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.
- 1Active
llmtrim
MCPMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
mcpmeasured growthOpen source ↗
Install
claude mcp add llmtrim -- npx @llmtrim/cli222GitHub stars+6 (+2.8 %) - 2Active
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
mcpmeasured growthOpen source ↗
Install
claude mcp add smart-context-mcp -- npx smart-context-mcp4GitHub starsstable - 3Dormant
Save tokens while coding — your AI agent gets structured code context, not file dumps.
mcpmeasured growthOpen source ↗
Install
claude mcp add codeweave -- npx @codeweave/mcp4GitHub starsstable - 4Dormant
Analyze your MCP setup: token costs, grades, duplicates, and optimization tips
mcpmeasured growthOpen source ↗
Install
claude mcp add mcp-checkup -- npx mcp-checkup1GitHub starsstable - 5Active
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
mcpmeasured growthOpen source ↗
Install
claude mcp add agent-booster -- uvx agent-booster1GitHub starsstable - 6Active
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen
mcpmeasured growthOpen source ↗
Install
claude mcp add vision-squeezer -- npx vision-squeezer2GitHub starsstable - 7Active
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
mcpmeasured growthOpen source ↗
Install
claude mcp add compactprompt -- uvx compactprompt0GitHub starsstable - 8Active
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
mcpmeasured growthOpen source ↗
Install
claude mcp add comparedge-llm-cost -- npx @comparedge/llm-cost-mcp2GitHub starsstable - 9Active
MCP server that cuts AI coding agent token usage via framework-aware context optimization
mcpmeasured growthOpen source ↗
Install
claude mcp add ai-optimizer -- npx @ai-optimizer/core0GitHub starsstable - 10Active
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
mcpmeasured growthOpen source ↗
Install
claude mcp add token_optimizer -- uvx slimctx1GitHub starsstable - 11Active
rtk
CLICLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
githubmeasured growthOpen source ↗
78 349GitHub stars+703 (+0.91 %) - 12Active
headroom
MCPCompress 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.
githubmeasured growthOpen source ↗
68 629GitHub stars+784 (+1.2 %) - 13Active
Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add sofumel/claude-handoff-revive6GitHub starsstable - 14Active
catalyst
SkillToken-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add coalesce-labs/catalyst20GitHub starsstable - 15Active
Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads
mcpmeasured growthOpen source ↗
Install
claude mcp add densely -- uvx densely6GitHub starsstable - 16Active
laconic
SkillToken-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add GabrielBarberini/laconic19GitHub starsstable - 17Active
somtum
SkillLocal-first memory and prompt-cache layer for Claude Code
githubmeasured growthOpen source ↗
Install
/plugin marketplace add riz007/somtum7GitHub starsstable - 18Active
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…
githubmeasured growthOpen source ↗
17GitHub starsstable - 19Active
basecamp
SkillA production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add janmaaarc/basecamp7GitHub starsstable - 20Active
opencode-skill
SkillClaude Code skill — delegate coding tasks to Opencode, supervise via git diff & save 50-90% Claude token usage
githubmeasured growthOpen source ↗
Install
git clone https://github.com/pcx-wave/opencode-skill ~/.claude/skills/opencode-skill17GitHub stars+1 (+6.2 %) - 21Active
voly
AgentControl plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.
githubmeasured growthOpen source ↗
16GitHub starsstable - 22Active
mcp-recall
Skillmcp-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.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add sakebomb/mcp-recall8GitHub starsstable - 23Dormant
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.
githubmeasured growthOpen source ↗
15GitHub starsstable - 24Active
cc-hud
SkillCompact Claude Code statusline — zero-dependency, crash-free on Windows
githubmeasured growthOpen source ↗
Install
/plugin marketplace add WaterTian/cc-hud8GitHub starsstable - 25Active
better-compact
SkillStaged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add AshishKumar4/better-compact12GitHub stars+1 (+9.1 %)