Files
Nicolò Boschi 6f2799569f docs: make every integration changelog reachable, and compact the Integrations Hub (#4005)
* docs: link every integration changelog from its doc page

The release script has written a changelog page per integration since 0.4.20
(src/pages/changelog/integrations/<slug>.md), but nothing reliably linked them:
16 of 61 doc pages carried a "View Changelog" link, and the only index was a
hand-written table at the bottom of /changelog listing 6 of the 48 pages, stale
since the release that introduced them. coding-agents was one of the 31 pages
with a changelog nobody could reach except by guessing the URL.

Adds the link to the 30 pages missing one, plus a third invariant in
check-integrations.mjs so the next one can't ship unlinked: every changelog page
whose integration has a gallery entry must be linked from its doc page.

coding-agents.md is generated, so its link goes in the README as an absolute
hindsight.vectorize.io URL — the sync script rewrites our own absolute URLs to
site-relative, so it resolves on npm, GitHub and the docs site. It sits outside
the skill:begin regions, so SKILL.md is unchanged.

Claude-Session: https://claude.ai/code/session_01DNWFQn8AUN6SApcswHG3aN

* docs(integrations): compact grouped gallery with Docs/Changelog buttons

The Integrations Hub listed 60 three-line cards with a repeated "Hindsight Team"
byline and an OFFICIAL badge on 52 of them, running 6092px tall — scanning it
meant scrolling past what you came for. Cards are now a compact row (icon, name,
two-line description) grouped by category, with the featured three using the same
row tinted rather than a second card design: 4352px, and the shape of the
catalogue is visible at a glance.

Each card carries Docs and Changelog buttons. Which integrations have a changelog
comes from a new build-time plugin that indexes
src/pages/changelog/integrations/*.md and joins integrations.json on the link
slug (vercel-ai-sdk -> /sdks/integrations/ai-sdk -> ai-sdk.md), so an integration
grows the button on its first release with nothing to update by hand.

The card is a <div> now — nested anchors are invalid — so the name and the pills
are the links, not the whole card. /changelog's first line points here instead of
carrying its own listing.

Also drops the 14 CSS classes the old card owned, and shares CATEGORY_LABELS /
groupByCategory from src/lib/integrations.ts so the taxonomy has one definition.

Claude-Session: https://claude.ai/code/session_01DNWFQn8AUN6SApcswHG3aN
2026-09-02 10:21:08 +02:00

4.1 KiB

sidebar_position, title, description
sidebar_position title description
23 Flowise Persistent Memory with Hindsight | Integration Add persistent long-term memory to any Flowise chatflow or agent with Hindsight. Three Tool nodes — Retain, Recall, Reflect — drop into any flow alongside your other LangChain tools.

Flowise

Persistent memory for Flowise chatflows and agents via Hindsight. Three Tool nodes — Hindsight Retain, Hindsight Recall, Hindsight Reflect — drop into any flow alongside your other LangChain tools.

View Changelog →

Why this matters

Flowise is the LangChain-derived visual builder for non-developers and developers alike. Until now, Flowise chatflows have been stateless across sessions. With Hindsight tool nodes you can:

  • Retain every closed conversation, support ticket, or form submission into a memory bank
  • Recall relevant context before an LLM step so the model sees prior history
  • Reflect to ask synthesizing questions ("What do we know about this customer?") inside a flow

Installation

Flowise distributes nodes only inside its main monorepo, so installation today means using a Flowise checkout with the Hindsight nodes copied in. The user-facing distribution will be the upstream PR to FlowiseAI/Flowise.

git clone https://github.com/FlowiseAI/Flowise.git
cd Flowise

# Copy the three tool nodes
cp -r /path/to/hindsight/hindsight-integrations/flowise/nodes/tools/Hindsight* \
  packages/components/nodes/tools/

# Copy the credential class
cp /path/to/hindsight/hindsight-integrations/flowise/credentials/HindsightApi.credential.ts \
  packages/components/credentials/

# Add the client dep
cd packages/components && pnpm add @vectorize-io/hindsight-client
cd ../.. && pnpm install && pnpm build
pnpm start  # opens http://localhost:3000

Setup

:::tip Hindsight Cloud (recommended) Sign up free — no infrastructure to run. Skip straight to creating your credential below. :::

  1. Sign up at Hindsight Cloud (free tier) or self-host
  2. Get an API key from the Hindsight dashboard
  3. In Flowise, create a new credential of type Hindsight API:
    • API URL — defaults to https://api.hindsight.vectorize.io (Cloud); change for self-hosted
    • API Key — your hsk_... key (optional for self-hosted unauthenticated instances)

Tools

Each Hindsight tool node returns a LangChain DynamicStructuredTool, so it slots into any agent that accepts tools.

Hindsight Retain

Stores content in a memory bank. Hindsight extracts facts asynchronously after the call returns.

Field Description
Default Bank ID Memory bank to retain into when the agent doesn't pass one

Tool input schema (the agent passes these): bankId, content, optional tags.

Hindsight Recall

Searches a bank for memories relevant to a query. Returns ranked results.

Field Description
Default Bank ID Memory bank to search when the agent doesn't pass one
Default Budget low / mid / high

Tool input schema: bankId, query, optional budget, maxTokens, tags.

Hindsight Reflect

Returns an LLM-synthesized answer over the bank.

Field Description
Default Bank ID Memory bank to reflect on when the agent doesn't pass one
Default Budget low / mid / high

Tool input schema: bankId, query, optional budget.

Example chatflow

Conversational support agent

  1. ChatOpenAI (or any chat LLM)
  2. Conversational Agent with three tools attached: Hindsight Retain + Hindsight Recall + Hindsight Reflect, all sharing the same hindsightApi credential
  3. Set Default Bank ID to something like user-${sessionId} on each tool
  4. The agent learns to call Recall before answering and Retain after meaningful exchanges. Use Reflect for "what do we know about this user?" prompts.

Source