How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

memory-reflect - Skill - OpenSmartRoute

Skillv1.0.0

memory-reflect

Name: memory-reflect
Author: vectorize-io

Answer questions about history, habits and past decisions by reasoning over Hindsight memory. Use when asked what was decided about something, how something is usually done, what changed over time…

by vectorize-io(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from vectorize-io/hindsight (hindsight-integrations/grok-bot/skills/memory-reflect/SKILL.md). Install upstream with npx skills add vectorize-io/hindsight --skill memory-reflect. Copyright stays with the author.

Reason over memory

recall returns individual memories. reflect reads across them and answers the question, which is better for anything that needs a judgement over history.

Steps

Call reflect with the user's question on the bank most likely to hold the answer: grok-bot::shared for things about the user or the team, this Bot's bank for its own work, or one of the user's other banks for their work in other tools.
If the answer depends on more than one bank, reflect on each and combine the answers, saying which part came from where.
Give the answer directly. If memory is thin or contradictory, say so rather than filling the gap.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install memory-reflect and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

vectorize-io-hindsight-memory-reflect.ocm.jsonjson

{
  "ocm": "1",
  "id": "vectorize-io-hindsight-memory-reflect",
  "kind": "skill",
  "name": "memory-reflect",
  "description": "Answer questions about history, habits and past decisions by reasoning over Hindsight memory. Use when asked what was decided about something, how something is usually done, what changed over time, or what is known about a topic.",
  "publisher": "vectorize-io",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Answer questions about history, habits and past decisions by reasoning over Hindsight memory. Use when asked what was decided about something, how something is usually done, what changed over time, or what is known about a topic."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/vectorize-io/hindsight",
      "path": "hindsight-integrations/grok-bot/skills/memory-reflect/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/vectorize-io/hindsight/blob/HEAD/hindsight-integrations/grok-bot/skills/memory-reflect/SKILL.md",
      "key": "vectorize-io/hindsight/hindsight-integrations/grok-bot/skills/memory-reflect/SKILL.md"
    }
  },
  "instructions": "# Reason over memory\n\n`recall` returns individual memories. `reflect` reads across them and answers the question, which is better for anything that needs a judgement over history.\n\n## Steps\n\n1. Call `reflect` with the user's question on the bank most likely to hold the answer: `grok-bot::shared` for things about the user or the team, this Bot's bank for its own work, or one of the user's other banks for their work in other tools.\n2. If the answer depends on more than one bank, reflect on each and combine the answers, saying which part came from where.\n3. Give the answer directly. If memory is ",
  "cost": {
    "context_tokens": 164
  }
}

Fetch it by URL: GET /api/v1/registry/vectorize-io-hindsight-memory-reflect/manifest?version=1.0.0

About

Reason over memory

Steps

Use it

Install memory-reflect and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews