. So here is a small MCP that lets you send work directly to Anthropic's Batch API from inside Claude Code, for the same quality responses just 50% cheaper, results come back in ~30min-1hr. How it works: you type /batch review this…

• 
  CodeBurn – Analyze Claude Code token usage by taskApr 2026 · github.com · ▲112

  Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level. CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved). One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was…

• 
  Cached Claude APIJun 2026 · claude.sell.app · ▲2

  Cut Claude API costs by 90% via active prompt caching.

• 
  toktrackFeb 2026 · github.com · ▲68

  Did you know Claude Code deletes your session data after 30 days? I found out the hard way when I tried to check my spending history. My session files hit 3GB (2000+ files) and existing tools took 40+ seconds. Rewrote it in Rust with simd-json + rayon. - First run: ~1s (vs 40s+) - Daily use: ~0.04s (1000x faster, cached) - TUI dashboard with daily/weekly/monthly breakdown - Supports Claude Code, Codex CLI, Gemini CLI - Persistent cache — history survives even after CLI deletes files GitHub: https://github.com/mag123c/toktrack Feedback welcome!

• RC
  Reduce ChatGPT costs 10x with distributed cache for LLMs2024 · edgematic.dev · ▲22

  Hello HN! We're building a caching solution for LLMs (ChatGPT, Claude). By combining cutting-edge approaches, such as edge computing, prompt compression, vectorization, and others - it can reduce your AI bills by up to 10x and significantly lower response times. Key Features: - cost efficiency: our system stores frequent queries, reducing the number of upstream (paid) API calls - fast responses: with various nodes globally, we reduce latency by serving data from the nearest location - scalability: designed to handle increasing loads and data sizes without degrading performance. The cache…

• 
  ClawPool – Pool Claude tokens to make $$$ or crazy cheap Claude CodeFeb 2026 · clawpool.ai · ▲21

  I built a pool-based proxy that hacks Claude Code's pricing tiers. To actually use Claude Code you need Max at $200/mo, and then most of that capacity sits idle anyway. So ClawPool lets subscribers pool their OAuth tokens and earn up to $120/mo from the spare capacity. Everyone else gets Opus, Sonnet, all models for $8/mo. Setup — they actually support proxies themselves via standard env params: export ANTHROPIC_AUTH_TOKEN="your-pool-key" export ANTHROPIC_BASE_URL="https://proxy.clawpool.ai" claude

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• TL
  The load-bearing vocabulary of Claude▲710

  Life & fun · Aug 2026 · louisabraham.github.io

• 
  Hey Noah▲656

  A proactive AI executive assistant for founders

  AI · Aug 2026 · heynoah.io

• 
  Clipto MCP▲655

  Hey HN, We recently built Clipto. It’s a tool that lets you search over terabytes of video, audio, and images on your computer, without relying on the cloud. Motivation: we probably all had this similar experience, we know a moment exists in a video or audio, but finding it takes hours scrubbing the timeline. You can send all the media to process in the cloud, but it’s slow, expensive and raises privacy concerns. So we decided to build our own on-device media search engine. How it works (high level): 1. We ingest video, audio, image; normalize formats via ffmpeg; run content analysis to…

  Work · Aug 2026 · clipto.com

• 
  Simple algorithm and color space to generate diverse skin tones▲627

  Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…

  Life & fun · Aug 2026 · toneyalexander.github.io

• 
  AdAnt AI▲620

  Claude for viral, high-converting social ads

  AI · Aug 2026 · adant.ai

• 
  Astute▲606

  Automate your B2B brand going viral, with new media creators

  AI · Aug 2026 · company-app.joinastute.com