Hydrate for GitHub Copilot · v1 launch

Your Copilot, minus the context tax.

Hydrate is an auditable, on-premise memory and efficiency layer for AI assistants. Already shipping for Claude Code. The same binary - unchanged - extends to GitHub Copilot via a VS Code extension. Claude Code and Copilot share one memory when they both run on your machine: a decision captured from Copilot Chat injects into the next Claude Code prompt, and vice versa.

See how it works For Copilot Enterprise buyers

Ships with Hydrate v1 · on-prem by architecture · EU AI Act aligned

Two things shrink the context Copilot carries: Hydrate compresses long project docs through a local summariser before they reach the model, and recalls only the prior decisions a turn actually needs instead of re-sending the whole history. Both run on your machine, and every request is auditable per editor.

How it works →

One engine, three surfaces

The same memory, wherever you work.

Hydrate doesn't care which assistant is asking. The on-prem binary answers context queries from any of three integrations - and every fact captured on one surface flows to the others.

Claude Code

shipping

Native hooks - UserPromptSubmit, Stop, PreToolUse, PostToolUse. Zero configuration. Works on day one with your existing Claude subscription.

Install guide →

VS Code + Copilot

v1 launch

VS Code extension registering an @hydrate chat participant plus three Language Model Tools. Copilot chooses to call them when it needs prior context, wants to compress a long doc, or encounters a file its built-in read would struggle with.

Details ↓

MCP server

shipping

Works with every MCP-aware client - Claude Desktop, Cursor, Cline, Zed, Gemini CLI, your own agent. One endpoint, the same memory, the same savings.

Integration guide →

Where the savings come from

Two levers, both on your machine.

The saving is not a trick of prompt engineering. It comes from two concrete mechanisms you can inspect per request.

Compress

Long project docs pass through a local summariser before they reach the model, so a large CLAUDE.md or spec folder arrives as a compact brief rather than raw text. The bigger the corpus, the more this saves, because compression scales with input size.

Recall

Instead of re-sending the whole history every turn, Hydrate injects only the prior decisions and session context a given prompt needs. That keeps the per-turn context small no matter how long the project runs.

Every Copilot-originated request is attributable per editor, so the effect is auditable rather than asserted. Fresh, published reduction figures for Copilot are being re-run for v1 and will appear here once the benchmark lands.

How it works

Four surfaces Copilot already knows how to use.

Hydrate's VS Code extension registers a chat participant plus three Language Model Tools. Copilot decides when to call them - the same mechanism it uses for every other tool in its toolbox. No magic routing, no middleware, no new UI to learn.

@hydrate chat participant

Explicit invocation from Copilot Chat. @hydrate /recall <topic> returns exactly what Claude Code's hook would inject for the same query. /drain pulls any dashboard-queued thoughts. /capture flushes the session immediately.

→

`hydrate_recall`

Pulls prior decisions, session summaries, and pinned canon when the user references past work.

→

`hydrate_compress`

Compresses long prose through the local summariser before it reaches the model. 15×-100× ratios on real docs.

→

`hydrate_read_file`

Reads a workspace file, auto-compressing when it's bigger than 4 KB. Stops README.md blowing the context window.

The extension ships ~2,000 lines of TypeScript - a thin HTTP client over hydrate-server. Every Copilot-originated request carries X-Hydrate-Source: copilot; the server stamps the column server-side so savings attribute cleanly per editor.

Copilot Enterprise buyers

Three walls every deployment hits between now and August 2026.

Token economics

The unit economics of the $39/seat Copilot Enterprise tier do not work at heavy-user volume without either a price rise or an efficiency lever. Hydrate is the efficiency lever: a smaller per-turn context compounds across every seat in a large deployment.

EU AI Act - August 2026

Copilot Enterprise routes context through Azure OpenAI. Regulated customers in finance, healthcare and public sector are already refusing deployments where the context layer touches cloud. Hydrate's single on-prem binary, AES-GCM encryption at rest, and Article-mapped hydrate compliance report subcommand fill the gap without re-architecting Azure.

Customer-controllable compliance

Windows MSI, ADMX template for Group Policy, Intune/SCCM deployable. Storage mode, retention, forbidden paths, and API key all domain-configurable. Audit log rotates to JSONL for SIEM ingestion (Splunk, Sentinel, Elastic). Enterprise reviewers can reproduce every figure in the compliance report with one sqlite3 query.

Full enterprise page

Ships with Hydrate v1 · currently alpha

In open beta. Install live.

The Copilot extension is in alpha today and ships production-grade alongside Hydrate's public v1 release. Press, researchers and anyone writing about the launch can request early access.

How the beta rolls out →