Token efficiency: tools for developers

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

   voly

   Agent

   ActiveLast commit 1 day ago · 2026-09-03

   Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

   PythonLicense: Apache-2.0

   • a2a
   • ag-ui
   • agentic-ai
   • ai-agents
   • ai-coding

   githubcreated 2 months agomeasured growthOpen source ↗

   16GitHub starsstable
2. 2

   MCP Surface Lint

   MCP

   ActiveLast commit today · 2026-09-03

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

   TypeScript

   mcpcreated 53 days agomeasured growthOpen source ↗

   Remote server, to be declared in the MCP configuration https://mcplint-web.vercel.app/api/mcp

   0GitHub starsstable
3. 3

   token_consumer

   CLI

   ActiveLast commit 7 days ago · 2026-08-28

   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

   githubcreated 38 days agomeasured growthOpen source ↗

   1GitHub starsstable
4. 4

   Spiderbrain-V3

   Skill

   DormantLast commit 3 months ago · 2026-06-04

   SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.

   • agent-skills
   • ai
   • ai-agents
   • anthropic
   • claude

   githubcreated 3 months agomeasured growthOpen source ↗

   Install git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V3

   65GitHub starsstable
5. 5

   permafrost

   Skill

   ActiveLast commit 2 months ago · 2026-06-23

   Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

   PythonLicense: MIT

   • cache-optimization
   • claude-code
   • claude-code-plugin
   • cost-optimization
   • deepseek

   githubcreated 2 months agomeasured growthOpen source ↗

   Install /plugin marketplace add jianzhichun/permafrost

   21GitHub starsstable
6. 6

   usage-aware-claude-statusline

   CLI

   ActiveLast commit 2 months ago · 2026-06-29

   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…

   Python

   • ccusage-alternative
   • claude-code
   • claude-code-skills
   • claude-code-statusline
   • context-window

   githubcreated 2 months agomeasured growthOpen source ↗

   1GitHub starsstable
7. 7

   somtum

   Skill

   ActiveLast commit 54 days ago · 2026-07-12

   Local-first memory and prompt-cache layer for Claude Code

   TypeScriptLicense: MIT

   • agentic-ai
   • agentic-coding
   • ai
   • ai-agents
   • anthropic

   githubcreated 4 months agomeasured growthOpen source ↗

   Install /plugin marketplace add riz007/somtum

   7GitHub starsstable
8. 8

   bonsai

   Skill

   DormantLast commit 4 months ago · 2026-04-22

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

   JavaScriptLicense: MIT

   • benchmarking
   • bonsai
   • cursor
   • cursor-rules
   • developer-tools

   githubcreated 4 months agomeasured growthOpen source ↗

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

   0GitHub starsstable
9. 9

   ComparEdge LLM Cost

   MCP

   ActiveLast commit 55 days ago · 2026-07-10

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

   ↓ 27 downloads/weekJavaScriptLicense: MIT

   mcpcreated 55 days agomeasured growthOpen source ↗

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

   2GitHub starsstable
10. 10

    pdf-decompiler-mcp

    MCP

    ActiveLast commit 30 days ago · 2026-08-04

    A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token…

    JavaScriptLicense: AGPL-3.0

    • ai
    • ai-tools
    • claude
    • claude-code
    • claude-code-plugin

    githubcreated 4 months agomeasured growthOpen source ↗

    17GitHub starsstable
11. 11

    io.github.eralpozcan/vision-squeezer

    MCP

    ActiveLast commit 44 days ago · 2026-07-22

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

    ↓ 53 downloads/weekRustLicense: NOASSERTION

    mcpcreated 3 months agomeasured growthOpen source ↗

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

    2GitHub starsstable
12. 12

    webfetch

    Skill

    ActiveLast commit 43 days ago · 2026-07-23

    Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with…

    PythonLicense: MIT

    • agent-memory
    • agent-skills
    • agentic-workflow
    • agents
    • anthropic

    githubcreated 4 months agomeasured growthOpen source ↗

    Install git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch

    55GitHub starsstable
13. 13

    mcp-recall

    Skill

    ActiveLast commit 1 day ago · 2026-09-02

    mcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls per session for heavy MCP workloads.

