# Agent Relay vs Letta (slim)

> Agent Relay scores 69.9 (B) to Letta's 63.5 (B) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/agent-relay-vs-letta.md (~6,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/agent-relay-vs-letta.json · canonical https://www.anchorterminal.com/compare/agent-relay-vs-letta
- 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 Letta's 63.5 (B), and leads in 5 of 7 scored categories. Letta leads on payments & pricing and maintenance & community. Both do multi-agent orchestration.

- Agent Relay: B 69.9, rank #319 of 1557 · https://www.anchorterminal.com/tools/agent-relay.min.md
- Letta: B 63.5, rank #630 of 1557 · https://www.anchorterminal.com/tools/letta.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 58; Schema & documentation, 87 against 70; Security & auth, 58 against 35; Transparency & trust, 77 against 55.
- Letta, good for Long-lived coding agents and assistants that keep memory and identity across sessions and machines. Ahead on Payments & pricing, 90 against 60; Maintenance & community, 85 against 73.

| Category | Agent Relay | Letta |
| --- | --- | --- |
| Reliability (16%) | 73 | 58 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 87 | 70 |
| Agent ergonomics (13%) | 68 | 67 |
| Security & auth (14%) | 58 | 35 |
| Payments & pricing (10%) | 60 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 73 | 85 |
| Transparency & trust (7%) | 77 | 55 |

| Fact (where they differ) | Agent Relay | Letta |
| --- | --- | --- |
| Kind | MCP server | Agent harness |
| Vendor | Agent Workforce Incorporated | Letta |
| Tools exposed | 34 | none |
| Last release | 2026-11-17 | 2026-11-06 |
| Terms last updated | 2026-05-27 | no date given |
| Privacy policy last updated | 2026-10-14 | no date given |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 1.1k stars | 3.8k stars, 86k npm/wk, 2.2k PyPI/wk |

Why the edge:
- Payments & pricing, Letta +30: Agent Relay 60 (No payment protocol (0).); Letta 90 (No x402, MPP or L402 (0 of 40).)
- Security & auth, Agent Relay +23: Agent Relay 58 (Harness reading of the framework checklist, as for Harness by Autonomous.); Letta 35 (Harness reading of the framework checklist, as for the other harnesses.)
- Transparency & trust, Agent Relay +22: Agent Relay 77 (Apache-2.0, copyright Agent Workforce Incorporated (30).); Letta 55 (Apache-2.0 (30).)
- Schema & documentation, Agent Relay +17: Agent Relay 87 (Read as an MCP server.); Letta 70 (Harness reading.)
- Reliability, Agent Relay +15: Agent Relay 73 (Read as local software, since the CLI, MCP server and default server run on the person's machine.); Letta 58 (Local-software lines, read for the harness.)
- Maintenance & community, Letta +12: Agent Relay 73 (v18.10.0 on 17 November 2026, the day before the check (30).); Letta 85 (v0.34.42 on 6 November 2026 (30).)
