flow
Active·★ 27·Apache-2.0·Updated 2026-10-22
Aixle Flow provides a team-level control plane for AI coding agents, addressing challenges like visibility, cost tracking, and consistent setup when multiple team members use agents. It offers a Kanban board, DAG workflow engine, and container-isolated execution to make AI agents usable by teams without opening a terminal.
#AI Agent Management#Workflow Orchestration#Containerization#Cost Tracking#Kanban Board#Team Collaboration#Developer Tooling#Durable Execution
01
Features
01Kanban board with column-workflow bindings to trigger agent runs.
02DAG workflow engine supporting retries, approval gates, and parallel steps.
03Container-isolated execution for various AI coding agents (e.g., Claude Code, Cursor CLI).
04Per-session cost tracking for agent runs, displaying tokens and cents.
05Leverages Temporal for durable, long-running agent execution.
02
Compatibility
Ruby on Rails
Backend
Verified via docs
React
Frontend
Verified via docs
PostgreSQL
Database
Verified via docs
Redis
Cache/Queue
Verified via docs
Temporal
Workflow Engine
Verified via docs
Docker
Container Runtime
Verified via docs
03
Quick start
1
$ git clone https://github.com/AixleHQ/flow.git
2
$ cd flow
3
$ cp .env.example .env.development
4
$ make setup
04
Use cases
↳Managing and orchestrating AI coding agent tasks across a development team.
↳Tracking the activities, costs, and outputs of AI agents for team visibility and auditing.
↳Standardizing the setup and consistent usage of AI agents within a team.
↳Automating complex coding workflows by linking Kanban board card movements to agent actions.
05
Alternatives
omk★ 148
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
agentic-kit★ 61
One command to install, heal & prove ruflo (claude-flow) + agentic-qe — plus Claude + Codex dual-host with per-activity model routing. Thin, reversible, cross-platform.
hera★ 946
Hera makes Python code easy to orchestrate on Argo Workflows through native Python integrations. It lets you construct and submit your Workflows entirely in Python. ⭐️ Remember to star!
OpenAaaS★ 31
OpenAaaS: science agent network — bring AI to your data, not your data to AI. AaaS, Agent as a Service, MCP protocol, local execution, Docker sandbox, zero-config Rust nodes.
dos-kernel★ 20
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
cmuxlayer★ 30
cmux MCP server — 25 tools for terminal agent lifecycle management. Spawn, monitor, and orchestrate Claude, Codex, Cursor, Gemini, Kiro agents. Thinking-state detection, chunked input, layout management.
Comments
Log in to leave a comment
No comments yet. Be the first!