# griptape-ai/griptape

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

Repository: https://github.com/griptape-ai/griptape
Canonical: https://ross.abutalabs.com/products/griptape
Homepage: https://www.griptape.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: gpt, llm, openai, ai, python, huggingface, anthropic, claude
Last push: 2026-08-26T20:11:39+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 94
- inputs: {"age_days": 1327, "days_push": 7, "days_rel": 7, "gap_med": 2, "n_releases_24m": 78}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2573, forks 252 (observed 2026-08-28T04:07:01.528695+00:00)

## What it is
Griptape is a modular Python framework for building generative AI applications, providing abstractions for agents, pipelines, workflows, RAG, tools, and memory. It uses swappable drivers so developers can switch LLM providers and external services with minimal changes to business logic.

## Use cases
- build ai agents in python
- orchestrate llm workflows and pipelines
- implement rag pipelines with retrieval and memory
- build multi-agent systems with parallel workflows
- swap between openai anthropic and huggingface models
- add tools and chain-of-thought reasoning to an llm app
- retain conversation memory across llm interactions

## When to choose
- you want a Python-first framework for agents, pipelines, and RAG with clean abstractions
- you need provider-agnostic drivers to swap LLM vendors without rewriting logic
- you need built-in conversation, task, and meta memory handling
- you want to compose single agents up to systems of agents and workflows

## When to avoid
- you need a no-code visual builder rather than a code framework (consider Griptape Nodes instead)
- you only need raw LLM API calls without orchestration or memory
- your stack is not Python
- you want a fully managed hosting solution rather than a self-managed framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference, prompt-engineering, chatbot, workflow-automation, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, cloud
- tags: llm-orchestration, ai-agents, pipelines, conversational-memory, multi-provider, chain-of-thought, tools, retrieval-augmented-generation, automation

## Member repositories
- griptape-ai/griptape (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:01.528695+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:22:52.531930+00:00, confidence not recorded.
  - readme: https://github.com/griptape-ai/griptape (fetched 2026-08-28T04:07:01.528695+00:00, sha 31ccf35ee11f)
  - homepage: https://www.griptape.ai (fetched 2026-08-29T10:06:32.567641+00:00, sha 7e0ab20e70a0)
  - site_page: https://www.griptape.ai/blog/getting-started-with-custom-widget-components-in-foundry-griptape (fetched 2026-08-29T10:06:32.581247+00:00, sha 2aca0555d6ad)
  - registry_pypi: https://pypi.org/pypi/griptape/json (fetched 2026-08-29T10:06:32.586405+00:00, sha 4296a9fa3f0b)
  - site_page: https://www.griptape.ai/team (fetched 2026-08-29T10:06:32.579164+00:00, sha 013d73be5828)
- Data as of 2026-08-30T08:39:29.467469+00:00.