ai-persistence

A set of tools for saving and restoring AI chat conversations with TanStack AI. It separates saved conversation history from delivery durability, which lets a running response resume after a connection problem.

In plain words
What is it for?
Use it to add server-side or browser-side chat persistence, store conversations across sessions, and support resumable AI responses.
Why use it?
It prevents chat history from existing only in temporary memory or being confused with a reconnectable response stream. You can connect the storage contract to databases such as Postgres, SQLite, D1, or Mongo.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tanstack/ai/ai-persistence
Any agent
npx skills add TanStack/ai --skill ai-persistence
Clone the repo
git clone --depth 1 https://github.com/TanStack/ai

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00088 $0.02840
Opus 5 $0.00044 $0.01420
Sonnet 5 $0.00018 $0.00568
Haiku 4.5 $0.00009 $0.00284

Measured 2d ago against content hash 4508322a41a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-persistence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/ai-persistence/skills/ai-persistence/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TanStack AI Persistence

Builds on the ai-core skill in @tanstack/ai, and usually ai-core/chat-experience.

TanStack AI splits delivery durability from state persistence. They share no code and solve different problems.

Layer Answers Package / API
Delivery durability Reconnect to a stream still running memoryStream / @tanstack/ai-durable-stream on the response; see resumable streams docs
State persistence What is the conversation, later? Client persistence on useChat + server withPersistence from @tanstack/ai-persistence

A replayable stream is not a saved conversation. A saved conversation is not a live stream. Production apps often use both.

Persistence is a contract, not a database

@tanstack/ai-persistence ships the store interfaces, the middleware that drives them, an in-memory reference backend, and a conformance testkit. It does not ship a backend for your database, and you do not need one: implement the stores against whatever you already run — Postgres, SQLite, D1, Mongo — and hand the result to withPersistence. The core never inspects your tables.

Ships in the package What it is
MessageStore / RunStore / InterruptStore / MetadataStore The four chat state contracts
GenerationRunStore / ArtifactStore / BlobStore The generation contracts (job lifecycle + bytes)
withPersistence / withGenerationPersistence Chat + generation middleware
memoryPersistence() In-process reference backend, all seven stores (dev, tests)
reconstructChat / reconstructGeneration Server hydrate route helpers (chat / generation)
retrieveArtifact / retrieveBlob / resolveArtifactBlobKey Serve persisted generation-media bytes back
LockStore / withLocks / InMemoryLockStore (from @tanstack/ai/locks) Coordination, not this package — see ai-core/locks
@tanstack/ai-persistence/testkit runPersistenceConformance gate (chat state stores)

Read the full file on GitHub · 226 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 226 lines · 88 tokens per session scan A 4508322a41a4

Subscribe to this mod's changes

ai-persistence is a skill published in the GitHub repository TanStack/ai (3,056 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 2,840 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.