AI Agent Platforms
The project documents an Ollama lane for local model use; desktop hardware and model downloads remain the user’s responsibility.
Captain Claw is MIT-licensed. Local Ollama inference avoids a per-request provider API bill when a compatible model is selected. Optional hosted models, connectors, and any external services have separate terms and charges. No weights are bundled. The official Ollama qwen2.5-coder:7b listing states Apache-2.0 and 4.7GB; verify compatibility and model licensing separately. Local hardware, storage, download, and electricity still have costs. Optional remote inference can be billed.
Pricing checked .
Check official pricing
A desktop automation and agent workspace that can connect to a local Ollama model or separately billed cloud providers. Visit the project website to check the currently available deployment options.
Official README and root license checked against this revision on 2026-11-01. Local model and provider costs are recorded separately; AltStack did not execute the project or its installers.
Availability checked 1 Nov 2026. Check the provider’s release or installation information
The MIT application is free. A local model uses your hardware and separately licensed weights; optional provider inference may be billed.
No one-line command has been verified for Captain Claw; follow its official installation instructions instead of guessing a Docker image or installer.
Captain Claw provider setup documentationTechnologies recorded in the catalog snapshot.
Use a desktop AI agent with persistent context and integrations across communication platforms.
The MIT-licensed agent can run locally without a software license fee. Model APIs, optional Nous Portal subscriptions, search or other services, and cloud machines may charge separately. A free agent is not free access to every model.
Use an AI assistant to write and edit code.
OpenCode can be used without a Go subscription. Optional Go is USD 10/month and Go Plus USD 40/month, with model-specific usage limits. Local models use your hardware; connected provider APIs and subscriptions bill separately. Promotional free models are limited-time offers.
Build and run AI agents that handle recurring work for you.
Self-hosting has no license fee; you pay for infrastructure and model providers. The hosted Platform is paid with usage-based runs. Platform code uses Polyform Shield for personal/internal business use; classic components are MIT, so the whole platform should not be described as MIT open source.
Build AI chatbots and automated workflows.
Cloud Sandbox is free with limited credits and storage. The provider lists Professional at USD 590/workspace/year and Team at USD 1,590/workspace/year on annual billing, before applicable taxes. Community self-hosting uses your infrastructure; model API keys and paid features can add costs.
Prototype AI workflows visually and connect components into runnable applications.
The published Langflow builder has a free self-hosted option. Your server, database, external model APIs and integrations may cost money. Any managed cloud allowance is a separate provider plan, not unlimited free model usage.
Minimal terminal coding agent you can fully customize.
Official README supplies the installable Pi harness under MIT and instructs users to connect their own provider subscription or API key. The free harness does not include model usage or provider subscription fees.
Allow Google Analytics to measure page visits and basic device information using cookies? Your searches and form entries are excluded. You can change this choice at any time. Privacy details.
