pivsWarp
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
pi
Earendil Inc. · Terminal agent
#9OSS
Panel
6.82 spec wins
- Reliability
- 6.5
- Usefulness
- 6.5
- Cost
- 7.3
- Longevity
- 7.0
“A coding agent that ships themes, which is the first time anyone has cared what the terminal looks like while a file gets deleted.”
Warp
Warp · Terminal agent
#20OSSMCP
Panel
6.55 spec wins
- Reliability
- 6.5
- Usefulness
- 6.7
- Cost
- 5.5
- Longevity
- 7.2
“Scored 75.8 on SWE-bench Verified with a best-of-k wrapper, which is also how most of us get through code review.”
Spec by spec
| Spec | pi | Warp |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local, cloud |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | Yes |
| Browser control | No | YesComputer Use environments bundle Chromium plus the Playwright CLI and can attach over CDP, so the agent navigates, clicks, fills forms and reads pages. |
| Sandboxed execution | No | YesCloud runs execute in a containerized sandbox built from a Docker image with no access to the local machine; local interactive sessions are not sandboxed. |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | OpenAI, Anthropic, Google, OpenRouter, llama.cpp | GPT, Claude, Gemini, Grok, open-weight models via Fireworks |
| Bring your own model | Yes | YesAny OpenAI-compatible endpoint (OpenRouter, LiteLLM, an internal gateway) plus BYO Anthropic, OpenAI or Google keys and custom routers. |
| Local models | Yes | YesOllama, LM Studio, vLLM and llama.cpp are supported through the custom inference endpoint, but only when exposed at a public URL via a tunnel, since localhost and private addresses are rejected. |
| Cost | ||
| Pricing model | byok | mixed |
| Starts at | $0/mo | $20/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | AGPL-3.0 |
| GitHub stars | 111,339 | 65,338 |
Which one would each critic pick
| Critic | pi | Warp | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.3 | pi — Pick pi if you want a terminal agent small enough to read in an afternoon and extend in TypeScript; pick OpenCode if your workflow already depends on MCP servers. |
| El Crítico | 6.8 | 6.0 | pi — Extensions are TypeScript modules loaded into the agent's own process, so a package is a supply chain, and the install line already says --ignore-scripts. |
| El Profesor | 7.3 | 6.0 | pi — A unified LLM API, an agent loop, a TUI and a CLI in one monorepo; sessions branch into a tree with compaction that summarises abandoned branches; no benchmark is published. |
| La Inversora | 5.5 | 6.8 | Warp — Warp spent years building a terminal, open-sourced it under AGPL, and is now selling credits and $200 Max plans on top of it; the terminal is the distribution, the agent is the business. |
| La Jefa | 5.5 | 6.0 | Warp — SAML SSO and bring-your-own-key arrive at Business, $50 a seat with a 25-seat cap, so sixty engineers means Enterprise and a custom quote; approved with conditions. |
| El Hacker | 8.5 | 6.8 | pi — MIT TypeScript, extensions that add tools, commands and UI, /llama for llama.cpp on my box, ANTHROPIC_API_KEY in the environment, and packages to share it all. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.