Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.
제작자가 쓴 설명
Compression V2 cuts coding-agent token bills by 15-20% in production, and by 50% on SWE-bench Lite in our published benchmark. Three techniques across two layers: sharper tool result trimming, new task-aware tool surface reduction, and output brevity. Drop-in for Claude Code, Codex, OpenCode, and Cursor. We benchmarked Codex alone against Codex routed through Edgee's compression gateway on the same repo, with the same model, under the same workflow.
반응 (4)
비슷한 프로덕트
설명이 비슷한 순
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!
- Hacker News
- 14점
- Product Hunt
- 반응 없음
- GitHub
- 반응 없음
Graft
Claude Code hooks that cut grep tokens by 42%
- Hacker News
- 39점
- Product Hunt
- 반응 없음
- GitHub
- 스타 11,131
headroom
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.
- Hacker News
- 반응 없음
- Product Hunt
- 반응 없음
- GitHub
- 스타 79,067
Save Claude tokens with semantic search powered by SQLite and Ollama
Save 30% token costs when using Claude Code, Codex, OpenCode for free - with open source, local semantic search. Works for small and large codebases and monorepos! Enterprise-ready and fully compliant via Ollama and SQLite-vec.
- Hacker News
- 10점
- Product Hunt
- 반응 없음
- GitHub
- 스타 317
Boxes.dev
ditch localhost; run Claude Code and Codex in the cloud
- Hacker News
- 105점
- Product Hunt
- 추천 113
- GitHub
- 반응 없음
