Edgee

For developers: Edgee runs open-source models in Claude Code at 4× speed for $29/month so you ship faster without code changes.

Built by Sacha MORARD · Artificial Intelligence · Developer Tools · Software Engineering · Freemium

Visit website

In category: #352 of 2034 · Artificial Intelligence

Product Hunt listing

Listing status

196upvotes

Community score

Sacha MORARD (Joined Jun 2026)

Founder

Compared against 5 alternatives

Market comparison

Launched on Launch Llama Jun 21, 2026 · #21 of 41 that day

About

It helps engineering teams control token spending by setting budgets per developer or squad and automatically rerouting to cost-effective models mid-task. Edgee works with coding agents like Claude Code, Cursor, and Copilot without requiring code changes.

Follow Edgee: X (Twitter) · LinkedIn

Launch Llama's Take

Based on Launch Llama data as of November 2026

Edgee has 196 upvotes, including the votes it received on Product Hunt, which ranks it #352 of 2,034 Artificial Intelligence tools on Launch Llama by upvotes, in the top quarter. It has been listed on Launch Llama since June 2026. No Launch Llama members have upvoted it yet and it has no reviews yet.

Edgee is a tool that controls token spending by setting budgets per developer or squad, whereas The Claude Code Cost Control Playbook is a written field manual of cost-cutting tactics.

Edgee vs The Claude Code Cost Control Playbook

Edgee is a tool that controls token spending by setting budgets per developer or squad, whereas The Claude Code Cost Control Playbook is a written field manual of cost-cutting tactics.

Edgee vs The Claude Code Cost Control Playbook: side-by-side comparison
	Edgee	The Claude Code Cost Control Playbook	Claude Code Desktop App Redesigned	DoneDone
What it does	For developers: Edgee runs open-source models in Claude Code at 4× speed for $29/month so you ship faster without code changes.	For Claude users: This playbook cuts your API costs with 15 sourced tactics, frameworks, and a 90-day implementation plan.	For developers: Claude Code desktop runs parallel coding agents across repos, reviews diffs, and ships code—all in one workspace.	For developers: DoneDone verifies AI-built WordPress migrations page-by-page, catching product pages, cart calculations, and checkout dif…
Pricing	Freemium	Paid	Paid	Paid
Free plan	Yes, free plan	No free plan listed	No free plan listed	No free plan listed
Category	Software Engineering	Artificial Intelligence	Productivity	SaaS
Upvotes on Launch Llama	196	9	547	36
Listed on Launch Llama	June 2026	May 2026	April 2026	May 2026

See all Edgee alternatives

Key Features

Route requests across multiple LLM providers based on budget policies
Compress input and output tokens without changing application code
Track cost and usage per developer, repository, and pull request
Automatically failover to alternative models when providers fail or hit rate limits
Deploy on-premise within your own infrastructure for data isolation

Use Cases

Organizations needing visibility into which teams and projects consume the most tokens and cost
Companies with strict data residency or compliance requirements that cannot send prompts to third-party providers

Who it is for

Software developers using coding agents such as Claude Code, Codex, Copilot, OpenCode, or Cursor
Engineering leaders who need cost and usage visibility across developers and squads
Teams building AI apps or agents that want to control LLM token spend and routing

Pricing

Free plan for solo developers. Team plan at €30 per developer per month. Enterprise plan with custom pricing for scale and security requirements.

View Edgee pricing →

Edgee at a glance

01What it is: Edgee: For developers: Edgee runs open-source models in Claude Code at 4× speed for $29/month so you ship faster without code changes.
02Pricing: Edgee pricing: Free plan for solo developers.
03Best for: Edgee is best for software developers using coding agents such as Claude Code, Codex, Copilot, OpenCode, or Cursor, engineering leaders who need cost and usage visibility across developers and squads and teams building AI apps or agents that want to control LLM token spend and routing.
04Alternatives: Top Edgee alternatives on Launch Llama: The Claude Code Cost Control Playbook, Claude Code Desktop App Redesigned and DoneDone.

Compare Edgee with The Claude Code Cost Control Playbook

FAQ

What is Edgee?

Edgee is an Agent Gateway: the layer between AI agents (Claude Code, Codex, Copilot, OpenCode, Cursor) and LLM provider APIs (Anthropic, OpenAI, GLM). It applies three things to every request. It routes under a budget you define, it compresses the payload, and it meters every token so cost can be attributed to a developer, a repo, or a PR. Up to 70% token cost reduction.

How does budget-driven routing work?

You define a routing Strategy and assign it to a developer, a squad, or the whole organization. A Strategy ties spend thresholds to routing rules. For example, on a $100 weekly Claude budget: at 75% consumption, Opus-targeted requests reroute to Kimi K3; at 85%, Sonnet requests go to GLM 5.2; at 100%, everything routes to DeepSeek. Rerouting happens mid-task, without quality loss and without interrupting the session.

Can I use my own provider API keys?

Yes. You can use Edgee’s unified access with a single Edgee API key, or bring your own provider keys for direct billing and custom models.

What visibility do engineering leaders get?

Cost and token usage per developer, per repo, per PR, per model, and per environment. Sessions are replayable, and every token is attributed rather than pooled into a single API-key line item.

Does Edgee work with Claude Code?

Yes. Install the Edgee CLI and run `edgee launch claude` to start Claude Code through the gateway. No code changes required. Edgee works with all provider plans, including consumer subscriptions such as Claude Pro and Max, not only API credits.

Which agents does Edgee support?

Edgee supports Claude Code, Codex, Copilot, OpenCode, and Cursor. The Edgee CLI wraps your agent transparently, so routing, compression, and metering happen at the network layer.