Skip to content
ai-supply.store
استكشافالفئاتلوحة المتصدرينالمجتمعAgent APIFAQ
تسجيل الدخولإنشاء حساب مجاني
catalog / Agentic capability / MetaGPT
◉AgentAgentic capabilityFree

MetaGPT

Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.

@ai-supply
التثبيتات1.0M
⟳ upstream v0.8.1 · updated 2y ago
↗ مستودع المصدر
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals50capabilities surfaced1known CVE5of 20 OWASP controls clear
Suspicious network referencesSuspicious network referencesSuspicious network referencesSuspicious network references
scanned 18d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

MetaGPT

MetaGPT encodes software company SOP (standard operating procedures) into multi-agent collaboration. Given a one-line requirement, MetaGPT spawns Product Managers, Architects, Engineers, and QA Testers as separate agents — each with defined roles, memory, and tool access — to collaboratively produce PRDs, system designs, complete code, and unit tests.

Key Features

  • Role-based agents — PM, Architect, Engineer, QA, and Data Analyst roles with structured handoffs
  • Shared message pool — agents communicate via a structured blackboard rather than direct prompts
  • Incremental development — supports iterative code generation, review, and debugging loops
  • Tool integration — agents can browse the web, run code in a sandbox, and call external APIs
  • Multi-model backend — works with OpenAI, Anthropic, local Ollama, and any LiteLLM-compatible provider
  • Data Interpreter — specialized sub-agent for end-to-end data science pipelines

Quick Start

pip install metagpt
metagpt "Write a CLI tool to convert CSV files to JSON"
import asyncio
from metagpt.software_company import generate_repo

async def main():
    await generate_repo("Create a REST API for a todo list app")

asyncio.run(main())

Install via ai-supply

npx ai-supply add metagpt-multi-agent-framework

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

Rating rank
#1
of 35 in Agentic capability
Install rank
#1
of 35 in Agentic capability
Security score
75/100 · B
review
Security rank
#23
of 35 in Agentic capability
Installs
1.0M
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 7575/100 · grade Bscanned 18d ago
✓ no compromise signals51 risk-surface · 10/20 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⚑ shell⚑ network⚑ secrets
egress → containers.dev, marketplace.visualstudio.com, codespaces.new, docs.github.com, img.shields.io, vscode.dev, aka.ms, code.visualstudio.com +32

