← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

headroom

github.com

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

LibraryOpen source

Visit github.comexternal siteGitHub79,067 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. Token compression CLI to save Codex/Astra costs

    Yolanda and Spencer here - wanted to share a token compression tool that we’ve built for ourselves to save 30% costs on codex!

    news.ycombinator.comCLIlatest reaction

    Hacker News
    14 pts
    Product Hunt
    No reaction
    GitHub
    No reaction

  2. SigMap

    81.1% retrieval hit 5, 96.9% token reduce,zero deps

    github.comCLIOpen source2 reactionslatest reaction

    Hacker News
    14 pts
    Product Hunt
    No reaction
    GitHub
    646 stars

  3. Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens

    Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

    github.comCLIOpen source2 reactionslatest reaction

    Hacker News
    10 pts
    Product Hunt
    No reaction
    GitHub
    32 stars

  4. Min.js style compression of tech docs for LLM context

    Min.js Style Compression of Tech Docs for LLM Context

    github.comOpen source2 reactionslatest reaction

    Hacker News
    177 pts
    Product Hunt
    No reaction
    GitHub
    671 stars

  5. Edgee Codex Compressor V2

    Use Codex at 35.6% lower costs

    edgee.ai4 reactionslatest reaction

    Hacker News
    No reaction
    Product Hunt
    212 votes
    GitHub
    No reaction