# Letta vs OpenAI Agents API (slim)

> OpenAI Agents scores 73.3 (BB) to Letta's 59.7 (C) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/letta-vs-openai-agents-api.md (~5,900 tokens) · this version ~2,180 tokens · JSON https://www.anchorterminal.com/compare/letta-vs-openai-agents-api.json · canonical https://www.anchorterminal.com/compare/letta-vs-openai-agents-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

OpenAI Agents API scores 73.3 (BB) on agent readiness against Letta's 59.7 (C), and leads in 6 of 7 scored categories. Letta leads on payments & pricing. Both do agent harnesses.

- Letta: C 59.7, rank #684 of 1486 · https://www.anchorterminal.com/tools/letta.min.md
- OpenAI Agents API: BB 73.3, rank #110 of 1486 · https://www.anchorterminal.com/tools/openai-agents-api.min.md
- Letta, good for Long-lived coding agents and assistants that keep memory and identity across sessions and machines. Ahead on Payments & pricing, 60 against 30. Also Runs on your own machine; Open source.
- OpenAI Agents API, good for Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention. Ahead on Schema & documentation, 88 against 70; Agent ergonomics, 80 against 67; Security & auth, 87 against 35; Transparency & trust, 85 against 55. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install.

| Category | Letta | OpenAI Agents API |
| --- | --- | --- |
| Reliability (16%) | 58 | 60 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 88 |
| Agent ergonomics (13%) | 67 | 80 |
| Security & auth (14%) | 35 | 87 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 85 | 87 |
| Transparency & trust (7%) | 55 | 85 |

| Fact (where they differ) | Letta | OpenAI Agents API |
| --- | --- | --- |
| Kind | Agent harness | HTTP API |
| Vendor | Letta | OpenAI |
| Hosted endpoint | no (local only) | `https://api.openai.com/v1/agents/sessions` |
| Transports | stdio | https |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Pay per use |
| Licence | Apache-2.0 | Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0 |
| Last release | 2026-11-06 | 2026-10-16 |
| Terms last updated | no date given | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models | not found in the text | couldn't be read |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | not found in the text | couldn't be read |
| Terms or service can change without notice | not found in the text | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 3.8k stars, 86k npm/wk, 2.2k PyPI/wk | none |

Why the edge:
- Security & auth, OpenAI Agents API +52: Letta 35 (Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is `unrestricted`; `standard`, `acceptEdits` and `strict` are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.); OpenAI Agents API 87 (Project keys with restricted per-endpoint permissions, service accounts and workload identity, per the openai-api listing; we didn't confirm a key can be limited to /v1/agents (27 of 30). Automatic review for approvals, a sandbox network restricted to a host allowlist, vaults for secrets and a sandbox security guide (17 of 20). The agent reads web pages, MCP results and browser content; the sandbox security guide and approval flow are the mitigations, with no prompt-injection guide of its own found (8 of 15). Tracing, observability and usage per session and admin audit logs (15). SOC 2 Type 2, ISO 27001 family, Bugcrowd bounty and a disclosure policy, per the openai-api listing (20). Not ZDR-eligible and US residency only, recorded under transparency. 27 + 17 + 8 + 15 + 20 = 87.)
- Payments & pricing, Letta +30: Letta 60 (No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.); OpenAI Agents API 30 (No machine payment protocol (0). Model, tool and container prices published without a login, and no fee for the API itself (20). The Free tier reading of the openai-api listing, half (10). Sign-up in a browser (0). 0 + 20 + 10 + 0 = 30.)
- Transparency & trust, OpenAI Agents API +30: Letta 55 (Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55.); OpenAI Agents API 85 (Closed service with clear terms, Apache-2.0 SDKs (15). Session state retained until deleted, deletable sessions and artifacts, not ZDR-eligible, US residency only, and the data-controls guide agrees; no retention period for artifacts after a sandbox expires (25 of 30). Dated deprecation notices with minimum periods for GA models; a beta API can change faster (15 of 20). Subprocessors and processing countries listed, per the openai-api listing (20). 15 + 25 + 15 + 20 = 75.)
- Schema & documentation, OpenAI Agents API +18: Letta 70 (Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an `applies_to` block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.); OpenAI Agents API 88 (The reference is linked from the overview and the SDKs carry beta.agents types; we didn't confirm /agents/sessions in OpenAI's public OpenAPI file, so 15 of 25. llms.txt with every Agents API page and Markdown twins (10). The overview, architecture page and the agents guide that compares the Agents API, Agents SDK and Responses API say when to use it (20). Typed configuration with enumerated container sizes, network modes and environment types (13 of 15). Examples in six languages and an errors page with codes per HTTP status, turn and session (15). Dated changelog entries and a versioned beta header (15). 15 + 10 + 20 + 13 + 15 + 15 = 88.)
- Agent ergonomics, OpenAI Agents API +13: Letta 67 (Harness reading. Toolsets switch with `/model`, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). `letta -p --output-format json` for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.); OpenAI Agents API 80 (Read as an API an agent drives. Context is compacted automatically, and session budgets and streamed events keep output sized (20 of 25). Sessions can be listed, continued and steered, events streamed or sent by webhook, artifacts fetched (15 of 20). Actionable error codes with recovery steps (20). No idempotency key; a documented check-then-retry procedure (10 of 20). One session call with defaults (medium sandbox, network enabled), SDKs in five languages (15). 20 + 15 + 20 + 10 + 15 = 80.)