heymrun/heym
Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure. observed · 2026-09-03
Health v2 · maintenance only
78/100
- Activity 100
- Release rhythm 88
- Longevity 11
Flags: young no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 1.0
- age_days: 158
- days_rel: 0
- days_push: 0
- n_releases_24m: 103
Adoption not part of the score
1083 stars · 90 forks observed · 2026-09-03
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Heym is an AI-native, low-code workflow automation platform with a visual drag-and-drop editor for building agentic systems. It provides LLM and Agent nodes, RAG over Qdrant or Postgres/pgvector, MCP client/server support, human-in-the-loop approvals, execution traces, and evals, and is source-available and fully self-hostable via Docker Compose or Kubernetes.
Use cases
- automate business processes with ai agents
- build ai workflows without coding
- orchestrate multiple llm agents
- self-host an n8n alternative
- add human approval checkpoints to automations
- build rag pipelines over company knowledge
- connect mcp tools to agents
- generate workflows from natural language
When to choose
- you want a self-hosted, AI-first workflow platform with agents, RAG, and MCP built in
- you need human-in-the-loop approvals, tracing, and evals for production automations
- you prefer visual low-code building with optional natural-language workflow generation
- you want data and automations to stay on your own infrastructure
When to avoid
- you need a permissively licensed tool - Heym is source-available with a Commons Clause condition
- you only need simple trigger-action automations without AI, where lighter tools suffice
- you want a fully managed SaaS rather than self-hosting
- you need a mature, long-proven platform rather than a young project (v0.0.x)
Facets
application · maturity active
workflow-automation agent-framework rag mcp chatbot llm-inference webhook scheduling self-hosted data-visualization large-language-models self-hosted developer-tools messaging-platforms self-hosted python cross-platform low-code no-code visual-workflow-editor human-in-the-loop multi-agent-orchestration n8n-alternative source-available qdrant pgvector evals tracing mcp-server mcp-client browser-automation guardrails ai-agents automation retrieval-augmented-generation docker kubernetes web-server
10 sources
- readme: https://github.com/heymrun/heym · fetched 2026-09-03 · ed5c4cd16cd8
- homepage: https://heym.run · fetched 2026-08-29 · fd3455404da5
- site_page: https://heym.run/features · fetched 2026-08-29 · a8a6420b206e
- site_page: https://heym.run/docs/reference/environment-variables · fetched 2026-08-29 · e4aee453d589
- site_page: https://heym.run/docs/getting-started/introduction · fetched 2026-08-29 · 16296b1df485
- site_page: https://heym.run/docs/reference/node-types · fetched 2026-08-29 · edecc210749c
- site_page: https://heym.run/docs/reference/integrations · fetched 2026-08-29 · 46489bcc63d7
- site_page: https://heym.run/docs/reference/features · fetched 2026-08-29 · ebf787d785a1
- site_page: https://heym.run/docs · fetched 2026-08-29 · b48145002bae
- site_page: https://heym.run/changelog · fetched 2026-08-29 · f134fbb3e2c1
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| heymrun/heym | main | 78 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem