Sandbox
Sign in
@sortie-ai/sortie
Harnesses#Claude Code#Codex#Copilot#Gemini CLI#Coding#Testing#Code review

Tracker tickets to agent sessions

Sortie is an orchestration layer for coding agents and issue trackers. You define the work in a `WORKFLOW.md` file, and Sortie matches issues, runs agents in parallel workspaces, retries failures, and sends feedback back into the loop. It is built as a single binary, so you do not need a separate database or job queue. The project includes tracker adapters, workflow examples, and docs for wiring it into real issue backlogs.

181 stars•16 forks•Go•Updated 7d ago
Who it's for

Builders who want GitHub Issues, Jira, Linear, GitLab, or Gitea tickets to become agent work sessions.

What it delivers

You can run multiple agent tasks from your backlog in parallel without manually launching each session.

What it does

Workflow file driven execution

Uses one `WORKFLOW.md` file to choose issues, pick an agent, and set instructions.

Parallel isolated workspaces

Runs each agent session in its own workspace so work stays separated.

Tracker integrations

Connects to GitHub Issues, GitLab Issues, Gitea Issues, Linear, and Jira.

Retry and feedback loop

Retries failed runs and can send CI and review feedback back to the agent.

Run history and cost tracking

Keeps history across restarts and tracks progress and costs.

How to get it

  1. 1Run
    curl -sSL https://get.sortie-ai.com/install.sh | sh

README

Sortie - Turn tracker tickets into agent sessions

Your next sprint isn't capped by headcount.

The open-source coding agent orchestrator.
Run the coding agents you already use on tasks from your issue tracker - in parallel, on your own machine or server.

CI codecov Go Reference

Website · Documentation · Contributing

English | 简体中文

The Problem

Coding agents can fix bugs, update dependencies, add tests, and build features. But running agents you trust across a backlog takes more than launching sessions: isolated workspaces, retries, tracker integration, and cost tracking all need to work together.

Building and maintaining that infrastructure becomes another engineering project.

Sortie is that infrastructure.

Works With

Issue trackers: GitHub Issues, GitLab Issues, Gitea Issues, Linear and Jira.

Coding agents: Claude Code, Copilot, OpenCode, Codex, Kiro and Gemini.

Install

curl -sSL https://get.sortie-ai.com/install.sh | sh

Or via Homebrew: brew install --cask sortie-ai/tap/sortie

Try the local demo with a simulated agent and no external services, or connect your tracker and coding agent.

How It Works

  1. Choose which issues to work on, which agent to run, and what instructions to give it in one WORKFLOW.md file.
  2. Sortie picks up matching issues and runs agents in parallel, each in its own workspace.
  3. Failed runs are retried automatically. Enable CI and review feedback to send failures and comments back to the agent.

Run history survives restarts. You can track progress and costs, and update the workflow without restarting Sortie.

Sortie is a single binary, with no separate database or job queue to deploy. Sortie itself sends no telemetry.

Documentation

Full configuration reference, CLI usage, and getting started guide: docs.sortie-ai.com

Prior Art

Sortie's architecture is informed by OpenAI Symphony.

License

Apache License 2.0

Files in the repo

Repository payload•32 top-level entries
  • .github
  • cmd
  • docs
  • examples
  • internal
  • scripts
  • testdata
  • .coderabbit.yaml
  • .dockerignore
  • .gitattributes
  • .gitignore
  • .golangci-no-tests.yml
  • .golangci.yml
  • .goreleaser.yaml
  • .prettierignore
  • .tool-versions
  • CHANGELOG.md
  • CLAUDE.md
  • codecov.yml
  • CONTRIBUTING.md
  • default.mk
  • Dockerfile
  • go.mod
  • go.sum
  • install.ps1
  • install.sh
  • LICENSE
  • Makefile
  • README.md
  • README.zh-CN.md
  • SECURITY.md
  • WORKFLOW.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More harnesses

affaan-m/
ECC
affaan-m/ECCHarnesses

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

258k
ruvnet/rufloHarnesses

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

72k
cobusgreyling/loop-engineeringHarnesses

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

11k