cachly is a persistent AI memory platform for developers. It gives AI coding assistants like Claude Code, Cursor, GitHub Copilot and Windsurf a brain that remembers every lesson, fix, and architecture decision — forever. It connects via the MCP (Model Context Protocol) standard and includes 121 tools. Free tier available. Runs on German (EU) servers.

How does cachly work?

Run 'npx @cachly-dev/mcp-server@latest autopilot' once. The wizard auto-detects every AI editor you have installed (Claude Code, Cursor, Copilot, Windsurf, Cline, Zed) and writes the correct config for each. It then reads your entire git history with brain_from_git and loads years of team knowledge into your Brain before your first session. From that point, sessions start automatically, memory is shared across all your editors simultaneously, and a git post-commit hook teaches cachly from every commit.

Does cachly auto-detect my editors?

Yes. The cachly setup wizard automatically detects Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Continue.dev — any editor that supports MCP. It writes the correct config file for each editor in one pass. You never manually edit JSON config files.

Is memory shared across all my AI editors?

Yes. cachly uses a single Brain that all your AI editors connect to simultaneously. A lesson remembered in Claude Code is instantly available in Cursor and GitHub Copilot. If your team uses different editors, all of you share the same persistent memory pool.

What is brain_from_git?

brain_from_git is a cachly tool that reads your entire git history before your first session and extracts lessons from every commit, PR, and revert. Your AI arrives knowing years of architectural decisions, bug fixes, and team conventions — without you writing a single line of documentation. Zero onboarding.

What is causal_trace?

causal_trace is a cachly tool that traces the history of any file or bug across your entire git history in seconds — replacing 30+ minutes of manual git blame. Describe a problem in plain English. It returns the root cause, the failure chain, and the exact fix that worked — with date, command, and file path.

What is brain_predict?

brain_predict is a cachly tool that scans your Brain for failure patterns before every deploy, migration, or dependency upgrade. It returns probability-weighted warnings based on your team's actual incident history — so you catch the next incident before it happens.

Does cachly work with Claude Code, Cursor, and GitHub Copilot?

Yes. cachly works with Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Continue.dev — anywhere that supports MCP. Run 'npx @cachly-dev/mcp-server@latest autopilot' to configure all editors in one step. Memory is shared across all editors simultaneously.

Can cachly search memory across languages?

Yes. cachly uses semantic vector embeddings, not keyword search. A lesson stored in German appears when you search in English. A fix documented in Arabic matches a Japanese query about the same bug pattern. Supported languages include English, German, French, Spanish, Italian, Portuguese, Japanese, Chinese (Simplified and Traditional), Korean, Arabic, Hebrew, and more.

How is cachly different from mem0?

mem0 is a memory layer for Python LLM apps and chatbots — great for building AI products. cachly is built specifically for developer tooling: it connects to your AI editor via MCP, learns from your git history automatically, predicts failures before deploy, and gives your whole team shared memory. cachly runs on EU servers and is GDPR-native. For developers using Claude Code, Cursor, or Copilot, cachly is the right choice.

Is cachly GDPR compliant?

Yes. cachly runs exclusively on German servers (Hetzner). All data stays in the EU. No data is shared with third parties. cachly is fully GDPR compliant. An AVV (Auftragsverarbeitungsvertrag / Data Processing Agreement) is available for Business and Enterprise customers.

How many MCP tools does cachly have?

cachly ships 121 MCP tools. They cover the full AI memory lifecycle: session_start (pre-briefing), smart_recall (semantic search), learn_from_attempts (lesson storage), brain_from_git (git history bootstrap), brain_predict (pre-deploy failure prediction), causal_trace (root-cause analysis), memory_crystalize (lesson compression), crystal_view, team Brain tools, cache tools, and more.

What editors does cachly support?

cachly supports Claude Code, Cursor, GitHub Copilot (VS Code), Windsurf, Cline, Zed, Continue.dev — any editor that supports MCP (Model Context Protocol). The setup wizard auto-detects all installed editors and configures them in one step. Memory is shared across all editors simultaneously.

What is the session_start tool?

session_start is the cachly tool that auto-runs at the beginning of every AI session. It retrieves the most relevant lessons from your Brain via smart_recall and delivers a briefing to your AI — so it arrives knowing your stack, your patterns, and your recent lessons without you typing anything.

What is the causal_trace tool?

causal_trace finds the root cause of any bug or regression by tracing the causality chain through your Brain's knowledge graph. Describe the problem in plain English. It returns the failure chain, the root cause, and the exact fix that worked — with date, commit, and file path. Replaces 30+ minutes of manual git blame.

How does cachly's Team Brain work?

Team Brain is a shared knowledge pool that all team members connect to. When one developer finds a fix, every developer's AI knows about it by the next session — automatically. Invite teammates with invite_link. Admins can set roles with role_assign. The entire team shares one Brain instance, keeping AI context consistent across the whole codebase.

Does cachly learn from git commits automatically?

Yes. cachly installs a git post-commit hook during setup. Every commit is analyzed for lessons — bug fixes, reverts, refactors, and architectural decisions are stored in the Brain automatically. No manual documentation required. brain_from_git additionally bootstraps the full history (years of commits) in a single run.

What is brain_predict used for?

brain_predict scans your Brain before a deploy, migration, or dependency upgrade and surfaces failure patterns from your actual incident history. It returns confidence-weighted warnings so you can catch the next incident before it happens. It runs in under 500ms and can be integrated into CI pipelines with the cachly CLI.

What is memory_crystalize?

memory_crystalize compresses thousands of Brain lessons into a compact, category-grouped snapshot called a Memory Crystal. Categories: deploy, fix, debug, arch, perf. The crystal is injected into every session briefing instead of the raw lesson list, keeping context clean and dense. Run monthly or after a major project milestone.

Interactive Deep Dives

Every cachly feature, hands-on.

The landing page shows you what cachly does. This page shows you how — with live demos, interactive code snippets, and real config examples for every major feature.

🔌MCP↓🤖OpenClaw↓🦾AI Agents↓🏗️Bot Builder↓⚡Instant Setup↓🔧Terraform↓🐉Dragonfly↓🌐Cluster↓🎨Multimodal↓💾AI Memory↓⚡brain_from_git↓

BRAIN FROM GIT · ZERO ONBOARDING

Your git history IS your knowledge base

brain_from_git reads your entire git log before your first session. Your AI arrives knowing years of architectural decisions, bug fixes, and team conventions — before you write a single line of new code.

📜

Full git history scan

Every commit message, PR description, and revert note is extracted and loaded into your Brain automatically during setup.

🧠

Lesson extraction

cachly classifies commits as fixes, reverts, decisions, and warnings — building a typed Causal Knowledge Graph from day one.

⚡

Zero manual effort

No documentation to write. No onboarding sessions. Your AI knows your codebase the moment setup finishes.

🔄

Continuous git learning

A post-commit hook installed by setup keeps the Brain updated after every commit. Yesterday's fix is today's recalled lesson.

What brain_from_git extracts

# Run once during setup — automatically
npx @cachly-dev/mcp-server@latest brain-from-git

# What gets extracted:
✓ Fix: JWT validation — check expiry before signature (commit a3f91c2)
✓ Revert: removed Redis pub/sub — race condition under load (commit 8b2e441)
✓ Decision: switched to tRPC for type safety across monorepo (commit f9c1203)
✓ Warning: Stripe webhooks not ordered — always idempotent (commit 2d8a917)

# Your AI knows all of this before your first session.

Get started free

Ready to stop paying twice?

Free tier. No credit card. Live in 30 seconds.

Start for free ← Back to overview