PyPI
MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Apache-2.028 ago 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#token-savings
Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.
8 registros
PyPI · npm
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.
Licencia propia16 jul 2026 · métricas 2.10.0
npm · crates.io
GlitterKill/sdl-mcp
Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.
Licencia propia17 jul 2026 · métricas 2.10.0
Go
enola-labs/enola
Architecture intelligence for developers, coding agents, and CI - understand codebases, analyze change impact, and catch architectural regressions.
Apache-2.06 sept 2026 · métricas 2.10.0
npm · PyPI
PsYcGoD/sage
SAGE — Save AI coding tokens by compressing terminal output, keeping raw logs local, and tracking real savings. 🧠S.A.G.E - Smart Agent Guidance Engine for AI coding assistants. by⚡ PsYc+GoD AI&ML 🤖 | IF YOU DONOT USE SAGE RUN install or PYTEST. SAGE WILL NOT ACTIVATE IN YOUR LOCAL ENVIORMENT.
MIT5 sept 2026 · métricas 2.10.0
npm
Houseofmvps/codesight
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
MIT28 ago 2026 · métricas 2.10.0
npm
jefuriiij/synthra
Make Claude Code cheaper and sharper on your codebase — a code graph that cuts token spend, smart per-task model routing, branch-aware memory, and a live token dashboard. Local, no telemetry.
MIT18 jul 2026 · métricas 2.10.0
Go
k1lgor/GoMem
Go single-binary persistent memory for AI coding agents. Saves 90-98% tokens vs re-reading files. CLI-first, full-text search, agent-agnostic.
MIT27 jul 2026 · métricas 2.10.0