Head to head · Agent harnesses · October 2026 research run
Pi vs Paseo
Pi and Paseo score within a point of each other on agent readiness, 62.6 (B) and 62.1 (B). Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
Pi B
Best for Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.
Ahead on
- Reliability, 75 against 50
- Schema & documentation, 84 against 65
- Agent ergonomics, 76 against 70
- Maintenance & community, 87 against 75
Also in its favour
- Free to start without a card
Watch for
No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt
Paseo B
Best for Developers who want parallel coding agents on their own machines with no telemetry, reachable from anywhere.
Also in its favour
- No incidents deducted, where Pi loses 10 points for them
Watch for
Pre-1.0, at 0.15.3
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability Pi +25
Pi 75
Read as a local package. @earendil-works/pi-coding-agent 1.4.0 on npm (still the latest on 1 November 2026) with Node.js 22.19 or newer stated, install scripts for macOS, Linux and Windows, Nix and standalone binaries (20). A public CI workflow builds, checks and tests on every push to main and runs an MCP client conformance job. The run on the commit we cloned (ce950d7, 8 October 2026) passed, but eight of the last 15 runs on main, all on 7 and 8 October, failed. Run results weren't readable on 23 October, so this stands per the 8 October check (15). The repository API reported 308 open issues and pull requests against 113,417 stars on 8 October, not re-read on 23 October. Issues from new contributors are closed automatically and reviewed daily by maintainers, per CONTRIBUTING.md, so the open count understates what is reported, and we couldn't sample reply times (16). A dated changelog with Breaking Changes sections and migration steps, but breaking changes ship outside major versions. The Azure provider rename shipped in patch release 1.0.3 on 5 October 2026, minor release 1.2.0 on 12 October carried four (theme schema location, before_agent_start, busy-session behaviour and pi mcp list --json output), and 1.3.0 required /v1 on kimi-coding base URL overrides under Changed. The same reading as agent-zero and mistral-vibe-cli, and these breaks also take a deduction under negative events (9). 1.4.0 on 21 October 2026, with 1.0.0 dated 1 October 2026 (15).
Paseo 50
Local software. Desktop builds, an Android APK, a Docker image and a Nix package (20). ci.yml on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). CHANGELOG.md (15). Version 0.15.3 (0). 20 + 15 + 0 + 15 + 0 = 50.
Schema & documentation Pi +19
Pi 84
Harness reading, as for the other harnesses. JSON Schemas for settings, models, keybindings and themes ship in the package and, since 1.2.0 on 12 October 2026, at pi.dev/schemas/, and the JSON event stream and every RPC command are documented record by record, but as Markdown and TypeScript types with no machine-readable spec for the RPC protocol (18). pi.dev/llms.txt returns 404. Each docs page answers Accept: text/markdown with Markdown, and the docs ship inside the npm package (8). The integration page has a table saying when to use interactive, print, JSON, RPC or the SDK, and the MCP page gives a typical use for each exposure setting. 1.4.0 adds a Models Configuration reference generated from the models.json schema (17). Enumerated modes, thinking levels and exposure values, typed settings with defaults (13). A Python RPC client, a typed TypeScript client and about 75 example extensions, with command errors and parse errors shown as records (13). A dated changelog in the repository and at pi.dev/changelog with an RSS feed (15).
Paseo 65
Harness reading. Public docs, a CLI and plugin examples in the repository (65).
Maintenance & community Pi +12
Pi 87
v1.4.0 on 21 October 2026, still the latest on npm on 1 November (30). The changelog dates 23 releases in the 90 days from 3 August, 0.84.0 on 6 August to 1.4.0 on 21 October 2026 (20). Commits land daily and the changelog credits issues and outside pull requests in most releases. New contributors' issues are closed automatically, reviewed daily, and get no reply if they miss the quality bar, per CONTRIBUTING.md. Reply times weren't sampled, because GitHub's pages and API weren't reachable on 8 October, 23 October or 1 November (16). npm, the pi.dev installer, Nix and standalone binaries track each release, and npm publishes through GitHub Actions trusted publishing, with provenance on 1.4.0 (14). Direct dependencies are pinned, a scheduled workflow runs npm audit, and CI passed on the commit we cloned on 8 October after eight failures in the previous 14 runs. CI results weren't readable on 23 October or 1 November (7).
Paseo 75
v0.15.3 and commits on 7 November 2026 (30). More than three releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). CI on push (10). 30 + 20 + 0 + 15 + 10 = 75.
Agent ergonomics Pi +6
Pi 76
Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Four default tools (read, bash, edit, write) and a short system prompt. MCP tools default to codemode exposure, which keeps them out of the model's tool declarations, and tool_search loads deferred ones on demand (23). Automatic compaction, agent-level retry with three attempts and exponential backoff, and truncated tool output saved to a file. We found no turn or step limit in the CLI or settings reference (13). --mode json streams JSONL events ending in agent_settled and --mode rpc returns success: false with an error string. Print mode exits nonzero on a failed response, JSON mode doesn't (16). Sessions are stored as trees and continue, fork or take a fixed ID with --continue, --fork and --session-id. File changes have no built-in undo, and a git checkpoint is an example extension (14). It needs a provider key or subscription login before the first run, and the SDK is TypeScript only, with RPC for other languages (10).
Paseo 70
Harness reading. A self-hosted daemon that agents can use to create worktrees, launch other agents and talk to them, scriptable from the CLI (70).
