# SylphAI-Inc/AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.

Repository: https://github.com/SylphAI-Inc/AdalFlow
Canonical: https://ross.abutalabs.com/products/adalflow
Homepage: http://adalflow.sylph.ai/
Language: Python
License: MIT
License Family: permissive
Topics: agent, framework, llm, rag, generative-ai, machine-learning, nlp, python, retriever, ai, chatbot, information-retrieval, question-answering, summarization, bm25, faiss, reranker, optimizer, trainer, auto-prompting
Last push: 2026-05-29T05:49:13+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 49, longevity 61
- inputs: {"age_days": 866, "days_push": 96, "days_rel": 342, "gap_med": 23, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4211, forks 387 (observed 2026-08-28T04:08:39.073571+00:00)

## What it is
AdalFlow is a PyTorch-like Python library for building and auto-optimizing LLM application workflows such as chatbots, RAG pipelines, and agents. It provides composable components (generators, embedders, retrievers, tools) plus trainers and optimizers that tune prompts and few-shot demos automatically.

## Use cases
- build a RAG pipeline in python
- auto-optimize llm prompts
- build a chatbot with tool calling
- create an ai agent framework
- optimize few-shot examples for llm tasks
- evaluate llm applications
- build question answering over documents

## When to choose
- you want a code-first, PyTorch-like framework for LLM workflows
- you need automatic prompt or few-shot demo optimization
- you're building RAG, chatbots, or agents in Python with multi-provider LLM support
- you want built-in tracing, evaluation, and training loops for LLM pipelines

## When to avoid
- you need a no-code or UI-driven LLM builder
- you want a lightweight single-call SDK rather than a full workflow framework
- your stack is not Python
- you need production orchestration features like queues or scaling out of the box

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, llm-inference, prompt-engineering, machine-learning, nlp, sdk
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cross-platform
- tags: llm-workflows, auto-optimization, text-grad, retrievers, pytorch-like, few-shot-optimization, tracing, structured-output, retrieval-augmented-generation, ai-agents, natural-language-processing

## Member repositories
- SylphAI-Inc/AdalFlow (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:39.073571+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 2026-08-29T18:22:29.108152+00:00, confidence not recorded.
  - readme: https://github.com/SylphAI-Inc/AdalFlow (fetched 2026-08-28T04:08:39.073571+00:00, sha 638965d9231b)
  - homepage: http://adalflow.sylph.ai/ (fetched 2026-08-29T09:12:44.738750+00:00, sha dbfb57376a1f)
  - registry_pypi: https://pypi.org/pypi/adalflow/json (fetched 2026-08-29T09:12:44.758224+00:00, sha 24ce26b5a846)
  - site_page: http://adalflow.sylph.ai/integrations/index.html (fetched 2026-08-29T09:12:44.748404+00:00, sha 102e9a4f5ad3)
  - site_page: http://adalflow.sylph.ai/integrations/integrations.html (fetched 2026-08-29T09:12:44.750315+00:00, sha dd6880ec84eb)
  - site_page: http://adalflow.sylph.ai/integrations/openai.html (fetched 2026-08-29T09:12:44.752184+00:00, sha 98023835b2bb)
  - site_page: http://adalflow.sylph.ai/integrations/anthropic.html (fetched 2026-08-29T09:12:44.754208+00:00, sha c2ce14883652)
  - site_page: http://adalflow.sylph.ai/integrations/ollama.html (fetched 2026-08-29T09:12:44.756458+00:00, sha 2997f95e2bbc)
- Data as of 2026-08-30T08:39:29.467469+00:00.