heym

Self-hosted runtime for building, running, observing and evaluating agents and workflows, with approval checkpoints.

Builder by heymrun

IndexedOther★ 1,261

Get started

About

Heym is a self-hosted runtime for agentic systems, where agents and deterministic workflows are composed visually or generated with AI. Workflows run from APIs, schedules, event triggers, MCP clients or chat portals, and executions record traces, tool calls and model costs. Workflows can pause at review checkpoints until a person decides, and the README badges show an MIT license with a Commons Clause condition.

Use cases: agent-orchestration, workflow-automation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Self-host: YesREADME
Open source: YesREADME
Agent features: tools, mcp, multi-agent, human-in-the-loop, evaluations, schedulingREADME
Deployment: self-host, dockerREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 1,261
Forks: 97
Open issues: 1
Last commit: Oct 24, 2026 (4 days ago)
Last release: Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Other
Repository: github.com/heymrun/heym
Website: heym.run
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql