LLM orchestration framework. ThoughtWorks Radar: Adopt. 8.5K GitHub stars, 450K weekly downloads.
Metrics
GitHub Stars
8,500
GitHub repository popularity
Radar Status
adopt
ThoughtWorks Technology Radar assessment
Framework Type
orchestration
Primary framework purpose
Weekly Downloads
450K
Package manager install frequency
Score Breakdown
adoption
30%82
Community size, growth velocity, and industry usage
ecosystem
25%91
Integrations, plugins, and extension availability
performance
30%85
Execution speed, latency, and resource efficiency
Compatibility(1)
Sources(1)
Related Signals(4)
Critical Vulnerability in LangChain Prompt Injection
FrameworksDec 20
92A critical prompt injection vulnerability (CVE-2025-12345) has been discovered in LangChain versions prior to 0.2.0, affecting chain-of-thought and agent implementations.
Related:
LangGraph Reaches Production Maturity
FrameworksDec 1
86LangGraph has matured into a production-ready framework for complex agent orchestration, with ThoughtWorks recommending 'Adopt' status in their Technology Radar.
Related:
LangGraph and vLLM Reach ThoughtWorks 'Adopt' Status
FrameworksNov 1
88ThoughtWorks Technology Radar Vol.33 elevated LangGraph and vLLM to 'Adopt' status, recommending them for broad production use. vLLM has become the default inference engine for Azure AI Model Catalog.
Related:
Agentic AI Frameworks Emerge: FastMCP, LiteLLM, and Pydantic AI
FrameworksNov 1
85New agent-focused frameworks are gaining traction: FastMCP simplifies MCP server implementation, LiteLLM provides unified multi-provider access, and Pydantic AI offers type-safe agent development. Model Context Protocol (MCP) is becoming the standard for LLM context and tooling.
Related: