helixml/helix
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own desktop. Run Claude, Codex, Gemini and open models on a full private GenAI Stack ♾️
Supports RAG via multiple backends (Typesense, Haystack, PGVector, LlamaIndex), MCP servers, and OpenAPI tool integration alongside an intelligent GPU scheduler that dynamically loads/unloads models based on demand. Built on a microservices architecture with Go control plane, React frontend, PostgreSQL+PGVector for embeddings, and Kubernetes/Helm deployment options, with complete execution tracing and token usage visibility across LLM calls and third-party APIs.
738 stars. Actively maintained with 966 commits in the last 30 days.
Stars
738
Forks
69
Language
Go
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
966
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/helixml/helix"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
elizaOS/eliza
Autonomous agents for everyone
Agent-Field/agentfield
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and...
gptme/gptme
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses...
SolaceLabs/solace-agent-mesh
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables...
SmythOS/sre
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI....