#141141st of 142 in Agent frameworks and SDKs
promptify
Python library for typed NLP tasks like NER and classification via LLMs
- Stars
- 4.6k
- License
- Apache-2.0
- Last commit
- Mar 2026
- Language
- Python
4,558 on 22 Apr 20264,648 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Promptify is a Python library that wraps LLM calls into task classes (NER, Classify, QA, Summarize, relation extraction, SQL generation) that return Pydantic objects. It routes requests through LiteLLM, so changing the model string switches between OpenAI, Anthropic, Ollama and other providers. It also includes batch and async calls, an evaluation module (precision, recall, F1, ROUGE) and token cost tracking.
Who it is for: Python developers extracting structured data from text with LLMs
Strengths
- Task classes return Pydantic objects instead of raw strings
- LiteLLM backend: switching provider is a model string change, including ollama/
- Built-in evaluation: precision, recall, F1, accuracy, exact match, ROUGE
- Batch with max_concurrent, async acall(), and get_cost_summary() for token cost
Weaknesses
- No GitHub release published; install is from PyPI or a git URL
- Evaluation metrics need the separate promptify[eval] extra
- No web UI, server or hosted API; use is in-process Python only
- No benchmark results given; accuracy depends on the chosen LLM
What it needs
- no GPU
- Needs LiteLLM, Pydantic, LLM provider API key or local Ollama
- Models: OpenAI, Anthropic, Google, Azure, Ollama
Also in Agent frameworks and SDKs
See all 142| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 90 out of 100 |