# Agent Zero vs Pi

> Pi scores 68.4 (B) to Agent Zero's 54.2 (C) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi
- Markdown: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.min.md (~480 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-12

Pi scores 68.4 (B) on agent readiness against Agent Zero's 54.2 (C), and leads in 6 of 7 scored categories. Both do agent harnesses.

- Agent Zero: grade C, 54.2/100, rank #709 of 986. Markdown https://www.anchorterminal.com/tools/agent-zero.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-zero.json
- Pi: grade B, 68.4/100, rank #219 of 986. Markdown https://www.anchorterminal.com/tools/earendil-pi.md · JSON https://www.anchorterminal.com/api/v1/tools/earendil-pi.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 205 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Agent Zero (C)

Good for: A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.

Watch for: No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow

### Pi (B)

Good 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 57
- Schema & documentation, 84 against 64
- Agent ergonomics, 76 against 62
- Security & auth, 61 against 54
- Maintenance & community, 87 against 75
- Transparency & trust, 64 against 55

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


## Score by category

| Category | Weight | Agent Zero | Pi | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 57 | 75 | Pi +18 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 64 | 84 | Pi +20 |
| Agent ergonomics | 13% (16.2 this run) | 62 | 76 | Pi +14 |
| Security & auth | 14% (17.5 this run) | 54 | 61 | Pi +7 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 75 | 87 | Pi +12 |
| Transparency & trust | 7% (8.8 this run) | 55 | 64 | Pi +9 |
| Negative events | ≤15 | -6 | -4 | |
| **Total** | | **54.2 · C** | **68.4 · B** | |

## Facts side by side

| Fact | Agent Zero | Pi |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Agent Zero, s.r.o. | Earendil |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-23 | 2026-10-07 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 19k stars | 113k stars, 5.2M npm/wk |

## Verdicts

**Agent Zero.** Self-hosted under the MIT licence, with nine releases in the 90 days to 12 October 2026 and breaking changes listed in the release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and five CVEs from the past year have no published GitHub advisory.

**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 1.0.0 is dated 1 October 2026.

## Before you call either

### Agent Zero

1. Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none
2. Fill `allowed_users`, `allowed_numbers` or `sender_whitelist` before enabling a channel. An empty list accepts every sender
3. Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled
4. Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal
5. Call `POST /api_message` with the `X-API-KEY` header. The token changes when the UI login or password changes

### Pi

1. Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands
2. Use `pi --mode json` and wait for `agent_settled`. A failed response doesn't set a nonzero exit code in JSON mode
3. Split the JSONL stream on LF only. Node's `readline` also splits on U+2028 and U+2029, which are valid inside JSON strings
4. Pass `--no-approve` or `--approve` in scripts to make the project trust decision explicit
5. Set `PI_TELEMETRY=0` and `PI_SKIP_VERSION_CHECK=1`, or `PI_OFFLINE=1`, to stop the default requests to pi.dev

## Questions

### Which is better for AI agents, Agent Zero or Pi?

Pi scores 68.4 (B) on agent readiness against Agent Zero's 54.2 (C), and leads in 6 of 7 scored categories.

### Are Agent Zero and Pi open source?

Yes. Agent Zero is open source (MIT). Pi is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "agent-zero", "b": "earendil-pi"}`. From a terminal: `anchor compare agent-zero earendil-pi`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-zero.json and https://www.anchorterminal.com/api/v1/tools/earendil-pi.json

## Other comparisons with Agent Zero or Pi

- [Agent Zero vs Aider](https://www.anchorterminal.com/compare/agent-zero-vs-aider.md)
- [Agent Zero vs Amp](https://www.anchorterminal.com/compare/agent-zero-vs-amp.md)
- [Agent Zero vs Antigravity CLI](https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.md)
- [Agent Zero vs Claude Code](https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.md)
- [Agent Zero vs Cline](https://www.anchorterminal.com/compare/agent-zero-vs-cline.md)
- [Agent Zero vs Cursor CLI](https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli.md)
- [Agent Zero vs Devin](https://www.anchorterminal.com/compare/agent-zero-vs-devin.md)
- [Agent Zero vs Droid CLI](https://www.anchorterminal.com/compare/agent-zero-vs-droid-cli.md)
- [Agent Zero vs Gemini CLI](https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.md)
- [Agent Zero vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/agent-zero-vs-github-copilot-cli.md)
- [Agent Zero vs goose](https://www.anchorterminal.com/compare/agent-zero-vs-goose.md)
- [Agent Zero vs Kilo Code CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli.md)
- [Agent Zero vs Kiro CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli.md)
- [Agent Zero vs OpenAI Codex](https://www.anchorterminal.com/compare/agent-zero-vs-openai-codex.md)
- [Agent Zero vs OpenCode](https://www.anchorterminal.com/compare/agent-zero-vs-opencode.md)
- [Agent Zero vs OpenHands](https://www.anchorterminal.com/compare/agent-zero-vs-openhands.md)
- [Agent Zero vs Prime Agent](https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent.md)
- [Agent Zero vs Qwen Code](https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code.md)
- [Aider vs Pi](https://www.anchorterminal.com/compare/aider-vs-earendil-pi.md)
- [Amp vs Pi](https://www.anchorterminal.com/compare/amp-vs-earendil-pi.md)
- [Antigravity CLI vs Pi](https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi.md)
- [Claude Code vs Pi](https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.md)
- [Cline vs Pi](https://www.anchorterminal.com/compare/cline-vs-earendil-pi.md)
- [Cursor CLI vs Pi](https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.md)
- [Devin vs Pi](https://www.anchorterminal.com/compare/devin-vs-earendil-pi.md)
- [Droid CLI vs Pi](https://www.anchorterminal.com/compare/droid-cli-vs-earendil-pi.md)
- [Pi vs Gemini CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.md)
- [Pi vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli.md)
- [Pi vs goose](https://www.anchorterminal.com/compare/earendil-pi-vs-goose.md)
- [Pi vs Kilo Code CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.md)
- [Pi vs Kiro CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.md)
- [Pi vs OpenAI Codex](https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.md)
- [Pi vs OpenCode](https://www.anchorterminal.com/compare/earendil-pi-vs-opencode.md)
- [Pi vs OpenHands](https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.md)
- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)
- [Pi vs Qwen Code](https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.md)