✍️Writing & Content32🎨Image Generation37🎬Video & Animation73🎵Audio & Music63💬Chatbots & Assistants49💻Coding & Development248📈Marketing & SEO81Productivity199🎯Design & UI/UX64📊Data & Analytics61📚Education & Research30💼Business & Finance72🏥Healthcare & Wellness18🔍Search & Knowledge16🤖AI Agent Infrastructure107🛡️AI Security & Testing13🧊3D & Spatial21🔎SEO Tools29🏡Real Estate4🗃️Data Extraction27🧠ADHD & Focus Tools9
Listed in Coding & Development with 251 other toolsPart of 1413+ curated AI tools on AISO
cachly logo

cachly

A background MCP memory layer that pre-briefs Claude Code, Cursor, Copilot and Windsurf every session and learns from every commit, with an EU-hosted semantic cache and managed Valkey alongside it.

freemiumFree forever tier with no credit card. Three separately priced products on one invoice. Team Brain is per-seat: Team €99/month for 5 seats (€19.80/seat), Business €299/month for 20 seats (€14.95/seat) adding SSO/SAML, audit logs and a 99.9% SLA, and Enterprise custom with a dedicated CSM and air-gapped or self-hosted deployment. Org plans bill on top of the instance tier hosting the Brain, most commonly Pro at €49/month. Semantic Cache is by volume: Dev €19/month for 200MB (€15 annually), Pro €49/month for 900MB (€39 annually), Speed €79/month for 900MB on Dragonfly with sub-millisecond recall (€63 annually). Managed Valkey is priced by instance size. All EU servers, GDPR-compliant, AVV/DPA included from the Team tier.View full pricing →

Visit cachly

https://cachly.dev

About cachly

cachly is persistent memory for AI coding assistants, built around the observation that every morning a developer re-explains the same codebase to a tool that forgot it overnight. It installs as an MCP server with a single autopilot command and then runs entirely in the background: at the start of every session it sends the assistant a briefing covering the stack, the open bugs and what the team learned since last time, and it learns continuously from commits without the developer having to remember to save anything. The deliberate design choice is zero user effort — no commands to invoke, no lessons to file, no context to paste — on the theory that any memory system requiring discipline will be abandoned. It works with Claude Code, Cursor, GitHub Copilot, Windsurf and VS Code, and ships 126 MCP tools. The product is actually three: Team Brain, the shared memory layer priced by seat; a semantic cache priced by storage volume, which serves repeat prompts from cache instead of spending tokens; and managed Valkey instances priced by size. Everything runs on German servers under GDPR, which is the pitch to EU teams that cannot send codebase context to US infrastructure. The npm package reports over 30,000 installs.

Key Features

Automatic session briefings — no commands, no manual saving
Learns from every commit in the background
126 MCP tools; works with Claude Code, Cursor, Copilot, Windsurf and VS Code
One-command setup via npx
Semantic cache serves repeat prompts instead of spending tokens
100% EU data on German servers, GDPR-compliant, AVV/DPA included

Tags

mcpclaude-codecursormemorygdpr
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

ChatGPT already recommends cachly. Does it recommend yours?

If you're building in Coding & Development, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Stay updated on Coding & Development tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Agent connectivity: not yet verified