|
SuperLeanAI — Prompt Compression & Token Efficiency Proxy
SuperLeanAI is a prompt compression and context compression proxy for AI coding agents: it debloats verbose tool definitions, MCP server schemas, and Skills...
|
87 % |
|
ctxpilot — Memory engine for AI coding agents
Cut repeated AI coding context with a local memory engine, token analytics, and Claude Code beta hooks.
|
84 % |
|
LazyToken — Stop burning tokens on noise
LazyToken cuts your AI coding agents' token consumption by up to 90% on supported commands and adds a Context Firewall (DLP) that redacts secrets before they...
|
84 % |
|
stuff.md — tokenmaxing for agent tools
A research notebook for tokenmaxing: building agent tools (CLI / MCP / code-exec) that finish a task in the fewest tokens — and a fair benchmark to prove whi...
|
83 % |
|
Tokeasy — Cut your AI coding-agent token bill
Cut your AI coding-agent token bill. Ten drop-in MCP tools for Claude Code, Codex, Copilot, Cursor & OpenClaw — fewer calls, smaller context, same model. On...
|
83 % |
|
chop — CLI Output Compressor for AI Agents
Cut token waste by up to 90% across 60+ commands. Works with Claude Code, Gemini CLI, Codex, and more.
|
82 % |
|
Tokengram — Claude Code on half the tokens
Tokengram is a local memory layer for Claude Code. It indexes your repo on your machine and feeds Claude compact search results instead of whole files.
|
82 % |
|
Tokenmeter — know what every AI prompt costs
A free local dashboard for Claude Code, Codex and GitHub Copilot CLI. Real cost, tokens by type, cache misses and rate-limit windows for every prompt, read f...
|
82 % |
|
Optimize - AI Cost Management Platform | Same AI, Smaller Bill
Optimize is the AI cost management platform. It watches every token your team spends across ChatGPT, Claude, Gemini and Copilot, finds the 30-40% that is pur...
|
81 % |
|
Compresso, cut Claude Code & Codex token costs
A macOS app that runs a local AI compression layer between Claude Code or Codex and the provider, shrinking what your agent reads, tool output, logs, files,...
|
81 % |
|
agent-wrapped — your year in AI coding agents
Turn your local Claude Code and Codex logs into a stats card for your GitHub README.
|
81 % |
|
tokentight: Fewer tokens in. Same code and logs out.
Strip whitespace, comments, and redundant noise from code, logs, PDFs, and JSON before it hits your AI's context. 100% client-side, nothing leaves your devic...
|
80 % |
|
Claude Code Token Limits: Compress Context, Save 60-90%
Hitting Claude Code's token limit? Token Limits compresses file reads, logs, and search results before they reach your context, so sessions run 3x longer. Wo...
|
80 % |
|
Tamp — Cut your AI coding costs in half
Tamp saves 45% of tokens at default level 5 with 100% quality retention across 216 A/B tasks. Works with Claude Code, Codex CLI, opencode, Cursor, Cline, Aid...
|
80 % |
|
ziptoken.ai — Less tokens. Same intelligence. | ziptoken.ai
ziptoken compresses your AI prompts by up to 50% — same output quality, half the cost. One API call. Zero stack changes.
|
80 % |
|
SlimFlow PRO — AI coding without token quotas
Meet SlimFlow PRO, the AI coding subscription with four models, unlimited tokens and a flat R$99/month price.
|
80 % |
|
Forte - AI Coding Ops
Forte is the AI coding infrastructure layer for engineering teams that turns team AI coding into a compounding system.
|
80 % |
|
Tokmizer · Fewer tokens for Claude Code and Codex
Free token optimizer for Claude Code, Codex and other coding agents. Reduce command output, keep more useful context and measure your savings with tkr.
|
80 % |
|
Memdoor — The headless-first coding agent
The headless-first coding agent, open source, on your own API key: start a run from CI, a schedule or a shell; finish it from your phone or a window. One gat...
|
80 % |
|
Tokenoscopy · See every token. Stop every runaway.
Routine screening for your AI spend. Visibility and hard stops for Claude subscriptions, coding agents and production APIs. Replay every session, see who spe...
|
80 % |
Detected social media networks