deepset-ai/haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 2nd, 2026
Created on November 14th, 2019
Open Issues & Pull Requests: 132 (-1)
GitHub issues: Enabled
Number of forks: 3,097
Total Stargazers: 26,441 (+0)
Total Subscribers: 164 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 25.0 hours
Mean response time: 21.4 days
90th percentile: 29.5 days
Tracked items: 1,125

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 89% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "information-needed" is answered fastest, typically in about 5 hours, while "topic:CI" waits about 4 weeks. 33% of tracked open issues have had no activity in three months. Only 9% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 74
New in 7 days: 21
Closed in 7 days: 18
Avg open age: 260 days
Stale 30+ days: 48
Stale 90+ days: 31

Recent activity

Opened in 7 days: 17
Closed in 7 days: 10
Comments in 7 days: 4
Events in 7 days: 18

Top labels

  • P1 (330)
  • P2 (275)
  • P3 (167)
  • type:documentation (128)
  • Contributions wanted! (50)
  • information-needed (34)
  • epic (22)
  • stale (18)

Detailed Description

Haystack is an open-source AI orchestration framework for building production-ready retrieval-augmented generation and agent applications in Python.

The framework addresses the challenge of constructing complex LLM workflows by providing explicit control over key components including retrieval, routing, memory, and generation. It enables developers to design modular pipelines and agent workflows with clear data flow and component composition, moving beyond simple prompt-chaining approaches to support sophisticated multi-step reasoning and information retrieval patterns.

Teams building retrieval-augmented generation systems, multi-agent applications, semantic search features, or conversational systems should consider this framework. It suits projects requiring fine-grained control over how context is retrieved and passed to language models, as well as applications needing explicit agent orchestration and routing logic. The framework supports multimodal applications and scales to handle complex agentic workflows where multiple components must coordinate.

The project maintains rigorous code quality standards through continuous integration testing, type checking with Mypy, and code coverage tracking. Development follows consistent style enforcement using Ruff. The team actively manages security and compliance, running license compliance checks and maintaining OpenSSF Best Practices certification. Documentation is kept current and accessible through a dedicated documentation site.