Skip to content
ai-supply.store
DécouvrirCatégoriesClassementsCommunautéAgent APIFAQ
Se connecterInscription gratuite
catalog / Agentic capability / Griptape — Modular Python Agent Framework
◉AgentAgentic capabilityFree

Griptape — Modular Python Agent Framework

Modular Python framework for building AI agents with chain-of-thought reasoning, tool use, memory, and structured workflows.

@ai-supply
Installations108k
⟳ upstream v1.11.0 · updated 14d ago
↗ Dépôt source
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals28capabilities surfaced1known CVE8of 20 OWASP controls clear
Broad capability surfacePotentially unbounded loopPossible obfuscationSuspicious network references
scanned 9d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Griptape

Griptape is a production-grade Python framework for building deterministic AI agents and pipelines. Unlike graph-based orchestration, Griptape uses composable drivers and tasks that keep agent behaviour predictable and auditable.

Key Features

  • Prompt Drivers: swap LLM backends without code changes
  • Tool system with automatic schema generation for any Python function
  • Conversation Memory and Task Memory for multi-turn agents
  • Pipelines and Workflows for sequential and parallel task orchestration
  • Cloud offering (Griptape Cloud) for hosted execution and observability
  • First-class support for OpenAI, Anthropic, Cohere, Hugging Face, and local models

Quick Start

from griptape.structures import Agent
from griptape.tools import WebSearch, TaskMemoryClient

agent = Agent(tools=[WebSearch(), TaskMemoryClient(off_prompt=False)])
agent.run("What are the top AI agent frameworks in 2026?")

