[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [OpenReview review search](https://spiral.ai/integrations/muse-code/openreview-review-search)

# How to Use OpenReview review search in Muse Code

Search public reviews, meta-reviews, decisions, and comments on OpenReview. Use it to investigate criticism and discussion around research, with coverage limited to publicly readable replies.

|  |  |
| --- | --- |
| Model | OpenReview review search |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with OpenReview review search in Muse Code

- Use OpenReview review search to collect public discussion about reproducibility at ICLR.cc/2025/Conference and create an evidence table with links to the original papers.
- Use OpenReview review search to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from OpenReview review search and tell me what changed since last week.
- Check OpenReview review search and summarize what you find in three bullet points.
- Pull the newest data from OpenReview review search and give me the result as a table.

## How to set up OpenReview review search in Muse Code

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run OpenReview review search**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "openreview-net/papers/search_replies",
    "input": {
      "query": "<query>"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds OpenReview review search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## OpenReview review search tools and prices

- [OpenReview · Search replies](https://spiral.ai/tools/alexandria/openreview-net/papers/search_replies) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| limit | 1 to 100 | — | Results per page, 1-100 (default 25). |
| venue |  | — | Venue group id to scope the search to, e.g. `ICLR.cc/2025/Conference`. Omit or pass `all` for every venue. |
| offset | 0 to 10000 | — | Zero-based offset of the first result; pass the previous page's `next_offset` to continue. |

## What can you do with OpenReview review search in Muse Code?

Build a research reference in your project with OpenReview venue records, paper metadata, or public discussion. A coding agent can turn the returned records into a bibliography, venue selector, or evidence table.

### Prepare a reading group packet

Discover the relevant ICLR tracks, check their venue details, find papers on diffusion models, and summarize public discussion for a reading group.

### Choose replication candidates

Find suitable venues, inspect their public configuration, collect papers on graph neural networks, and examine public reviews for concerns worth testing in a replication.

### Write a research brief

Map the venues relevant to retrieval augmented generation, add conference context, shortlist papers from their abstracts, and distinguish paper claims from public reviewer comments.

### Plan a benchmark comparison

Identify conference editions, check their venue configuration, find papers about long-context evaluation, and use public discussion to select comparison questions for an experiment.

### Collect evidence for an evaluation checklist

Search public discussion at a selected venue and turn recurring methodological concerns into questions to check before running experiments.

### Pair papers with public criticism

Create a research digest that pairs submission abstracts with matching public reviews or comments, associating replies with their original paper.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## OpenReview review search in other agents

- [Amp](https://spiral.ai/integrations/amp/openreview-review-search)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/openreview-review-search)
- [Claude](https://spiral.ai/integrations/claude-desktop/openreview-review-search)
- [Claude Code](https://spiral.ai/integrations/claude-code/openreview-review-search)
- [Cline](https://spiral.ai/integrations/cline/openreview-review-search)
- [Codex](https://spiral.ai/integrations/codex/openreview-review-search)
- [Cursor](https://spiral.ai/integrations/cursor/openreview-review-search)
- [Devin](https://spiral.ai/integrations/devin/openreview-review-search)
- [dots](https://spiral.ai/integrations/dots/openreview-review-search)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/openreview-review-search)
- [Gemini](https://spiral.ai/integrations/gemini/openreview-review-search)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/openreview-review-search)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/openreview-review-search)
- [goose](https://spiral.ai/integrations/goose/openreview-review-search)
- [Grok](https://spiral.ai/integrations/grok/openreview-review-search)
- [Grok Build](https://spiral.ai/integrations/grok-build/openreview-review-search)
- [Hermes](https://spiral.ai/integrations/hermes/openreview-review-search)
- [Instinct](https://spiral.ai/integrations/instinct/openreview-review-search)
- [Manus](https://spiral.ai/integrations/manus/openreview-review-search)
- [Muse](https://spiral.ai/integrations/muse/openreview-review-search)
- [n8n](https://spiral.ai/integrations/n8n/openreview-review-search)
- [Notion](https://spiral.ai/integrations/notion/openreview-review-search)
- [OpenClaw](https://spiral.ai/integrations/openclaw/openreview-review-search)
- [opencode](https://spiral.ai/integrations/opencode/openreview-review-search)
- [Perplexity](https://spiral.ai/integrations/perplexity/openreview-review-search)
- [Raycast](https://spiral.ai/integrations/raycast/openreview-review-search)
- [VS Code](https://spiral.ai/integrations/vscode/openreview-review-search)
- [Windsurf](https://spiral.ai/integrations/windsurf/openreview-review-search)
- [Zapier](https://spiral.ai/integrations/zapier/openreview-review-search)

## More Muse Code guides

- [OpenReview paper search](https://spiral.ai/integrations/muse-code/openreview-paper-search)
- [OpenReview venue details](https://spiral.ai/integrations/muse-code/openreview-venue-details)
- [OpenAI model token pricing](https://spiral.ai/integrations/muse-code/openai-model-token-pricing)
- [OpenReview venue directory](https://spiral.ai/integrations/muse-code/openreview-venue-directory)
- [OpenAI model specifications](https://spiral.ai/integrations/muse-code/openai-model-specifications)
- [OpenRouter author model catalog](https://spiral.ai/integrations/muse-code/openrouter-author-model-catalog)

## Questions about OpenReview review search in Muse Code

**Can Muse Code use OpenReview review search?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run OpenReview review search like any built-in tool.

**How much does OpenReview review search cost in Muse Code?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need an Alexandria account to use OpenReview review search in Muse Code?**

No. Spiral runs OpenReview review search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up OpenReview review search in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while OpenReview review search runs?**

OpenReview review search runs in the background. Muse Code starts the run, checks on it and gives you the json when it's ready.

**Does OpenReview include every submission to a hosted venue?**

Public results depend on the venue's readership settings. Organizers can restrict submissions to the committee or to program chairs and authors, and can change that access during the workflow.

**Why can a paper be visible without its authors?**

OpenReview applies permissions to individual fields as well as whole submissions. A readable paper can therefore omit author names and author IDs.

**How far back does OpenReview's current index reach?**

Older conference records can remain on the legacy API. OpenReview says this mainly affects conferences before 2024, so the current index alone does not cover every historical venue.

**Can these searches provide a complete conference archive?**

This service does not offer complete submission browsing, full paper threads fetched by ID, or PDF downloads. Paper links and search matches are useful for discovery, but do not constitute a complete conference archive.

**What kinds of discussion does OpenReview store?**

OpenReview stores reviews, meta-reviews, decisions, and public comments as notes. A reply's forum identifies the original submission it belongs to.

