Factory DroidvsPoolside
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Factory Droid
Factory · Terminal agent
#65MCP
Panel
6.41 spec wins
- Reliability
- 6.5
- Usefulness
- 7.0
- Cost
- 5.7
- Longevity
- 6.5
“Charges $200 a month for the Max plan and still governs you with rolling rate limits, so the ceiling is the product.”
Poolside
poolside · Terminal agent
#15MCP
Panel
6.91 spec wins
- Reliability
- 6.8
- Usefulness
- 7.0
- Cost
- 6.5
- Longevity
- 7.2
“One of its three network policies is named unsafe-allow-all, which is at least the most clearly labelled decision on this board.”
Spec by spec
| Spec | Factory Droid | Poolside |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local, cloud, sandbox | local, sandbox, cloud |
| Platforms | macos, linux, windows, web | macos, linux, windows |
| Context window | not documented | 1M tokens on Laguna S 2.1, 256k on XS 2.1 and M.1 |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | YesThe first-party Droid Control plugin (droid plugin install droid-control@factory-plugins) ships an `agent-browser` driver - a Playwright-backed CLI with Chrome DevTools Protocol support that navigates, fills forms, clicks and captures screenshots, powering /qa-test and /demo. | NoWeb search and fetch are documented; there is no DOM-level browser automation. |
| Sandboxed execution | YesOS-level sandboxing isolates Droid from the filesystem and network using kernel-enforced policies (https://docs.factory.ai/autonomy-and-safety/sandbox.md). | YesTool commands run inside a container on your machine and need a local Docker engine; network policy is off, allow-list or unsafe-allow-all, enforced through a proxy container. |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | Yes | Yes`pool exec --prompt ... --output json` with POOLSIDE_API_KEY, plus a documented GitHub Actions integration. |
| Models | ||
| Backbone | Claude, GPT, Gemini, open-source and local models via BYOK | Laguna S 2.1, Laguna XS 2.1, Laguna M.1 |
| Bring your own model | YesCustom models via `anthropic`, `openai` or `generic-chat-completion-api` providers with your own baseUrl and apiKey, plus an AWS Bedrock block with awsRegion/awsProfile. | Yes |
| Local models | YesBYOK config in ~/.factory/settings.json takes a baseUrl, so Ollama (http://localhost:11434/v1), LM Studio (http://localhost:1234/v1) and vLLM are all documented targets. | YesDocumented local-run guides for Ollama and vLLM on Metal, plus full on-premises and air-gapped deployment. |
| Cost | ||
| Pricing model | subscription | mixed |
| Starts at | $20/mo | n/a |
| Free tier | No | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | No | No |
| License | proprietary | proprietary |
| GitHub stars | 41 | n/a |
Which one would each critic pick
| Critic | Factory Droid | Poolside | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 6.8 | Factory Droid — Pick Droid if you want one agent in the terminal, in Slack and in CI; pick OpenCode if you would rather read the source and hold the keys yourself. |
| El Crítico | 6.3 | 6.5 | Poolside — Isolation needs a container engine running on the machine and enforces network policy through a proxy container, which is a configuration rather than a boundary. |
| El Profesor | 6.8 | 6.5 | Factory Droid — Droid's 58.8% Terminal-Bench result names the model and the leaderboard, which is more than most vendors manage, and its harness design is documented in hooks, MCP and Missions. |
| La Inversora | 7.0 | 7.0 | no preference |
| La Jefa | 6.5 | 7.0 | Poolside — It runs inside our own network, including air-gapped, on the Kubernetes platforms we already operate, and the enterprise price is a sales conversation. |
| El Hacker | 4.8 | 7.5 | Poolside — The client is proprietary and the model weights are published under OpenMDW-1.1 and Apache-2.0, which is the exact opposite of everyone else on this board. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.