tanstack-ai-memory-honcho

A hosted memory adapter that connects TanStack AI to Honcho, a service that stores conversations and answers recall requests from a user's stored representation.

In plain words
What is it for?
Use it to add Honcho-backed conversation memory through `memoryMiddleware`, with settings for users, sessions, the Honcho server, and API access.
Why use it?
It lets an AI assistant remember and save conversation turns without building its own memory service. Recall returns one synthesized answer rather than separate memory items.

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

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 428 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 $0.00055 $0.00428
Opus 5 $0.00028 $0.00214
Sonnet 5 $0.00011 $0.00086
Haiku 4.5 $0.00006 $0.00043

Measured 2d ago against content hash 71fc09e7bfad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tanstack-ai-memory-honcho 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-memory/skills/tanstack-ai-memory-honcho/SKILL.md · 41 lines

What it actually says

Honcho Memory Adapter

Hosted recall/save adapter backed by Honcho. Honcho models memory as peers exchanging messages in a session; recall returns a synthesized dialectic answer over the user peer's representation (so there are no discrete fragments), and save appends the turn's messages to the session.

Setup

import { memoryMiddleware } from '@tanstack/ai-memory'
import { honcho } from '@tanstack/ai-memory/honcho'

const memory = honcho({ user: currentUserId }) // baseURL defaults to HONCHO_URL

memoryMiddleware({ adapter: memory, scope })

@honcho-ai/sdk is an optional peer dependency, loaded lazily on first use — install it where you use honcho().

Options

  • user — user peer id (falls back to scope.userId, then 'demo-user').
  • baseURL — Honcho server URL (default HONCHO_URL or http://localhost:8001).
  • workspaceId — default HONCHO_APP_NAME or 'ai-memory'.
  • apiKey — default HONCHO_API_KEY.
  • assistantId — assistant peer id (default 'assistant').

Scope fields: session key = {tenantId|_}__{threadId}; peer id is {tenantId}__{user} when tenantId is set, otherwise user / scope.userId. namespace is ignored.

recall calls the user peer's dialectic chat() and injects the answer as the system prompt; Honcho exposes no LLM tools.

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 · 41 lines · 55 tokens per session scan A 71fc09e7bfad

Subscribe to this mod's changes

tanstack-ai-memory-honcho is a skill published in the GitHub repository TanStack/ai (3,056 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 428 once invoked, about $0.0003 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.