Premium skill
Give your AI SDK agent durable memory
Evidence-based write path, budgeted recall injection, decay, user-visible deletion, and recall-quality evals. Remember users without becoming a privacy or prompt-injection disaster.
Install
Install with skills CLIPremium skills install through a short-lived private link.
$ npx skills add … --skill agent-memoryOpen Premium install
Sign in with Premium to generate a fresh install link.
Filesystem
Browse the authored file tree — tools, references, and evals included. Source unlocks with Premium.
SKILL.mdmarkdownUnlock skill source
Browse every authored SKILL.md with premium.
File tree for agent-memory stays visible so you can see the pack before unlocking.
Use this when
- 01A support agent that remembers account preferences across sessions.
- 02A coach that keeps standing instructions without treating memory as system prompts.
- 03A settings page where users list, edit, export, and wipe what the agent knows.
- 04An agent that recalls stale facts: diagnose write path, ranking, and decay with metrics.
What you get
- Stores what changes behavior
- Memory kinds come from product evidence. A never-store list lives in code.
- Recalls as data
- Injects memories under a token budget, labeled as remembered data, never as instructions.
- Deletes for real
- Wipe reaches embeddings and summaries. An eval proves recall fails after delete.
- Measures recall
- Remember/recall, isolation, budget, and post-delete cases.
Unlock the files
Available with Premium. The private install link expires; the downloaded skill does not. Generate a fresh link when you want to update it.
Other Premium skills
Lifecycle skills and UI craft skills
- PlanPlan AI SDK AgentBefore you write agent code
- BuildAISDK AgentsImplementing agents, chat apps, and streaming UIs
- EvaluateBuild AI SDK Agent EvalsProtecting critical agent journeys before you optimize
- ObserveObserve AI SDK AgentDebugging and attributing agent behavior in production
- OptimizeOptimize AI SDK AgentImproving quality, speed, cost, or reliability with proof
- InstructWrite Agent PromptsAgents that ignore instructions or run on folklore prompts
- InstructWrite Prompt ContractsAgents that pick the wrong tool or narrate a plan instead of acting
- Chat UIBetter Chat UIBuilding or reviewing the conversation surface
- Generative UIBetter Generative UITurning model output into interactive product UI
- PrototypeTest UI VariantsSurfaces where one polished mock would hide the real choice
- IngestIngest Messy DocumentsPDF, scan, and table-heavy corpora feeding RAG or extraction
- GroundGround AI SDK AgentMaking an agent answer from your data with proof
- ExposeBuild MCP ServerMaking your product agent-accessible
- ExtractExtract Structured DataInvoices, resumes, contracts, forms, and free text to typed data
- ShipShip AI SDK on CloudflareGetting an AI SDK agent into production on Cloudflare
- ShipShip AI SDK on AWSGetting an AI SDK agent into production on AWS
- MobileAI SDK on MobileShipping AI SDK chat in an Expo or React Native app
- MigrateMigrate to AI SDKLeaving LangChain, the Assistants API, or hand-rolled LLM code