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 — 2 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/examples/android_assistant/requirements.txtrisk surface
•Dependency manifest — 7 npm dependencies declared · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/package.jsonrisk surface
•Dependency manifest — 22 npm dependencies declared · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/package.jsonrisk surface
•Non-registry dependency source — 1 dependency/ies pulled from git/URL/file · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/package.json (CWE-829)risk surface
•Dependency manifest — 4 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/metagpt/ext/sela/requirements.txtrisk surface
•Dependency manifest — 71 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/requirements.txtrisk surface
•Non-registry dependency source — 1 requirement(s) from git/URL/editable · FoundationAgents-MetaGPT-11cdf46/requirements.txt (CWE-829)risk surface
•Vulnerable dependencies — 151 known vulnerabilities in: pillow@9.5.0, pyarrow@9.0.0, pycryptodome@3.9.9, requests@2.9.2, aiohttp@3.8.6, curl-cffi@0.7.4, gitpython@3.1.40, qdrant-client@1.7.0 (CWE-1395)known CVE · -25 pts
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/documents.txt (CWE-77)expected
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · FoundationAgents-MetaGPT-11cdf46/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution · FoundationAgents-MetaGPT-11cdf46/examples/build_customized_agent.py (CWE-78)expected
•Suspicious code patterns — dynamic code execution · FoundationAgents-MetaGPT-11cdf46/examples/di/InfiAgent-DABench/DABench.py (CWE-95)expected
•Suspicious code patterns — OS command execution; dynamic code execution · FoundationAgents-MetaGPT-11cdf46/metagpt/actions/run_code.py (CWE-78)expected
•Suspicious code patterns — pickle deserialization · FoundationAgents-MetaGPT-11cdf46/metagpt/ext/sela/search/tree_search.py (CWE-502)expected
•Suspicious code patterns — dynamic code execution; pickle deserialization · FoundationAgents-MetaGPT-11cdf46/metagpt/utils/serialize.py (CWE-95)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 9 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/.devcontainer/README.mdexpected
•External endpoints declared — 3 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/.devcontainer/devcontainer.jsonexpected
•External endpoints declared — 1 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/.github/ISSUE_TEMPLATE/config.yamlexpected
•External endpoints declared — 16 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/README.mdexpected
•External endpoints declared — 2 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/config/examples/groq-llama3-70b.yamlexpected
•External endpoints declared — 7 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/.well-known/metagpt_oas3_api.yamlexpected
•External endpoints declared — 4 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/.well-known/skills.yamlexpected
•External endpoints declared — 8 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/FAQ-EN.mdexpected
•External endpoints declared — 5 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/NEWS.mdexpected
•External endpoints declared — 10 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/README_CN.mdexpected
•External endpoints declared — 14 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/docs/README_FR.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/answer.json (CWE-272)risk surface
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/documents.txt (CWE-272)risk surface
•External endpoints declared — 6 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/documents.txtexpected
•External endpoints declared — 12 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/examples/di/README.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · FoundationAgents-MetaGPT-11cdf46/examples/rag/rag_pipeline.py (CWE-918)expected
•Egress to a private/loopback host — 172.31.0.51 · FoundationAgents-MetaGPT-11cdf46/metagpt/const.py (CWE-918)expected
•External endpoints declared — 11 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/metagpt/utils/token_counter.pyexpected
•External endpoints declared — 165 distinct host(s) · FoundationAgents-MetaGPT-11cdf46/tests/data/search_rsp_cache.jsonexpected
•Egress to a private/loopback host — 192.168.50.82 · FoundationAgents-MetaGPT-11cdf46/tests/metagpt/roles/mock.py (CWE-918)expected
⚠LLM07System Prompt Leakagemedium
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · FoundationAgents-MetaGPT-11cdf46/metagpt/const.py (CWE-200)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · FoundationAgents-MetaGPT-11cdf46/metagpt/learn/text_to_speech.py (CWE-798)risk 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 · FoundationAgents-MetaGPT-11cdf46/metagpt/actions/di/execute_nb_code.py (CWE-835)risk surface
⚠LLM02Sensitive Information Disclosurelow
Secrets, credentials or PII shipped inside the artifact.
•Low-confidence secret match — 1 possible: generic-api-key · FoundationAgents-MetaGPT-11cdf46/metagpt/learn/text_to_speech.py (CWE-798)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓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.
✓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 — 2 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/examples/android_assistant/requirements.txtrisk surface
•Dependency manifest — 7 npm dependencies declared · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/package.jsonrisk surface
•Dependency manifest — 22 npm dependencies declared · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/package.jsonrisk surface
•Non-registry dependency source — 1 dependency/ies pulled from git/URL/file · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/package.json (CWE-829)risk surface
•Dependency manifest — 4 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/metagpt/ext/sela/requirements.txtrisk surface
•Dependency manifest — 71 pip requirements declared · FoundationAgents-MetaGPT-11cdf46/requirements.txtrisk surface
•Non-registry dependency source — 1 requirement(s) from git/URL/editable · FoundationAgents-MetaGPT-11cdf46/requirements.txt (CWE-829)risk surface
•Vulnerable dependencies — 151 known vulnerabilities in: pillow@9.5.0, pyarrow@9.0.0, pycryptodome@3.9.9, requests@2.9.2, aiohttp@3.8.6, curl-cffi@0.7.4, gitpython@3.1.40, qdrant-client@1.7.0 (CWE-1395)known CVE · -25 pts
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/documents.txt (CWE-77)expected
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · FoundationAgents-MetaGPT-11cdf46/Dockerfile (CWE-78)expected
•Suspicious code patterns — OS command execution · FoundationAgents-MetaGPT-11cdf46/examples/build_customized_agent.py (CWE-78)expected
•Suspicious code patterns — dynamic code execution · FoundationAgents-MetaGPT-11cdf46/examples/di/InfiAgent-DABench/DABench.py (CWE-95)expected
•Suspicious code patterns — OS command execution; dynamic code execution · FoundationAgents-MetaGPT-11cdf46/metagpt/actions/run_code.py (CWE-78)expected
•Suspicious code patterns — pickle deserialization · FoundationAgents-MetaGPT-11cdf46/metagpt/ext/sela/search/tree_search.py (CWE-502)expected
•Suspicious code patterns — dynamic code execution; pickle deserialization · FoundationAgents-MetaGPT-11cdf46/metagpt/utils/serialize.py (CWE-95)expected
§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.
✓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 (31) · hygiene / uncategorized
•Unrecognized file type — '.coveragerc' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/.coveragercrisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/.dockerignorerisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/.gitattributesrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/Dockerfilerisk surface
•Unrecognized file type — '.in' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/MANIFEST.inrisk surface
•Suspicious network references — suspicious TLD (2 URLs) · FoundationAgents-MetaGPT-11cdf46/config/examples/spark_lite.yamlrisk surface
•Unrecognized file type — '.example' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/docs/.agent-store-config.yaml.examplerisk surface
•Unrecognized file type — '.pylintrc' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/docs/.pylintrcrisk surface
•Suspicious network references — suspicious TLD (21 URLs) · FoundationAgents-MetaGPT-11cdf46/docs/.well-known/metagpt_oas3_api.yamlrisk surface
•Suspicious network references — suspicious TLD (7 URLs) · FoundationAgents-MetaGPT-11cdf46/docs/.well-known/skills.yamlrisk surface
•Suspicious network references — suspicious TLD (17 URLs) · FoundationAgents-MetaGPT-11cdf46/docs/FAQ-EN.mdrisk surface
•Suspicious network references — suspicious TLD (16 URLs) · FoundationAgents-MetaGPT-11cdf46/docs/README_JA.mdrisk surface
•Unrecognized file type — '.docx' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/examples/data/omniparse/test01.docxrisk surface
•Suspicious network references — URL shortener (3 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/answer.jsonrisk surface
•Suspicious network references — URL shortener (7 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/RGB_En/documents.txtrisk surface
•Suspicious network references — suspicious TLD (6 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/data/rag_bm/simplified_RGB/documents.txtrisk surface
•Suspicious network references — suspicious TLD (13 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/di/README.mdrisk surface
•Suspicious network references — suspicious TLD (10 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/di/requirements_prompt.pyrisk surface
•Suspicious network references — suspicious TLD (1 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/mgx_write_project_framework.pyrisk surface
•Suspicious network references — raw IP URL (1 URLs) · FoundationAgents-MetaGPT-11cdf46/examples/rag/rag_pipeline.pyrisk surface
•Suspicious network references — raw IP URL (2 URLs) · FoundationAgents-MetaGPT-11cdf46/metagpt/const.pyrisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/metagpt/environment/minecraft/mineflayer/.prettierignorerisk surface
•Suspicious network references — suspicious TLD (3 URLs) · FoundationAgents-MetaGPT-11cdf46/metagpt/provider/zhipuai/zhipu_model_api.pyrisk surface
•Suspicious network references — suspicious TLD (8 URLs) · FoundationAgents-MetaGPT-11cdf46/metagpt/tools/iflytek_tts.pyrisk surface
•Suspicious network references — suspicious TLD (15 URLs) · FoundationAgents-MetaGPT-11cdf46/metagpt/utils/token_counter.pyrisk surface
•Unrecognized file type — '.ini' is not on the allowlist · FoundationAgents-MetaGPT-11cdf46/pytest.inirisk surface
•Suspicious network references — raw IP URL (3 URLs) · FoundationAgents-MetaGPT-11cdf46/tests/conftest.pyrisk surface
•Suspicious network references — suspicious TLD (1363 URLs) · FoundationAgents-MetaGPT-11cdf46/tests/data/search_rsp_cache.jsonrisk surface
•Possible obfuscation — very long lines paired with a decode/execute sink · FoundationAgents-MetaGPT-11cdf46/tests/metagpt/actions/test_summarize_code.py (CWE-506)risk surface
•Suspicious network references — suspicious TLD (20 URLs) · FoundationAgents-MetaGPT-11cdf46/tests/metagpt/tools/test_summarize.pyrisk surface
✔ verified source · pinned FoundationAgents-MetaGPT-11cdf46
Check against a policy

