Rtk
via star
Aplicação
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
§01 · Projetos
Projetos.
Plugins Filament, pacotes Laravel e starter kits open source mantidos ativamente. Tudo MIT, com releases para v3, v4 e v5 quando aplicável.
§02 · catálogo
Headroom
via 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
via 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
via star
Pacote JavaScript
One project memory across Claude Code, Codex and OpenCode. Token usage measured, not estimated. Zero API calls.
Tailwind
React
Token Optimizer
via star
Aplicação
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Claude Token Optimizer
via star
Pacote JavaScript
Cut Claude Code token usage by 90% — real token counts, optimized project setup
Token Optimizer Mcp
via star
Pacote 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
via star
Aplicação
LLM-ready reasoning surface over logs
Th0th
via star
Docker
th0th - Ancient knowledge keeper for modern code. Semantic search with 98% token reduction
§03 · contribuir
Contribua, reporte issues, abra PRs.
Todos os pacotes têm CI, testes Pest e issues abertas marcadas com good first issue.