Rtk
por star
Aplicación
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
§01 · Proyectos
Proyectos.
Plugins Filament, paquetes Laravel y starter kits open source mantenidos activamente. Todo MIT, con releases para v3, v4 y v5 cuando aplique.
§02 · catálogo
Headroom
por star
Docker
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.
Jcodemunch Mcp
por star
Docker
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.
Openwolf
por star
Paquete JavaScript
One project memory across Claude Code, Codex and OpenCode. Token usage measured, not estimated. Zero API calls.
Tailwind
React
Token Optimizer
por star
Aplicación
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Claude Token Optimizer
por star
Paquete JavaScript
Cut Claude Code token usage by 90% — real token counts, optimized project setup
Token Optimizer Mcp
por star
Paquete JavaScript
Audit net MCP context avoided per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients
Ctrlb Decompose
por star
Aplicación
LLM-ready reasoning surface over logs
Th0th
por star
Docker
th0th - Ancient knowledge keeper for modern code. Semantic search with 98% token reduction
§03 · contribuir
Contribuye, reporta issues, abre PRs.
Todos los paquetes tienen CI, tests Pest e issues abiertas marcadas con good first issue.