Does it work with my existing CLAUDE.md and MCP servers?

Yes. Edgee runs as a wrapper around your Claude Code install. Your configs, MCP servers, and CLAUDE.md are untouched.

Will the compression affect Claude's output quality?

No. Compression is lossless in terms of semantic content. We rewrite tool results for token efficiency, the model still receives the full intent.

What happens if Edgee is down?

Edgee has automatic fallback: if the compression layer fails, your request is forwarded uncompressed to Claude. You're never blocked because of us.

Is my code sent to Edgee servers?

Only your prompts transit through the edge for compression. We don't store them.

Does it work on Windows / WSL?

Yes on WSL. Native Windows support is on the roadmap. macOS and Linux are first-class.

What's on the roadmap for Cursor and OpenClaw?

Both are in active development. Join the waitlist on the coding-agents page to get notified.

Claude Code usage limit

Hit your Claude Code limit? Keep coding.

Name: Edgee AI Gateway
Author: Edgee

Edgee compresses tokens before they reach Claude. Same plan, same code, up to 2x more session time. Install in 30 seconds.

Start free — no credit card See how it works

Works with Claude Code, Codex, OpenCode. Cursor coming soon.

edgee

Backed by founders and leaders of

You're paying for Max. You're still hitting limits.

The Claude Code usage limit resets every 5 hours, and the weekly Opus ceiling can lock a Max plan mid-sprint.

5-hour window

You burn through your quota before lunch and wait until evening to resume.

Weekly Opus limit

One deep session and Opus is locked for 6 days. You fall back to Sonnet for the rest of the sprint.

Pay-per-token overage

Extra usage kicks in and your monthly cost doubles without warning.

One command. Every token, compressed.

Extend your Claude Code session with edge-native token compression, no config changes, no proxy setup.

# Install
curl -fsSL https://edgee.ai/install.sh | bash

# Launch Claude Code with compression enabled
edgee launch claude

# That's it. Compression runs silently.
# Full observability in your Edgee dashboard.

Up to 80% tool compression

Tool results are compressed at the edge before reaching Claude, without losing context quality.

Zero code changes

Edgee wraps your existing Claude Code install. Your configs, MCP servers, and CLAUDE.md stay untouched.

Full observability

Track tokens saved, cost avoided, and latency per session in your dashboard.

With Edgee vs without

What the Claude Code weekly limit looks like before and after.

Claude Code with and without Edgee token compression.
	Claude Code alone	Claude Code + Edgee
Session duration before limit	~2h	~3–4h
Weekly Opus capacity	Locked fast	Stretched
Token cost per session	Full	Up to 50% less
Setup time	—	30 seconds

How the compression works

Your Claude Code

Edgee compresses at the edge

Claude API

Edgee sits between your coding agent and Claude. Prompts are compressed at the edge before being forwarded, then decompressed server-side for the model. Output quality stays identical.

Read the technical deep-dive

Questions devs actually ask

Keep coding

Stop watching your limit reset timer.

No credit card. Works with your existing Anthropic plan.

Start free — install in 30 seconds