GitHub Copilot

Cut Your GitHub Copilot Token Costs by 40–70%

Terse compresses every prompt before it reaches Copilot — removing filler, fixing typos, and stripping redundancy. Less context in means faster responses and lower cost on Copilot Business and Enterprise plans.

40–70%prompt compression
AutoVS Code detection
7-Stagecompression pipeline
0data leaves device

How Terse Works with GitHub Copilot

Copilot's context window fills up fast: your file, selected code, conversation history, and your typed prompt. Terse compresses the prompt text before it's sent — reducing tokens without reducing intent.

VS Code Integration

Terse detects VS Code via the Accessibility API and activates when you open the Copilot Chat panel or inline chat. No configuration required — it works the moment you start typing.

Automatic
🗜️

7-Stage Prompt Pipeline

Spell correction, whitespace normalization, filler word removal, hedge stripping, phrase shortening, redundancy elimination, and cleanup — in sequence, on every prompt you type to Copilot.

130+ Rules
📊

Per-Turn Cost Tracking

Terse's Agent Monitor shows token usage per Copilot Chat turn in real time. Know immediately when a single question is consuming 60,000 tokens — and why.

Live Monitor
🔁

Redundant Query Detection

Terse tracks when you ask Copilot the same question twice in a session, or ask about the same file or function multiple times. Each duplicate is flagged so you can reuse the previous response instead.

Session Awareness
💬

Copilot Chat Compression

Works in both Copilot Chat and inline chat (@workspace queries, /fix, /explain). Long natural-language questions are trimmed without losing technical accuracy — code blocks are always protected.

Chat + Inline
🔒

100% On-Device

Terse reads your prompts via macOS Accessibility APIs and compresses locally. No text is sent to Terse's servers — your code stays on your machine, just like Copilot's own privacy guarantees require.

Zero Cloud

GitHub Copilot Pricing — Where Terse Helps Most

Copilot's plans are seat-priced, but token efficiency directly affects how much value you get per seat and how fast context windows fill during long sessions.

Copilot Individual
$10
per month
Code completions + Copilot Chat. Context window fills quickly on large files. Terse reduces prompt token consumption so each chat turn has more budget for the file context.
Copilot Business
$19
per seat / month
All of Individual + organization policy controls. Teams with many daily Copilot Chat users benefit most from prompt compression — each seat's efficiency multiplied across the team.
Copilot Enterprise
$39
per seat / month
Adds custom models, larger context (including @workspace for full repo). Token efficiency matters most here — larger context windows mean more potential for token waste if prompts are verbose.

Frequently Asked Questions

Everything about using Terse with GitHub Copilot.

Does Terse work with GitHub Copilot?
Yes. Terse detects VS Code via macOS Accessibility APIs and compresses prompts you type in the Copilot Chat panel and inline chat. It works automatically — no configuration required.
Does Terse work with Copilot CLI?
Yes. Terse monitors terminal sessions and can compress prompts sent to Copilot CLI workflows. The Agent Monitor tracks per-turn token usage and flags redundant queries across CLI interactions.
Will Terse affect Copilot's code completion quality?
No. Terse only compresses the natural language text you type — questions, instructions, context descriptions. Code blocks are always protected and pass through unchanged. The meaning of your prompt is preserved while the redundant language is removed.
Does Terse send my Copilot prompts to any server?
No. Terse is 100% on-device. It reads text via macOS Accessibility APIs, compresses locally using a Rust engine, and writes the compressed text back. Your code and prompts never leave your machine.

Also Works With

Terse reduces token costs across every major AI coding tool.

Claude Code ⌨️ Cursor — AI Code Editor 💬 ChatGPT — Browser 🖥️ Aider — Terminal Agent

Stop Losing Tokens to Verbose Prompts

30-day free trial. No credit card required until your trial ends. Cancel anytime.

Start Free Trial — macOS Calculate Your Savings