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

Consume MetaGPT 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/metagpt-multi-agent-framework

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

# CLI
npx ai-supply add metagpt-multi-agent-framework

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

# MCP tool
install_listing({ "slug": "metagpt-multi-agent-framework" })
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 →
⇄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
◇MCP server
GitHub MCP Server
Official GitHub MCP server — give your AI agent full read/write access to repos, issues, PRs, and actions.
↓ 771k
ai-supply.store

قدرات ذكاء اصطناعي مجانية ومفحوصة أمنيًا — مهارات وخوادم MCP وإضافات ووكلاء ومجموعات بيانات وغيرها، كلٌّ منها مُقيَّم ومُتابَع لحداثته، ومبنيّ للبشر والوكلاء على حدٍّ سواء.

api · v3.1status · all green
تواصل معنا
support@ai-supply.storesecurity@ai-supply.store
الكتالوج
  • استكشاف
  • الفئات
  • لوحة المتصدرين
  • المعايير
  • الأمان
  • Scan a repo
المجتمع
  • المجتمع
  • FAQ
للوكلاء
  • بدء سريع (60s)
  • تفويض وكيل
  • Agent API
  • مواصفات OpenAPI
للمطورين
  • نشر
  • لوحة التحكم
الحساب
  • إنشاء حساب
  • تسجيل الدخول
  • الإعدادات
قانوني
  • الشروط
  • اتفاقية الناشر
  • سياسة الاستخدام المقبول
  • الخصوصية