Deploy Now

SaaS Alternative

Zapier Make Dify Cloud n8n Cloud

Stars

1,689

Forks

131

Watchers

44

Developer links

Heym

Heym lets you build AI agents and workflows on a visual canvas, run them from APIs, schedules, or chat, and watch every execution, token, and cost. Describe a system in text or voice and the AI Assistant draws the graph. Prefer hands-on? Compose it from LLM and Agent nodes, conditions, switches, loops, merges, and sub-workflows. An orchestrator calls named sub-agents in parallel. RAG runs on Qdrant or pgvector, and a knowledge graph keeps facts across runs. Triggers: cron, webhooks, messaging integrations, inbox events, WebSocket messages. Playwright nodes automate browsers, and Codex or OpenCode steps work on repositories. Checkpoints pause an agent so a person can accept, edit, or refuse before the run resumes. Every run lands in History. Traces list model requests, tool calls, tokens, latency, and USD cost, and alerts fire on errors, duration, spend, or run count. Evals compare prompts across models. OpenTelemetry exports reach Jaeger, Grafana Tempo, or Datadog. Publish workflows as REST or SSE endpoints, as MCP tools for Claude Desktop and Cursor, or as public Portal chat pages, then add dashboard widgets, Data Tables, a Kanban Board, and Drive file sharing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Source-available under the MIT License with the Commons Clause.

Heym
Heym
Heym
Heym
Heym
Heym

Benefits

  • Keep Humans In The Loop
  • Agent checkpoints pause a run so a reviewer can accept, edit, or refuse, and Heym resumes from the saved snapshot with the decision available to every downstream node.
  • See Every Token And Dollar
  • Traces record model requests, responses, tool calls, input and output tokens, and latency, while maintained pricing turns usage into USD cost you can explore by model and time range.
  • One Workflow, Many Entry Points
  • The same workflow runs from cron, webhooks, REST calls, SSE streams, MCP clients, or a public chat page, so you build the logic once and expose it everywhere.
  • Improve Prompts With Evals
  • Run repeatable prompt evaluations across several models, compare expected and actual outputs, and review saved runs to decide which prompt or model change actually helps.

Features

  • Visual Canvas And AI Assistant
  • Build workflow graphs by hand, or describe them in text or voice and let the AI Assistant generate or revise nodes, expressions, and templates for you.
  • Multi-Agent Orchestration
  • An orchestrator calls named sub-agents and sub-workflows, running independent calls concurrently, with Merge nodes, retries, backoff, error paths, and model fallback.
  • Knowledge And Persistent Memory
  • Agents retrieve documents through RAG on Qdrant or PostgreSQL with pgvector, and an optional knowledge graph keeps entities across runs with configurable sharing.
  • Traces, Analytics, And Alerts
  • Inspect tool calls and tokens, review success rates and duration, set alerts on errors or spend, and export OpenTelemetry spans to Jaeger, Grafana Tempo, or Datadog.
  • MCP, REST, And SSE Serving
  • Publish workflows as MCP tools at /api/mcp for Claude Desktop and Cursor, call them over REST, or stream execution events through SSE.
  • Board, Dashboard, And Drive
  • Kanban cards run ordered workflow chains, custom dashboard widgets are backed by workflows, and Heym Drive stores generated files behind password-protected share links.

Apps Similar to Heym