Install via ai-supply

npx ai-supply add griptape-modular-agent-framework

Curated mirror of the open-source Griptape (Apache-2.0). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#17
of 35 in Agentic capability
Security score
88/100 · B
review
Security rank
#13
of 35 in Agentic capability
Installs
108k
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 · 8888/100 · grade Bscanned 9d ago
✓ no compromise signals29 risk-surface · 7/20 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 → discord.com, semver.org, platform.openai.com, docs.aws.amazon.com, docs.griptape.ai, www.griptape.ai, img.shields.io, pypi.python.org +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 Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 1 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/calculator/requirements.txtrisk surface
•Dependency manifest — 2 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/computer/requirements.txtrisk surface
•Dependency manifest — 3 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/computer/resources/requirements.txtrisk surface
•Vulnerable dependencies — 120 known vulnerabilities in: idna@3.9.0, torch@2.9.1, filelock@3.9.1, python-multipart@0.0.9, aiohttp@3.13.4, click@8.1.8, cryptography@46.0.7, diffusers@0.33.1 (CWE-1395)known CVE · -12 pts
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · griptape-ai-griptape-93fbd84/.github/ISSUE_TEMPLATE/config.ymlexpected
•External endpoints declared — 2 distinct host(s) · griptape-ai-griptape-93fbd84/.github/ISSUE_TEMPLATE/preapproved.mdexpected
•External endpoints declared — 4 distinct host(s) · griptape-ai-griptape-93fbd84/CHANGELOG.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · griptape-ai-griptape-93fbd84/MIGRATION.md (CWE-272)risk surface
•External endpoints declared — 3 distinct host(s) · griptape-ai-griptape-93fbd84/MIGRATION.mdexpected
•External endpoints declared — 13 distinct host(s) · griptape-ai-griptape-93fbd84/README.mdexpected
•External endpoints declared — 10 distinct host(s) · griptape-ai-griptape-93fbd84/docs/assets/css/swagger-ui.css.mapexpected
•External endpoints declared — 5 distinct host(s) · griptape-ai-griptape-93fbd84/docs/assets/scripts/swagger-ui-standalone-preset.jsexpected
•Egress to a private/loopback host — 127.0.0.1 · griptape-ai-griptape-93fbd84/docs/contributing.md (CWE-918)expected
•External endpoints declared — 6 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-cloud/data-sources/create-data-source.mdexpected
•External endpoints declared — 15 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/drivers/prompt-drivers.mdexpected
•External endpoints declared — 11 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/drivers/web-search-drivers.mdexpected
•External endpoints declared — 16 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/index.mdexpected
•External endpoints declared — 118 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_12.txtexpected
•External endpoints declared — 34 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_13.txtexpected
•External endpoints declared — 82 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_14.txtexpected
•External endpoints declared — 94 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/structures/logs/task_memory_4.txtexpected
•External endpoints declared — 103 distinct host(s) · griptape-ai-griptape-93fbd84/docs/griptape-framework/structures/logs/tasks_reflect_on_tool_use.txtexpected
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — dynamic code execution · griptape-ai-griptape-93fbd84/docs/assets/scripts/swagger-ui-standalone-preset.js (CWE-95)expected
•Suspicious code patterns — OS command execution · griptape-ai-griptape-93fbd84/griptape/tools/base_tool.py (CWE-78)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 · griptape-ai-griptape-93fbd84/tests/mocks/docker/fake_api.py (CWE-200)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 · griptape-ai-griptape-93fbd84/docs/assets/scripts/swagger-ui-standalone-preset.js (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.
✓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 Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 1 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/calculator/requirements.txtrisk surface
•Dependency manifest — 2 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/computer/requirements.txtrisk surface
•Dependency manifest — 3 pip requirements declared · griptape-ai-griptape-93fbd84/griptape/tools/computer/resources/requirements.txtrisk surface
•Vulnerable dependencies — 120 known vulnerabilities in: idna@3.9.0, torch@2.9.1, filelock@3.9.1, python-multipart@0.0.9, aiohttp@3.13.4, click@8.1.8, cryptography@46.0.7, diffusers@0.33.1 (CWE-1395)known CVE · -12 pts
⚠ML09Output Integritymedium
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — dynamic code execution · griptape-ai-griptape-93fbd84/docs/assets/scripts/swagger-ui-standalone-preset.js (CWE-95)expected
•Suspicious code patterns — OS command execution · griptape-ai-griptape-93fbd84/griptape/tools/base_tool.py (CWE-78)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.
✓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 (12) · hygiene / uncategorized
•Unrecognized file type — '.coveragerc' is not on the allowlist · griptape-ai-griptape-93fbd84/.coveragercrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · griptape-ai-griptape-93fbd84/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · griptape-ai-griptape-93fbd84/LICENSErisk surface
•Unrecognized file type — '.map' is not on the allowlist · griptape-ai-griptape-93fbd84/docs/assets/css/swagger-ui.css.maprisk surface
•Possible obfuscation — very long lines paired with a decode/execute sink · griptape-ai-griptape-93fbd84/docs/assets/scripts/swagger-ui-standalone-preset.js (CWE-506)risk surface
•Suspicious network references — raw IP URL (5 URLs) · griptape-ai-griptape-93fbd84/docs/contributing.mdrisk surface
•Suspicious network references — raw IP URL (1 URLs) · griptape-ai-griptape-93fbd84/docs/griptape-framework/drivers/src/embedding_drivers_2.pyrisk surface
•Suspicious network references — raw IP URL (247 URLs) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_12.txtrisk surface
•Suspicious network references — raw IP URL (84 URLs) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_13.txtrisk surface
•Suspicious network references — raw IP URL (286 URLs) · griptape-ai-griptape-93fbd84/docs/griptape-framework/logs/index_14.txtrisk surface
•Unrecognized file type — '.tmpl' is not on the allowlist · griptape-ai-griptape-93fbd84/docs/plugins/tmpl/swagger.md.tmplrisk surface
•Unrecognized file type — '.j2' is not on the allowlist · griptape-ai-griptape-93fbd84/griptape/templates/engines/eval/results/system.j2risk surface
✔ verified source · pinned griptape-ai-griptape-93fbd84
Check against a policy

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

Consume Griptape — Modular Python Agent Framework 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/griptape-modular-agent-framework

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

# CLI
npx ai-supply add griptape-modular-agent-framework

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

# MCP tool
install_listing({ "slug": "griptape-modular-agent-framework" })
OpenAPI spec →
vlatest
! Security: Review · 881mo 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

Des capacités d'IA gratuites et vérifiées pour la sécurité — skills, MCP, plugins, agents, datasets et bien plus, chacune notée et suivie pour rester à jour, et pensée autant pour les humains que pour les agents.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalogue
  • Découvrir
  • Catégories
  • Classements
  • Benchmarks
  • Sécurité
  • Scan a repo
Communauté
  • Communauté
  • FAQ
Pour les agents
  • Démarrage rapide (60s)
  • Autoriser un agent
  • Agent API
  • Spécification OpenAPI
Pour les développeurs
  • Publier
  • Tableau de bord
Compte
  • Créer un compte
  • Se connecter
  • Paramètres
Mentions légales
  • Conditions
  • Accord éditeur
  • Utilisation acceptable
  • Confidentialité