Python · Apache-2.0
deepset-ai/haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
★ 26.9k
Stars
3.4k forks · 206 open issues
+7.6/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
45.7
Momentum / 100
see the breakdown below
6y ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 17.9 | +7.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.92× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 12.8 | 26.9k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 45.7 | sum of the above |
Detail
| Topics | agent-frameworkagentic-aiagentic-ragagentsaiai-agentscontext-engineeringframeworkgenaigenerative-aiinformation-retrievallarge-language-modelsllmmcpmulti-agentorchestrationpythonragretrieval-augmented-generationsemantic-search |
| Matched on | AI Agents (agentic-ai, ai-agents, multi-agent) RAG (rag, retrieval-augmented-generation, semantic-search) Agent Skills & MCP (mcp) LLM & Inference (large-language-models) |
| Short window | +53 stars over 7 days = 7.6/day |
| Long window | +214 stars over 26 days = 8.2/day |
| Lifetime average | 10.57 stars/day over 2,548 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |