Long-term memory
for AI coding agents.
Your AI agent works harder when it has the right context.
Kandela provides the decisions, gotchas, and history that matter — automatically.
Compatible with Claude Code.
3-seed A/B test
90 sessions · 2 scenarios
MedFlow (HIPAA pipeline) + InfraBot (Slack infra bot). Claude Sonnet 4.6, automated end-to-end.
How it works
Remembers decisions
Why did you choose Naver Maps over Google Maps? Why is the cache TTL 2 hours? Kandela stores the why, not just the what.
Instant recall
At session start, Kandela automatically loads relevant memories — gotchas, past decisions, infrastructure notes — so your agent starts informed.
Prompt Guard
When your agent suggests reversing a past decision, Kandela detects the conflict and surfaces the original reasoning before you regret it.
Circuit Breaker
After 3 repeated failures on the same issue, Kandela stops execution and surfaces relevant gotchas from memory.
Hybrid Search
Semantic + BM25 keyword search fused with Reciprocal Rank Fusion. Works across 50+ languages with multilingual embeddings.
Importance Engine
25 rules auto-score memories 1–10. Infrastructure decisions get boosted; trivial facts decay over time using the ACT-R cognitive model.
Telegram Bot
Save and search memories on the go. Remote commands coming soon. Available with Pro plan.
Cross-Provider
One memory store for all your tools. Switch between Claude, GPT, Gemini — your memories stay. Works with Claude Code, Cursor, VS Code, and any MCP client.
Multi-Project
Isolated memory per project with cross-project discovery. Global memories shared across all projects. Available with Pro plan.
Get started in 2 minutes
Sign up for beta, get an API key, run one command. That's it.