whereismyai
OpenProject Agent Engine
OpenProject Agent Engine is an open source engine that polls OpenProject work packages and dispatches AI coding agents.
OpenProject Agent Engine polls OpenProject work packages and dispatches the pi coding agent to work on them. The engine claims work, prepares a per-agent clone, renders a prompt, runs the agent, verifies the outcome against GitHub and OpenProject, and performs every status transition itself. It requires Docker, OpenProject 17 with API v3, and a GitHub repository for each project. Supported agent models include hosted providers via OpenRouter or a local llama.cpp router URL. The software is open source and released under the MIT License.
OpenProject Agent Engine at a glance
Key features
- Polls OpenProject work packages
- Dispatches AI coding agents
- Prepares per-agent clones
- Verifies outcomes against GitHub and OpenProject
- Performs status transitions
- Provides a read-only web dashboard
Use it for
- Execute OpenProject work packages automatically with AI agents
- Review pull requests and manage status transitions
- Run local AI models via llama.cpp for ticket processing
Companions
Tools that articles about OpenProject Agent Engine recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to OpenProject Agent Engine
- OpenBot — Runs entirely on your own infrastructure with strict document permissions and custom.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- OpenBot — Runs AI agents locally using existing subscriptions or local models.
- Adyen — Share AI agent resources across coding tools and repositories easily.
- OpenAgents — A shared workspace for humans and AI agents with multi-device sync.
- Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
- Open Agents Template — Spawn autonomous coding agents with full sandboxes and durable workflows.
- OpenWorker — Runs locally on your device with open-source code and model choice.
- OpenHarness — Manages Claude Code, Codex, and Hermes from a single command center.
- Muse Office — It organizes AI specialist teams and creates a central dashboard for oversight.
- OpenAI Agents SDK — Provider-agnostic multi-agent framework with built-in guardrails and tracing.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
All OpenProject Agent Engine alternatives