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.
github.com/heymrun/heymIndexed at 9b62de8Up to date with upstream
About this codebase
Heym is a self-hosted runtime and platform for building, orchestrating, running, observing, evaluating, and controlling agentic systems end-to-end: you define a workflow (graph of agents, deterministic steps, tools, and data), the runtime executes that graph with dependency/parallel coordination while recording execution history, and it outputs human-reviewable results plus interfaces to inspect, review, and consume execution state. In practice, the inputs are workflow definitions and connected tool/knowledge configurations; the pipeline is Build → Orchestrate → Run → Observe → Evaluate → Control → Expose; and the outputs are coordinated execution traces, tool results, evaluation artifacts, and exposed interfaces for people and downstream systems.
Written by gpt-5.4-nano from the index
1,643 files and 20,286 symbols in 5 modules, led by Python (786 files) and Vue (312).
Code health
This codebase scores 6.6 out of 10 for code health, which we rate fair. It also scores maintainability 6.7 and static performance 9.6 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 160 of 1,643 files are git hotspots, and they average 4.1 — which is where the fixes pay off most.
On the leaderboards:#30 of 44 Python repos
Do next
2 things worth doing in the week to Oct 1, the last indexed commit, 2 of them now.
Now
- Critical
Clean up what this week's commits left: 42 serious findings in 14 files
7 commits in the last 7 days added or worsened them, and they are still open. Start with
backend/app/services/hitl_service.py, which has 4 critical.- serious findings
- 42
- critical
- 8
- files
- 14
Large effort - High
Start breaking up execute (CCN 44, 190 lines): first lift lines 169-188
backend/app/services/node_execution/nodes/llm_node.py:169
execute nests its control flow deeply, and part of it is duplicated, so splitting it also removes a copy; 3 files import it, changed 5 times in 90 days.
- gain
- +0.6 health on this file(inferred)
- health recoverable
- +0.6(inferred)
- size
- CCN 44, 190 lines, nests 6 deep
- steps
- 2 (1 mechanical)
Small effort
Improve what Repowise can see
Add a test coverage report
Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.
- line coverage
- Unknown, no report
Small effort
Use heymrun/heym in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
https://api.repowise.dev/mcp/heymrun/heymOne command, run anywhere. Adds the server to your local Claude Code config.
Docsclaude mcp add --transport http repowise https://api.repowise.dev/mcp/heymrun/heym \ --header "Authorization: Bearer rw_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_overview()
- get_answer("how is heym put together?")
- get_why("why is heym structured this way?")
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Go deeper
- OverviewEverything the index found, what changed this week, commits and decisions.
- DocumentationModule-by-module documentation, 1,859 pages, 40 written by a model.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score, the findings behind it, tests and refactoring plans.
- CommitsEach commit's effect on code health, with agent provenance.
- ContributorsWho owns what, and where one person holds most of the knowledge.
- DecisionsArchitectural decisions mined from commits and pull requests.
- Ask this codebaseSign inGrounded answers over the indexed code.
Maintain this repo? Claim the page
Sign in with GitHub and we check that you are an admin or maintainer of heymrun/heym. Then add a badge to the README that links readers here.
Use this repo from Claude or ChatGPT
Add this URL as a custom connector and sign in with repowise when asked. No API key to copy.
https://api.repowise.dev/mcp/heymrun/heymFor maintainers
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/heymrun/heym?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/heymrun/heym?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/heymrun/heym?src=badge_card)How heymrun/heym works
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. This page is a map of the heymrun/heym repository, written primarily in Python, rebuilt from the source each time it is indexed. Repowise parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the architectural decisions into documentation you can read here or query through MCP.
The codebase has 1,643 files and 20,286 symbols in 5 modules, led by Python, Vue and TypeScript. Code health is 6.6 out of 10, rated fair.
Use the links above to open each view, or connect this repository to your agent for grounded answers inside Claude, Cursor, Codex or VS Code.