Token efficiency: tools for developers

Tools that reduce token costs, compress context or cache LLM requests. An entry can appear under several use cases when its topics or description provide several explicit signals.

Use case

Activity

Sort by

90 entries in this view.

Tool ranking

Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1

    Other
    Dormant

    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.

    TypeScriptLicense: MIT
    • agent-coordination
    • agent-to-agent
    • ai-protocol
    • ddd
    • grpc

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  2. 2

    CLI
    Active

    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.

    PythonLicense: MIT
    • claude
    • claude-code
    • claude-code-skills
    • cli
    • cost-optimization

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  3. 3

    Skill
    Active

    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).

    PythonLicense: MIT
    • claude
    • claude-ai
    • claude-code
    • claude-code-plugin
    • claude-code-skill

    githubmeasured growthOpen source ↗

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

    1GitHub starsstable
  4. 4

    MCP
    Active

    Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.

    ↓ 27 downloads/weekJavaScriptLicense: MIT

      mcpmeasured growthOpen source ↗

      Install claude mcp add comparedge-llm-cost -- npx @comparedge/llm-cost-mcp

      2GitHub starsstable
    • 5

      MCP
      Active

      Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen

      ↓ 53 downloads/weekRustLicense: NOASSERTION

        mcpmeasured growthOpen source ↗

        Install claude mcp add vision-squeezer -- npx vision-squeezer

        2GitHub starsstable
      • 6

        Agent
        Active

        Agent context compressor and memory persistent orchestration

        TypeScriptLicense: Apache-2.0
        • a2a-protocol
        • agent-framework
        • ai
        • ai-agents-framework
        • ai-tools

        githubmeasured growthOpen source ↗

        2GitHub starsstable
      • 7

        Other
        Active

        Claude Code skill: reduce token usage 60-80% — targeted reads, model switching, context management. One-line install.

        License: MIT
        • ai-tools
        • claude-code
        • claude-code-skill
        • llm
        • productivity

        githubmeasured growthOpen source ↗

        2GitHub starsstable
      • 8

        Other
        Active

        Turn your strongest model into a conductor: route each step to the cheapest capable model, and escalate only load-bearing pieces to a pricier reviewer that catches pitfalls early. Subscription, API, or hybrid.

        ShellLicense: MIT
        • ai-coding
        • claude
        • claude-code
        • claude-code-skill
        • cost-reduction

        githubmeasured growthOpen source ↗

        2GitHub starsstable
      • 9

        Skill
        Active

        🤫 Claude shuts up until it's done. A Claude Code plugin: one short answer at the end, the file to open, and no log dumps in your chat.

        JavaScriptLicense: MIT
        • adhd
        • agent-skills
        • ai
        • anthropic
        • claude

        githubmeasured growthOpen source ↗

        Install /plugin marketplace add V-Songbird/hush

        49GitHub stars+5 (+11.4 %)
      • 10

        MCP
        Active

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

        ↓ 19 downloads/weekTypeScriptLicense: NOASSERTION

          mcpmeasured growthOpen source ↗

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

          0GitHub starsstable
        • 11

          Skill
          Active

          Claude Code skill: caveman-style token efficiency, spoken with a real Spanish regional accent

          JavaScriptLicense: MIT
          • agent-skills
          • ai-agents
          • anthropic
          • claude-code
          • claude-code-plugin

          githubmeasured growthOpen source ↗

          Install /plugin marketplace add Mun1to/SpanishCaveMan

          2GitHub starsstable
        • 12

          Skill
          Dormant

          ⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

          PythonLicense: MIT
          • ai-tools
          • bm25
          • claude-code
          • claude-code-plugin
          • context-compression

          githubmeasured growthOpen source ↗

          Install /plugin marketplace add Madhan230205/token-reducer

          44GitHub starsstable
        • 13

          MCP
          Active

          Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.

          JavaScriptLicense: MIT

            mcpmeasured growthOpen source ↗

            Install claude mcp add gate402-mcp -- npx gate402-mcp

            2GitHub starsstable
          • 14

            MCP
            Active

            Persistent memory for any AI — zero token cost until recall

            RustLicense: Apache-2.0

              mcpmeasured growthOpen source ↗

              44GitHub starsstable
            • 15

              MCP
              Active

              Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads

              PythonLicense: MIT

                mcpmeasured growthOpen source ↗

                Install claude mcp add densely -- uvx densely

                6GitHub starsstable
              • 16

                Other
                Dormant

                Translate any language to English before Claude processes it. ~49% token savings combined with caveman.

                PythonLicense: MIT
                • claude-code
                • claude-code-skill
                • developer-tools
                • llm
                • multilingual

                githubmeasured growthOpen source ↗

                2GitHub starsstable
              • 17

                Skill
                Dormant

                Claude Code plugin that offloads large outputs to filesystem and retrieves when required.

                Python
                • ai-agents
                • claude-code
                • claude-code-hooks
                • claude-code-plugin
                • claude-code-plugins

                githubmeasured growthOpen source ↗

                Install /plugin marketplace add sheeki03/Few-Word

                38GitHub starsstable
              • 18

                Skill
                Active

                A Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.

                PythonLicense: MIT
                • agent-skills
                • anthropic
                • claude-code
                • claude-code-plugin
                • claude-code-skills

                githubmeasured growthOpen source ↗

                Install /plugin marketplace add Jimmynycu/token-efficiency

                2GitHub starsstable
              • 19

                MCP
                Dormant

                Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

                PythonLicense: MIT
                • claude
                • claude-code
                • claude-code-plugin
                • cli
                • context-window

                githubmeasured growthOpen source ↗

                35GitHub starsstable
              • 20

                MCP
                Dormant

                Save tokens while coding — your AI agent gets structured code context, not file dumps.

                ↓ 67 downloads/weekTypeScriptLicense: Apache-2.0

                  mcpmeasured growthOpen source ↗

                  Install claude mcp add codeweave -- npx @codeweave/mcp

                  4GitHub starsstable
                • 21

                  Skill
                  Dormant

                  Convert long AI conversations into portable conversation state graphs for LLM handoffs.

                  License: MIT
                  • age
                  • agent
                  • ai
                  • chatgpt
                  • claude-ai

                  githubmeasured growthOpen source ↗

                  Install git clone https://github.com/Adityapal67/context-graph-compressor ~/.claude/skills/context-graph-compressor

                  35GitHub starsstable
                • 22

                  MCP
                  Active

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

                  ↓ 27 downloads/weekPythonLicense: MIT

                    mcpmeasured growthOpen source ↗

                    Install claude mcp add compactprompt -- uvx compactprompt

                    0GitHub starsstable
                  • 23

                    MCP
                    Active

                    Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.

                    ↓ 98 downloads/weekJavaScriptLicense: MIT

                      mcpmeasured growthOpen source ↗

                      Install claude mcp add smart-context-mcp -- npx smart-context-mcp

                      4GitHub starsstable
                    • 24

                      Skill
                      Active

                      Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our…

                      JavaScriptLicense: MIT
                      • ai-agents
                      • anthropic
                      • claude
                      • claude-ai
                      • claude-code

                      githubmeasured growthOpen source ↗

                      Install /plugin marketplace add sup3x/claude-code-eco

                      33GitHub starsstable
                    • 25

                      MCP
                      Active

                      Compact, source-linked context packs that reduce token waste for coding agents.

                      TypeScriptLicense: MIT

                        mcpmeasured growthOpen source ↗

                        Install claude mcp add capsule -- npx capsulectx

                        4GitHub starsstable