Documentation
Everything you need to get started with Kandela.
🎬 See Kandela in Action
Demo video coming soon
Watch how Kandela remembers decisions across sessions, prevents repeated mistakes, and guards against drift.
☁️ Hosted (Cloud)
The fastest way to start. We handle the server — you just install the client.
Sign up for beta
Email support@kandela.ai to request access. Beta is free.
Create an API key
Dashboard → Account → Generate API Key
Run the installer
curl -fsSL https://kandela.ai/install | python3 Enter your API key when prompted. Done in ~60 seconds.
🏠 Self-Hosting
Run Kandela on your own server. Full control over your data.
Run Kandela on your own infrastructure with a few simple commands.
- Requirements: Docker 20.10+, 4GB+ RAM
- Setup: A few commands to pull, run, and connect
- Your data stays on your server — no external dependencies
📦 Full guide & source code: github.com/deep-on/kandela Coming Soon
🔧 Technical Overview
Built on multiple patent-pending technologies for memory retrieval, session continuity, and decision protection.
Hybrid Search
Semantic (ChromaDB) + BM25 keyword search, fused with Reciprocal Rank Fusion. Works across 50+ languages.
Importance Engine
25 rules auto-score memories 1–10. Infrastructure decisions get boosted; trivial facts decay over time (ACT-R model).
Prompt Guard
Detects when Claude suggests reversing a past decision. Surfaces the original reasoning before you regret it.
Circuit Breaker
After 3 repeated failures, stops execution and surfaces relevant gotchas from memory.
Lazy Retrieval
Brief mode (~260 tokens) at session start. Full context loaded on-demand via context_search.
Multi-Project
Isolated memory per project with cross-project discovery. Global memories shared across all projects.
A/B Benchmark Results
90 sessions, 2 scenarios (HIPAA pipeline + Slack infra bot), Claude Sonnet 4.6: