baml-py
BAML v0 — Python runtime for baml_client
Decision gist · record as of 2026-08-14
Yes, if you are building agents in Python and want the type safety that BAML provides. The package is actively maintained, has no known vulnerabilities, and installs cleanly across major platforms. However, verify the license terms first (currently unclear) and confirm that BAML's compilation tooling fits your workflow—baml-py is the runtime only.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- BAML programs must be compiled and available in your project; baml-py is the runtime component only.
- Medium install friction due to platform-specific binary wheels across macOS, Linux, and Windows architectures.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before adopting in commercial or restricted-license projects.
last release 2026-08-01 (13 days) · last repo commit 2026-08-14 · 9,006 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 489,945 downloads/mo, #6,372 on PyPI
Alternatives
Verify before relying
pip install baml-py
import baml_py
# Call BAML functions from your compiled BAML project- How baml-py integrates with the BAML compiler and project structure in practice
- Whether baml-py can be used standalone or requires external BAML tooling installation
- Performance characteristics and typical use patterns for agent workloads
- What the actual license terms are for this package
What it is and what it does
baml-py is the Python runtime component for BAML, a language designed specifically for building agents with a strong type system. It allows you to execute BAML code from Python, bridging the gap between BAML's compile-time safety guarantees and Python's runtime ecosystem. The package is a binary distribution with no runtime dependencies that executes pre-compiled BAML code.
BAML emphasizes preventing agent mistakes through typed errors, static analysis, and a built-in standard library for agents. The language supports green threads and colorless concurrency. baml-py enables incremental adoption—you can call BAML functions from Python alongside existing code, or integrate it into larger systems that also use other languages.
Use it for
- Build Python-based agents with compile-time type safety and error handling
- Incrementally adopt BAML in existing Python projects by calling BAML functions
- Implement agent logic with built-in testing and evaluation frameworks
- Create multi-language agent systems where Python calls BAML functions
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building agents in Python and want the type safety that BAML provides.
The package is actively maintained, has no known vulnerabilities, and installs cleanly across major platforms. However, verify the license terms first (currently unclear) and confirm that BAML's compilation tooling fits your workflow—baml-py is the runtime only.
Install
baml-py on PyPI
Before you install
Medium install friction due to platform-specific binary wheels across macOS, Linux, and Windows architectures. Active maintenance with recent releases and a well-maintained repository (9006 stars, last commit 2026-08-14).
Requires Python 3.10 or later. BAML programs must be compiled and available in your project; baml-py is the runtime component only.
License in practice
License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before adopting in commercial or restricted-license projects.
Quickstart
pip install baml-py
import baml_py
# Call BAML functions from your compiled BAML projectVerify before relying
- How baml-py integrates with the BAML compiler and project structure in practice
- Whether baml-py can be used standalone or requires external BAML tooling installation
- Performance characteristics and typical use patterns for agent workloads
- What the actual license terms are for this package
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 13 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 489,945 / month, #6,372 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: baml_py-0.225.0-cp38-abi3-macosx_10_12_x86_64.whl; baml_py-0.225.0-cp38-abi3-macosx_11_0_arm64.whl; baml_py-0.225.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; baml_py-0.225.0-cp38-abi3-manylinux_2_24_aarch64.whl; baml_py-0.225.0-cp38-abi3-musllinux_1_1_aarch64.whl; baml_py-0.225.0-cp38-abi3-musllinux_1_1_x86_64.whl; baml_py-0.225.0-cp38-abi3-win_amd64.whl; baml_py-0.225.0-cp38-abi3-win_arm64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agent programming language”
- baml-pybaml-py is the Python runtime for executing BAML programs, a language…
- dspy-aiDSPy is a framework for building and optimizing modular AI systems…
- llama-index-program-openaiIntegrates OpenAI-powered program synthesis with LlamaIndex, enabling…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also baml-bridge · smolagents · agent-framework-ollama · hol-guard · camel-ai · agent-framework-core · letta · praisonaiagents · openai-agents · agentlightning