--- id: haystack-experimental version: "0.19.0.post1" license: Apache-2.0 license_treatment: permissive maintenance: abandoned --- # haystack-experimental — Experimental components and features for the Haystack LLM framework. License: permissive · Maintenance: abandoned · Downloads: 713.7K/mo ## What it is and what it does haystack-experimental was a staging ground for early-access features in the Haystack LLM framework, allowing users to test and provide feedback on components before they were committed to the main release. The package has now been archived and is no longer maintained. Most experiments—including Agent, AsyncPipeline, Tool calling, multimodality support, and Human-in-the-Loop features—have graduated into haystack-ai itself. A smaller set of experiments were discontinued entirely and exist only in this final release. The 0.19.0.post1 release is frozen and will receive no updates, bug fixes, or compatibility patches. It depends only on haystack-ai and supports Python 3.10 through 3.13. If you need an experiment that graduated, use haystack-ai instead. If you depend on a discontinued experiment, you must pin this package explicitly and accept that it will drift out of sync with newer haystack-ai releases over time. Use it for: - Accessing discontinued experiments (e.g., OpenAIFunctionCaller, OpenAPITool) that were not adopted into Haystack core and exist nowhere else. - Maintaining legacy code that was written against a specific experimental feature before it graduated or was discontinued. - Pinning a known-working snapshot of an experiment for production use when the graduated version in haystack-ai has breaking changes. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. Provides archived experimental features for Haystack LLM framework that have either graduated into the main haystack-ai package or been discontinued; the final release (0.19.0.post1) is no longer maintained. No, unless you have legacy code that depends on a discontinued experiment and cannot migrate to haystack-ai. The package is archived, abandoned, and will not be maintained. Any new Haystack work should use haystack-ai directly. If you do install, pin to 0.19.0.post1 explicitly and understand that compatibility with future haystack-ai releases is not guaranteed. ## Install pip install haystack-experimental uv add haystack-experimental poetry add haystack-experimental ## Installing haystack-experimental Before you install: The package is archived and abandoned as of the final release on 2026-07-28. Install friction is low (pure Python wheel), but maintenance status is critical: no further updates, bug fixes, or compatibility work will occur. Only install if pinning to 0.19.0.post1 explicitly for a discontinued experiment not available elsewhere. License in practice: Licensed under Apache-2.0 (permissive). No licensing barrier to use, but the abandoned status means you assume all maintenance and compatibility risk yourself. Quickstart: pip install "haystack-experimental==0.19.0.post1" from haystack_experimental import SomeExperiment # Use only if the experiment is not available in haystack-ai Requires Python >=3.10. Most experiments have graduated to haystack-ai; check the Haystack documentation first. Pinning to 0.19.0.post1 is mandatory—no future releases will be published. Verify before relying: - Exact compatibility window with haystack-ai versions beyond February 2026 is unclear; drift risk increases over time. - Whether all discontinued experiments remain functional or have bitrotted is not specified in the fact sheet. ## Package facts - License: Apache-2.0 (permissive) - Python support: supports_current - Install friction: low - Maintenance: abandoned - Downloads: 713.7K/month (top 15,000 on PyPI) - Known vulnerabilities: none known ## Tags haystack experimental features, haystack legacy components, archived haystack experiments, haystack early access, haystack graduated features, discontinued haystack tools, haystack ai extensions, archived, legacy [View on SkillFed](https://skillfed.io/packages/haystack-experimental) · [View on PyPI](https://pypi.org/project/haystack-experimental/)