Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Research / STORM
◉AgentResearchFree

STORM

Stanford's LLM-powered knowledge curation agent that researches any topic and generates a full Wikipedia-style article.

@ai-supply
Installs86k
⟳ upstream v1.1.0 · updated 1y ago
↗ Source repository
← More ResearchResearch leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals10capabilities surfaced1known CVE9of 20 OWASP controls clear
External endpoints declaredExternal endpoints declaredBroad capability surfaceExternal endpoints declared
scanned 17d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

STORM

STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) is a research agent from Stanford OVAL that turns any topic into a well-cited, Wikipedia-quality article. It uses a multi-agent perspective-guided research loop to gather diverse information before writing.

Key Features

  • Perspective-driven research: Identifies multiple expert viewpoints and generates questions from each angle to ensure comprehensive coverage
  • Multi-source retrieval: Searches the web (Bing, You.com, Tavily) and synthesizes information with citations
  • Outline-first writing: Generates a structured outline before writing to ensure logical flow
  • Co-STORM mode: Interactive, collaborative research session where a human and multiple AI agents research together in real time
  • Any LLM backend: Works with GPT-4, Claude, Gemini, Llama, and local models via LiteLLM
  • Citation grounding: Every claim in the output is linked to a source URL

Quick Start

pip install knowledge-storm
from knowledge_storm import STORMWikiRunnerArguments, STORMWikiRunner
from knowledge_storm.lm import OpenAIModel
from knowledge_storm.rm import YouRM

lm_configs = STORMWikiRunnerArguments(output_dir="./output")
runner = STORMWikiRunner(lm_configs, OpenAIModel("gpt-4o"), YouRM())
runner.run(
    topic="The impact of large language models on scientific research",
    do_research=True, do_generate_outline=True, do_generate_article=True
)

Add to ai-supply

npx ai-supply add storm-research-agent

Curated mirror of the open-source STORM (MIT). Get it from the source.

Rating rank
#1
of 17 in Research
Install rank
#4
of 17 in Research
Security score
75/100 · B
review
Security rank
#9
of 17 in Research
Installs
86k
cat avg 51k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Research leaderboard →
! Security: Review · 7575/100 · grade Bscanned 17d ago
✓ no compromise signals11 risk-surface · 6/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ network⚑ secrets
egress → pre-commit.com, storm.genie.stanford.edu, arxiv.org, www.arxiv.org, storm-project.stanford.edu, img.shields.io, docs.litellm.ai, huggingface.co +28

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 10 pip requirements declared · stanford-oval-storm-fb951af/frontend/demo_light/requirements.txtrisk surface
•Dependency manifest — 12 pip requirements declared · stanford-oval-storm-fb951af/requirements.txtrisk surface
•Vulnerable dependencies — 144 known vulnerabilities in: streamlit@1.31.1, gitpython@3.1.9, idna@3.9.0, pillow@9.5.0, protobuf@4.25.9, pyarrow@9.0.0, pymdown-extensions@9.9.2, diskcache@5.6.3 (CWE-1395)known CVE · -25 pts
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — pickle deserialization · stanford-oval-storm-fb951af/knowledge_storm/utils.py (CWE-502)risk surface
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · stanford-oval-storm-fb951af/.pre-commit-config.yamlrisk surface
•External endpoints declared — 2 distinct host(s) · stanford-oval-storm-fb951af/CONTRIBUTING.mdrisk surface
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · stanford-oval-storm-fb951af/README.md (CWE-272)risk surface
•External endpoints declared — 11 distinct host(s) · stanford-oval-storm-fb951af/README.mdrisk surface
•External endpoints declared — 7 distinct host(s) · stanford-oval-storm-fb951af/examples/storm_examples/README.mdrisk surface
•External endpoints declared — 10 distinct host(s) · stanford-oval-storm-fb951af/knowledge_storm/lm.pyrisk surface
•External endpoints declared — 13 distinct host(s) · stanford-oval-storm-fb951af/knowledge_storm/rm.pyrisk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · stanford-oval-storm-fb951af/knowledge_storm/collaborative_storm/modules/information_insertion_module.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 10 pip requirements declared · stanford-oval-storm-fb951af/frontend/demo_light/requirements.txtrisk surface
•Dependency manifest — 12 pip requirements declared · stanford-oval-storm-fb951af/requirements.txtrisk surface
•Vulnerable dependencies — 144 known vulnerabilities in: streamlit@1.31.1, gitpython@3.1.9, idna@3.9.0, pillow@9.5.0, protobuf@4.25.9, pyarrow@9.0.0, pymdown-extensions@9.9.2, diskcache@5.6.3 (CWE-1395)known CVE · -25 pts
⚠ML09Output Integritymedium
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — pickle deserialization · stanford-oval-storm-fb951af/knowledge_storm/utils.py (CWE-502)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (4) · hygiene / uncategorized
•Unrecognized file type — '.gitignore' is not on the allowlist · stanford-oval-storm-fb951af/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · stanford-oval-storm-fb951af/LICENSErisk surface
•Unrecognized file type — '.in' is not on the allowlist · stanford-oval-storm-fb951af/MANIFEST.inrisk surface
•Suspicious network references — suspicious TLD (12 URLs) · stanford-oval-storm-fb951af/knowledge_storm/lm.pyrisk surface
✔ verified source · pinned stanford-oval-storm-fb951af
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/storm-research-agent/check). Click a policy:

Consume STORM programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/storm-research-agent

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/storm-research-agent/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add storm-research-agent

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/storm-research-agent/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "storm-research-agent" })
OpenAPI spec →
vlatest
! Security: Review · 751mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy