support

AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.
4,209 stars387 forksPythonUpdated 5/29/2026100% free · open source
What it does

AdalFlow lets you compose, run, and automatically optimize LLM pipelines in pure Python.

When to use it
  • You need a repeatable LLM workflow (prompt → model → post‑processing) that you can version‑control.
  • You want the library to automatically tune prompts or model parameters for cost or quality targets.
  • You prefer a single Python dependency instead of stitching together LangChain, PromptLayer, etc.
Ready-to-paste prompt
python demo.py  # runs the script above and prints a concise, LLM‑generated answer
Heads up: AdalFlow requires a valid OpenAI API key (or another provider key) and Python >=3.9; without the key the LLM class raises an authentication error at runtime.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/adalflow && curl -fsSL https://workflowstacks.com/api/skills/adalflow/claude-skill -o ~/.claude/skills/adalflow/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

12
top-level files
8
folders
118.3M
source size
MIT
license
Key files
.pre-commit-config.yaml
README.md
File tree
.github/
adalflow/
benchmarks/
docs/
notebooks/
scripts/
tutorials/
use_cases/
.env_example
.gitattributes
.gitignore
.pre-commit-config.yaml
AUTO_RELEASE.md
CNAME
LICENSE.md
Makefile
NOTES.md
poetry.lock
pyproject.toml
README.md
Quick Actions
Details
Creator
SylphAI-Inc
Language
Python
Category
support
Published
4/19/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Ready-to-run pack · one-time $29

Review Watchdog

Catch every bad review the day it lands — with a reply ready.

Includes the tested workflow and a written setup playbook. Needs: Google Places API key (free tier).

See what you get