# Agent Relay vs Antigravity CLI (slim)

> Agent Relay scores 69.9 (B) to Antigravity CLI's 56.6 (C) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/agent-relay-vs-antigravity-cli.md (~7,500 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/agent-relay-vs-antigravity-cli.json · canonical https://www.anchorterminal.com/compare/agent-relay-vs-antigravity-cli
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Agent Relay scores 69.9 (B) on agent readiness against Antigravity CLI's 56.6 (C), and leads in 6 of 7 scored categories. Antigravity CLI leads on agent ergonomics. Both do multi-agent orchestration.

- Agent Relay: B 69.9, rank #319 of 1557 · https://www.anchorterminal.com/tools/agent-relay.min.md
- Antigravity CLI: C 56.6, rank #926 of 1557 · https://www.anchorterminal.com/tools/antigravity-cli.min.md
- Agent Relay, good for Teams running several Claude Code or Codex sessions who want them to message, hand off and spawn each other across machines. Ahead on Reliability, 73 against 43; Schema & documentation, 87 against 78; Security & auth, 58 against 53; Payments & pricing, 60 against 45; Maintenance & community, 73 against 68; Transparency & trust, 77 against 55. Also Runs on your own machine; Open source; No incidents deducted, where Antigravity CLI loses 3 points for them.
- Antigravity CLI, good for Developers on Google AI plans or Gemini Enterprise who want a terminal agent with a sandbox on by default and access to several model families, depending on plan. Ahead on Agent ergonomics, 78 against 68.

| Category | Agent Relay | Antigravity CLI |
| --- | --- | --- |
| Reliability (16%) | 73 | 43 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 87 | 78 |
| Agent ergonomics (13%) | 68 | 78 |
| Security & auth (14%) | 58 | 53 |
| Payments & pricing (10%) | 60 | 45 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 73 | 68 |
| Transparency & trust (7%) | 77 | 55 |

| Fact (where they differ) | Agent Relay | Antigravity CLI |
| --- | --- | --- |
| Kind | MCP server | Agent harness |
| Vendor | Agent Workforce Incorporated | Google |
| Transports | stdio |  |
| Licence | Apache-2.0 | Proprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy Policy |
| Tools exposed | 34 | none |
| Last release | 2026-11-17 | 2026-10-30 |
| Terms last updated | 2026-05-27 | no date given |
| Privacy policy last updated | 2026-10-14 | 2026-10-01 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Popularity | 1.1k stars | none |

Why the edge:
- Reliability, Agent Relay +30: Agent Relay 73 (Read as local software, since the CLI, MCP server and default server run on the person's machine.); Antigravity CLI 43 (Local-package reading.)
- Transparency & trust, Agent Relay +22: Agent Relay 77 (Apache-2.0, copyright Agent Workforce Incorporated (30).); Antigravity CLI 55 (Closed source, with clear terms.)
- Payments & pricing, Agent Relay +15: Agent Relay 60 (No payment protocol (0).); Antigravity CLI 45 (Harness reading of the published rubric.)
- Agent ergonomics, Antigravity CLI +10: Agent Relay 68 (About 34 tools in the default server (5), with 5 back for the `--sessions-only` subset (10 of 25).); Antigravity CLI 78 (Framework reading, adapted to a harness driven by a pipeline.)
- Schema & documentation, Agent Relay +9: Agent Relay 87 (Read as an MCP server.); Antigravity CLI 78 (Framework reading.)
- Security & auth, Agent Relay +5: Agent Relay 58 (Harness reading of the framework checklist, as for Harness by Autonomous.); Antigravity CLI 53 (Framework reading (credentials and telemetry defaults, approvals and sandboxing, guardrails, audit, security programme), five lines.)