    TypeScriptLicense: MIT

    • bun
    • claude
    • claude-code
    • claude-code-plugin
    • context-window

    githubcreated 6 months agomeasured growthOpen source ↗

    Install /plugin marketplace add sakebomb/mcp-recall

    8GitHub starsstable
14. 14

    io.github.JesusGarcia9009/lethe

    MCP

    ActiveLast commit 55 days ago · 2026-07-10

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

    PythonLicense: Unlicense

    mcpcreated 2 months agomeasured growthOpen source ↗

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

    0GitHub starsstable
15. 15

    cycgraph

    Agent

    ActiveLast commit today · 2026-09-03

    Agent context compressor and memory persistent orchestration

    TypeScriptLicense: Apache-2.0

    • a2a-protocol
    • agent-framework
    • ai
    • ai-agents-framework
    • ai-tools

    githubcreated 5 months agomeasured growthOpen source ↗

    2GitHub starsstable
16. 16

    lazy-cat

    Skill

    ActiveLast commit 2 months ago · 2026-06-11

    Claude Code skills for developers who code like cats — never more effort than the problem requires.

    JavaScriptLicense: MIT

    • ai-productivity
    • anthropic
    • cat
    • claude
    • claude-code

    githubcreated 3 months agomeasured growthOpen source ↗

    Install git clone https://github.com/albertobarnabo/lazy-cat ~/.claude/skills/lazy-cat

    50GitHub starsstable
17. 17

    lossless-code

    MCP

    DormantLast commit 3 months ago · 2026-05-16

    DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.

    PythonLicense: MIT

    • claude
    • claude-code
    • claude-code-plugin
    • coding-agent
    • context-management

    githubcreated 5 months agomeasured growthOpen source ↗

    15GitHub starsstable
18. 18

    catalyst

    Skill

    ActiveLast commit 2 days ago · 2026-09-01

    Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

    JavaScript

    • agent-memory
    • agentic-coding
    • ai-agents
    • ai-coding
    • claude-code-commands

    githubcreated 11 months agomeasured growthOpen source ↗

    Install /plugin marketplace add coalesce-labs/catalyst

    20GitHub starsstable
19. 19

    compactor-skill

    Other

    ActiveLast commit 2 months ago · 2026-06-15

    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

    githubcreated 4 months agomeasured growthOpen source ↗

    2GitHub starsstable
20. 20

    io.github.RudrenduPaul/tokentrust

    MCP

    ActiveLast commit 9 days ago · 2026-08-25

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

    TypeScriptLicense: Apache-2.0

    mcpcreated 54 days agomeasured growthOpen source ↗

    Install claude mcp add tokentrust -- uvx tokentrust-cli

    0GitHub starsstable
21. 21

    io.github.omkar9854/token_optimizer

    MCP

    ActiveLast commit 46 days ago · 2026-07-19

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

    ↓ 13 downloads/weekPythonLicense: Apache-2.0

    mcpcreated 46 days agomeasured growthOpen source ↗

    Install claude mcp add token_optimizer -- uvx slimctx

    1GitHub starsstable
22. 22

    claude-lean-skill

    Other

    ActiveLast commit 2 months ago · 2026-06-10

    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

    githubcreated 5 months agomeasured growthOpen source ↗

    2GitHub starsstable
23. 23

    token-reducer

    Skill

    DormantLast commit 4 months ago · 2026-05-02

    ⚡ 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

    githubcreated 5 months agomeasured growthOpen source ↗

    Install /plugin marketplace add Madhan230205/token-reducer

    44GitHub starsstable
24. 24

    basecamp

    Skill

    ActiveLast commit 24 days ago · 2026-08-11

    A production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.

    ShellLicense: MIT

    • ai-agents
    • claude
    • claude-code
    • claude-code-plugin
    • context-engineering

    githubcreated 2 months agomeasured growthOpen source ↗

    Install /plugin marketplace add janmaaarc/basecamp

    7GitHub starsstable
25. 25

    SpanishCaveMan

    Skill

    ActiveLast commit 22 days ago · 2026-08-13

    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

    githubcreated 30 days agomeasured growthOpen source ↗

    Install /plugin marketplace add Mun1to/SpanishCaveMan

    2GitHub starsstable