Le descrizioni degli strumenti sono in inglese.

Efficienza dei token

Strumenti per ridurre i costi dei token e comprimere il contesto.

Utilizzo

Attività

Ordina per

101

Classifica degli strumenti

Classifica mista: la crescita misurata ha la precedenza. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1
    Attivo

    A skill that shrink noisy log/output 60-90% before read — filter, group, dedupe, truncate. Cut token, cut cost, keep signal. By Dhayalan (aka Joy).

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add Da-ya7/PromptCompressor-skill

    1stelle GitHubstabile
  2. 2
    Attivo

    Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  3. 3
    Dormiente

    Analyze your MCP setup: token costs, grades, duplicates, and optimization tips

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add mcp-checkup -- npx mcp-checkup

    1stelle GitHubstabile
  4. 4
    Attivo

    Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add agent-booster -- uvx agent-booster

    1stelle GitHubstabile
  5. 5
    Attivo

    Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add token_optimizer -- uvx slimctx

    1stelle GitHubstabile
  6. 6

    Altro
    Dormiente

    Agent-to-Agent coordination that doesn't waste your context window. Token-efficient protocol with progressive discovery, zero-schema invocation, gRPC transport, and task lifecycle management.

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  7. 7
    Attivo

    Usage-aware status line for Claude Code: session & weekly rate-limit gauges with reset countdowns and a precise context-window meter, plus tokens, git & weather. Template-driven and extensible — set it up by chatting with Claude or via a…

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  8. 8

    Skill
    Dormiente

    Agent context gate for Codex, Claude Code, Copilot, MCP, Cursor, Cline, Gemini and Windsurf repos

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/grnbtqdbyx-create/contextforge ~/.claude/skills/contextforge

    1stelle GitHubstabile
  9. 9

    MCP
    Attivo

    Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add distil -- npx @munhq/distil

    1stelle GitHubstabile
  10. 10

    Skill
    Attivo

    Cut Claude Code token costs by delegating bulk LLM work to cheap models. 600+ models via NanoGPT, OpenRouter, Groq or local Ollama — batched, resumable, with real per-call cost tracking.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add bicced/sidequest

    1stelle GitHubstabile
  11. 11

    Skill
    Dormiente

    Drop-in Cursor rules to cut AI response tokens (no filler/hedging, preserve code + technical strings). Includes local, reproducible benchmarks.

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/marcomondelli/bonsai ~/.claude/skills/bonsai

    0stelle GitHubstabile
  12. 12
    Attivo

    Statically audits MCP tool surfaces for token cost, schema quality, and design issues.

    mcpcrescita misurataApri fonte ↗

    Server remoto da dichiarare nella configurazione MCP https://mcplint-web.vercel.app/api/mcp

    0stelle GitHubstabile
  13. 13
    Attivo

    Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add tokentrust -- uvx tokentrust-cli

    0stelle GitHubstabile
  14. 14
    Attivo

    Context GC for LLM agents: offload large tool outputs and recall them to save tokens.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add lethe -- uvx lethe-llm-context

    0stelle GitHubstabile
  15. 15
    Attivo

    MCP server that cuts AI coding agent token usage via framework-aware context optimization

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add ai-optimizer -- npx @ai-optimizer/core

    0stelle GitHubstabile
  16. 16
    Attivo

    Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add compactprompt -- uvx compactprompt

    0stelle GitHubstabile
  17. 17

    Altro
    Attivo

    Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous…

    githubmomentum stimatoApri fonte ↗

    1 254stelle GitHub
  18. 18

    Skill
    Attivo

    The Agent Knowledge Kit & Architecture System — 10–32x token-efficient architecture discovery for AI coding agents

    githubmomentum stimatoApri fonte ↗

    Installa git clone https://github.com/chama-x/quiv ~/.claude/skills/quiv

    3stelle GitHub
  19. 19
    Attivo

    Installable agentic skills (SKILL.md) for Claude Code, Cursor, Codex, Gemini & Antigravity — 292+ product, efficiency, and common-sense skills. npx major-ai-skills

    githubmomentum stimatoApri fonte ↗

    Installa git clone https://github.com/alivirgo/Major-AI-Skills ~/.claude/skills/Major-AI-Skills

    1stelle GitHub
  20. 20

    Agente
    Attivo

    Experimental no-install semantic language for AI agents: typed action/state, safe NL/JSON fallback, and falsifiable public evals. Try the one-file probe.

    githubmomentum stimatoApri fonte ↗

    1stelle GitHub

Risorse didattiche e di riferimento

Classifica per crescita misurata e normalizzata tra le fonti. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

  1. 1
    AttivoApri fonte ↗

    A cheat sheet that stops AI agents from scanning your whole repo and saves you tokens.

    github

    Installa git clone https://github.com/toshon-jennings/SUMMARY-md ~/.claude/skills/SUMMARY-md

    Risorsacrescita misurata
    0stelle GitHubstabile

Elencati senza metrica pubblica

Classifica mista: la crescita misurata ha la precedenza. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1
    SconosciutoUltimo commit: non disponibile

    Semantic context compression and cognitive memory layer for LLM swarms.

    mcpmetrica non pubblicataApri fonte ↗

    Server remoto da dichiarare nella configurazione MCP https://recallmax-mcp.vercel.app/api/mcp

    Nessuna metrica pubblica disponibile
  2. 2

    MCP
    SconosciutoUltimo commit: non disponibile

    Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.

    mcpmetrica non pubblicataApri fonte ↗

    Nessuna metrica pubblica disponibile
  3. 3
    SconosciutoUltimo commit: non disponibile

    MCP server for Skim code transformation. Compresses code 60-95% for LLM context optimization.

    mcpmetrica non pubblicataApri fonte ↗

    Installa claude mcp add skim-mcp-server -- npx skim-mcp-server

    Nessuna metrica pubblica disponibile
  4. 4
    SconosciutoUltimo commit: non disponibile

    LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.

    mcpmetrica non pubblicataApri fonte ↗

    Server remoto da dichiarare nella configurazione MCP https://cache.api.ainode.tech/mcp

    Nessuna metrica pubblica disponibile