Ollama runs language models locally and provides tools to work with model files and APIs.
Open source
24 alternativesStakpak
Stakpak runs an agent on a machine to ship code and keep applications running.
About Stakpak
Stakpak is an open source agent that installs on a user's own machines and runs in the background to ship code and keep applications running. It can generate infrastructure code, debug Kubernetes, configure CI/CD, and automate deployments, with scheduled checks and messaging through Slack, Telegram, or Discord.
Behavior is set with profiles for model, allowed tools, approval, and credentials, separate from notification routing for channels and targets. Running autopilot requires Docker, with 2GB+ RAM recommended, plus swap on small hosts and linger for Linux user services in some cases.
Key features
- Runs background autopilot agent on user's own machines 24/7
- Generates infrastructure code and automates deployments
- Debugs Kubernetes and configures CI/CD workflows
- Substitutes secrets so LLM uses credentials without seeing them
- Applies network-level policies to block destructive operations
- Schedules recurring checks and connects Slack, Telegram, Discord
Best for: Developers and operators who maintain apps on their own machines and need help with deployment and upkeep tasks.
Good for
- Runs on user's own machines as open source code
- Separates credential use from LLM access through secret substitution
- Blocks destructive operations with network-level policies before they run
Watch out for
- Requires Docker installed and accessible to the current user
- Recommends 2GB+ RAM for reliable autopilot and sandbox runs
- Small Linux hosts may need swap and linger to stay running
Stakpak at a glance
- Website
- github.com/stakpak/agent
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Stakpak alternatives
Tools and sites you could use instead, ranked by how closely they match.
The abso TypeScript SDK calls more than 100 LLM providers through an OpenAI compatible format.
Open source
24 alternatives
Glide provides an open model gateway for developing production generative AI applications.
Open source
24 alternatives
Hugging Face Text Embeddings Inference serves text embedding models through an inference solution.
Open source
24 alternatives
OpenModelZ scales LLM inference on Kubernetes with engines including vLLM, SGLang, and LMDeploy.
Open source
24 alternatives
Respan unifies LLM observability, evals, prompt optimization, and an AI gateway so teams can ship reliable AI applications.
Popular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
Stakpak FAQ
What is needed before running autopilot on a remote VM?
Docker must be installed and accessible to the current user, 2GB+ RAM is recommended, swap is recommended on small Linux hosts, and Linux user services may require linger to survive logout.
How do I start the agent?
Run stakpak init to review apps and tech stack, then stakpak autopilot up or stakpak up to start the background autopilot.
How do profiles and notifications work?
Profiles control model, allowed tools, approval, and credentials, while channels set the transport such as Slack and targets set the destination; notification routes only control where messages are delivered.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.