Open SWE vs pi
Two of the top projects in Coding agents and AI editors, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
Open SWE
Agent that turns issues into pull requests, reviews PRs and monitors CI
pi
Terminal coding agent with extensions, skills, and an SDK
Verdict
Open SWE ranks higher, 83 to 80. Of the 5 score parts we measure for both, Open SWE leads on 3, pi on 1 and 1 is even.
- Adoptionpi leads by 29 points, 98 to 69: a wide gap.
- FreshnessEven at 100.
- MaintenanceOpen SWE leads by 3 points, 100 to 97: close to even.
- Easy to runOpen SWE leads by 17 points, 67 to 50: a wide gap.
- Agent-readyOpen SWE leads by 55 points, 85 to 30: a wide gap.
Pick Open SWE if you are
Teams building an internal coding agent that ships PRs from issues
- Covers the full loop: implement, open PR, review, CI monitoring via /baby-sit, and follow-ups
- Triggers from dashboard, GitHub, Slack, and Linear (via MCP)
Pick pi if you are
Developers who want a scriptable, customizable terminal coding agent
- Multiple interfaces: interactive CLI, print/JSON mode, RPC and a TypeScript SDK
- Extensions, skills, prompt templates and themes ship as npm or git packages
| What we compare | Open SWE | pi |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 69, popular | 98, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 100, healthy | 97, healthy |
| Easy to run | 67, easy | 50, easy |
| Agent-ready | 85, ready | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 11.1k | 117k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Python | TypeScript |
| Docker | Yes | No |
| GPU | Not stated | Not needed |
| arm64 or Apple Silicon | Mentioned | Mentioned |
Open SWE
Open SWE is a LangChain coding agent built on Deep Agents and LangGraph. It takes work from a dashboard, GitHub issues and PRs, Slack or Linear, implements changes in per-thread Linux sandboxes, and opens pull requests. It also reviews PRs, learns review preferences, and watches CI. The README says it is under active development and accepts no external issues or contributions.
Who it is for: Teams building an internal coding agent that ships PRs from issues
Strengths
- Covers the full loop: implement, open PR, review, CI monitoring via /baby-sit, and follow-ups
- Triggers from dashboard, GitHub, Slack, and Linear (via MCP)
- Models, sandbox provider, skills, and MCP servers are configurable; local execution is supported
- Persistent per-thread sandboxes reuse context; independent threads run in parallel
Weaknesses
- Deploying as-is requires Managed Deep Agents; otherwise the README advises forking and adapting
- Breaking changes expected; no stability or compatibility guarantees
- Not accepting issues or external contributions
- Sandboxes normally get installation-wide GitHub App access; approvals only guard detected Git pushes
- Docker + Compose
- Needs Managed Deep Agents, LangSmith, GitHub App, Slack, Linear
pi
Pi is a TypeScript coding agent CLI that runs in your project directory and connects to LLM providers through a login or API key. It is customized with extensions, skills, prompt templates and themes, shared as npm or git packages, and can be driven interactively, in print/JSON mode, over RPC, or through a TypeScript SDK. The monorepo also ships a multi-provider LLM API, an agent runtime and a terminal UI library.
Who it is for: Developers who want a scriptable, customizable terminal coding agent
Strengths
- Multiple interfaces: interactive CLI, print/JSON mode, RPC and a TypeScript SDK
- Extensions, skills, prompt templates and themes ship as npm or git packages
- Core libraries (pi-ai, pi-agent-core, pi-tui) are published as separate packages
- Installer pins dependencies; Nix flake builds on Linux and macOS, ARM64 and x86-64
Weaknesses
- No built-in permission system; runs with the launching user's full permissions
- Sub-agents and plan mode are intentionally omitted and must be added via packages
- Requires Node.js 22.19 or newer
- New contributors' issues and PRs are auto-closed by default
- no GPU
- Needs Node.js 22.19+, LLM provider API key or subscription
- Models: OpenAI, Anthropic, Google
More in Coding agents and AI editors
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.