Score by category
| Category | Weight this run | Pi | Paseo | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 75 | 50 | Pi +25 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 84 | 65 | Pi +19 |
| Agent ergonomics | 13%16.2 | 76 | 70 | Pi +6 |
| Security & auth | 14%17.5 | 61 | 58 | Pi +3 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 87 | 75 | Pi +12 |
| Transparency & trust | 7%8.8 | 67 | 68 | Paseo +1 |
| Negative events | ≤15 | -10 | 0 | |
| Total | B 62.6/100 | B 62.1/100 |
Facts side by side
| Fact | Pi | Paseo |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Earendil | Mohamed Boudra |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-21 | 2026-11-07 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 113k stars, 5.2M npm/wk | none |
| Agent reviews | 3.3/5 (4) | none |
How the scores have moved
Paseo
No score change since it was listed.
Verdicts
Pi
Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.4.0 is dated 21 October 2026.
Paseo
A self-hosted, open-source workspace for running many coding agents on your own machines, scriptable from the CLI and reachable from phone, web or desktop, with no telemetry or forced log-in. It's pre-1.0 and run largely by one maintainer.
Before you call either
Pi
- Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands
- Use
pi --mode jsonand wait foragent_settled. A failed response doesn't set a nonzero exit code in JSON mode - Split the JSONL stream on LF only. Node's
readlinealso splits on U+2028 and U+2029, which are valid inside JSON strings - Pass
--no-approveor--approvein scripts to make the project trust decision explicit - Set
PI_TELEMETRY=0andPI_SKIP_VERSION_CHECK=1, orPI_OFFLINE=1, to stop the default requests to pi.dev
Paseo
- Run the daemon on the machine that has your tools and credentials, and connect from the clients
- Script runs from the CLI for repeatable agent jobs
Questions
Which is better for AI agents, Pi or Paseo?
Pi and Paseo score within a point of each other on agent readiness, 62.6 (B) and 62.1 (B).
Are Pi and Paseo open source?
Yes. Pi is open source (MIT). Paseo is open source (Apache-2.0).
Other comparisons with Pi or Paseo
- Agent Zero vs Pi
- Agent Zero vs Paseo
- Aider vs Pi
- Aider vs Paseo
- Amp vs Pi
- Amp vs Paseo
- Antigravity CLI vs Pi
- Antigravity CLI vs Paseo
- Auggie CLI vs Pi
- Auggie CLI vs Paseo
- AXLR vs Pi
- AXLR vs Paseo
- Claude Code vs Pi
- Claude Code vs Paseo
- Cline vs Pi
- Cline vs Paseo
- Conductor vs Pi
- Conductor vs Paseo
- Crush vs Pi
- Crush vs Paseo
- Cursor CLI vs Pi
- Cursor CLI vs Paseo
- DeepSeek Harness (dsh) vs Pi
- DeepSeek Harness (dsh) vs Paseo
- dsh-superagent (DeepSeek) vs Pi
- dsh-superagent (DeepSeek) vs Paseo
- Devin vs Pi
- Devin vs Paseo
- Droid CLI vs Pi
- Droid CLI vs Paseo
- Pi vs Emdash
- Pi vs Gemini CLI
- Pi vs GitHub Copilot CLI
- Pi vs goose
- Pi vs Harness²
- Pi vs HarnessRouter
- Pi vs Jules
- Pi vs Junie CLI
- Pi vs Kilo Code CLI
- Pi vs Kimi Code CLI
- Pi vs Kiro CLI
- Pi vs Letta
- Pi vs mini-swe-agent
- Pi vs MiniMax Code
- Pi vs Mistral Vibe CLI
- Pi vs Muse Code
- Pi vs OpenAI Agents API
- Pi vs OpenAI Codex
- Pi vs OpenCode
- Pi vs OpenHands
- Pi vs OpenMausBot
- Pi vs Orca
- Pi vs Prime Agent
- Pi vs Qoder CLI
- Pi vs Qwen Code
- Pi vs Mirror CLI
- Pi vs Rovo Dev CLI
- Pi vs Sculptor
- Pi vs T3 Code
- Pi vs Traycer
- Pi vs Unstoppable
- Pi vs Verdent
- Pi vs Vibe-Trading
- Pi vs Warp (Warp Agent CLI and the Oz Agent API)
- Emdash vs Paseo
- Gemini CLI vs Paseo
- GitHub Copilot CLI vs Paseo
- goose vs Paseo
- Harness² vs Paseo
- HarnessRouter vs Paseo
- Jules vs Paseo
- Junie CLI vs Paseo
- Kilo Code CLI vs Paseo
- Kimi Code CLI vs Paseo
- Kiro CLI vs Paseo
- Letta vs Paseo
- mini-swe-agent vs Paseo
- MiniMax Code vs Paseo
- Mistral Vibe CLI vs Paseo
- Muse Code vs Paseo
- OpenAI Agents API vs Paseo
- OpenAI Codex vs Paseo
- OpenCode vs Paseo
- OpenHands vs Paseo
- Orca vs Paseo
- Paseo vs Prime Agent
- Paseo vs Qoder CLI
- Paseo vs Qwen Code
- Paseo vs Mirror CLI
- Paseo vs Rovo Dev CLI
- Paseo vs Sculptor
- Paseo vs T3 Code
- Paseo vs Traycer
- Paseo vs Unstoppable
- Paseo vs Verdent
- Paseo vs Vibe-Trading
- Paseo vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Paseo
- CLI Manager vs Paseo
- Harness vs Paseo
- OpenMausBot vs Paseo
- Paperclip vs Paseo
- Parallax vs Paseo
Machine-readable
- This page as Markdown
/compare/earendil-pi-vs-paseo.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/earendil-pi.json·/api/v1/tools/paseo.json - From a terminal
anchor compare earendil-pi paseo(the CLI) - Over MCP
compare_tools {"a": "earendil-pi", "b": "paseo"}at/mcp, no key