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.

Installs108k
⟳ upstream v1.13.0 · updated 15d ago
Source repository
! Grade B · 88/100 · ReviewSecurity assessment
No compromise signals28capabilities surfaced1known CVE8of 20 OWASP controls clear
Broad capability surfacePotentially unbounded loopPossible obfuscationSuspicious network references
scanned 12d agoosv · gitleaks · opengrep · picklescan + heuristicsfull 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.

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