Bảng xếp hạng repo GitHub theo sao, tốc độ tăng trưởng và mức độ hoạt động.

• rtk-ai

  #1rtk-ai/rtk

  CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

  Rust79.860 saopush cuối 10 giờ trước
• headroomlabs-ai

  #2headroomlabs-ai/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.

  Python71.398 saopush cuối 13 giờ trước
• yvgude

  #3yvgude/lean-ctx

  LeanCTX — Context Intelligence for AI systems.

  Rust3.761 saopush cuối 21 giờ trước
• jgravelle

  #4jgravelle/jcodemunch-mcp

  Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

  Python2.680 saopush cuối 15 giờ trước
• Paritok-official

  #5Paritok-official/paritok-4b-v1

  Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

  Python1.451 saopush cuối 8 giờ trước
• crwdla

  #6crwdla/tokentab

  A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.

  Python267 saopush cuối 4 ngày trước
• activeing123

  #7activeing123/mcptoon

  MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax

  HTML195 saopush cuối 4 giờ trước

#	Repo	Ngôn ngữ	Sao	Xu hướng 30 ngày	Cập nhật lần cuối
1	rtk-ai rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies	Rust	79.860		push cuối 10 giờ trước
2	headroomlabs-ai headroomlabs-ai/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.	Python	71.398		push cuối 13 giờ trước
3	yvgude yvgude/lean-ctx LeanCTX — Context Intelligence for AI systems.	Rust	3.761		push cuối 21 giờ trước
4	jgravelle jgravelle/jcodemunch-mcp Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.	Python	2.680		push cuối 15 giờ trước
5	Paritok-official Paritok-official/paritok-4b-v1 Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.	Python	1.451		push cuối 8 giờ trước
6	crwdla crwdla/tokentab A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.	Python	267		push cuối 4 ngày trước
7	activeing123 activeing123/mcptoon MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax	HTML	195		push cuối 4 giờ trước

Tất cả · 11.658