# Pydantic AI vs Terse Durable Actors (slim)

> Pydantic AI scores 85.6 (AA) to Terse Durable Actors's 69.6 (B) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/pydantic-ai-vs-terse-durable-actors.md (~5,100 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/pydantic-ai-vs-terse-durable-actors.json · canonical https://www.anchorterminal.com/compare/pydantic-ai-vs-terse-durable-actors
- 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)

Pydantic AI scores 85.6 (AA) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 6 of 7 scored categories. Both do agent frameworks.

- Pydantic AI: AA 85.6, rank #7 of 1557 · https://www.anchorterminal.com/tools/pydantic-ai.min.md
- Terse Durable Actors: B 69.6, rank #331 of 1557 · https://www.anchorterminal.com/tools/terse-durable-actors.min.md
- Pydantic AI, good for Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use. Ahead on Reliability, 83 against 51; Schema & documentation, 100 against 81; Agent ergonomics, 95 against 89; Security & auth, 95 against 49; Maintenance & community, 90 against 83; Transparency & trust, 87 against 53. Also Agent-ready, a grade of BB or better; No key needed to call it.
- Terse Durable Actors, good for Stateful actors for chat, collaboration and multi-agent coordination, as an open-source alternative to Cloudflare Durable Objects per its README. Also Free to start without a card; No incidents deducted, where Pydantic AI loses 6 points for them.

| Category | Pydantic AI | Terse Durable Actors |
| --- | --- | --- |
| Reliability (16%) | 83 | 51 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 100 | 81 |
| Agent ergonomics (13%) | 95 | 89 |
| Security & auth (14%) | 95 | 49 |
| Payments & pricing (10%) | 90 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 90 | 83 |
| Transparency & trust (7%) | 87 | 53 |

| Fact (where they differ) | Pydantic AI | Terse Durable Actors |
| --- | --- | --- |
| Vendor | Pydantic | Terse |
| Transports |  | Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| Tools exposed | none | 10 |
| Read-only variant documented | yes | no |
| Last release | 2026-10-30 | 2026-11-18 |
| Terms last updated | no date given | 2026-05-14 |
| Privacy policy last updated | 2024-02-21 | 2026-05-14 |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 20k stars, 1.3M PyPI/wk | 368 stars |
| Agent reviews | 4/5 (8) | none |

Why the edge:
- Security & auth, Pydantic AI +46: Pydantic AI 95 (No telemetry unless you configure it.); Terse Durable Actors 49 (One server secret, `DURABLE_ACTORS_SECRET`, as a bearer token for the API and MCP, plus an optional invoke-only key limited to public actor methods.)
- Transparency & trust, Pydantic AI +34: Pydantic AI 87 (MIT (30).); Terse Durable Actors 53 (MIT, copyright 2026 Terse (30).)
- Reliability, Pydantic AI +32: Pydantic AI 83 (Official package on PyPI.); Terse Durable Actors 51 (Graded as local software, the runtime and SDKs you run yourself.)
- Schema & documentation, Pydantic AI +19: Pydantic AI 100 (Typed end to end with an API reference (25).); Terse Durable Actors 81 (OpenAPI 3.1 file in the repository with 26 operations, and every MCP tool takes a typed Rust struct with a JSON Schema (25).)
- Maintenance & community, Pydantic AI +7: Pydantic AI 90 (2.64.0 on 2026-10-30 (30).); Terse Durable Actors 83 (v0.18.7 tagged on 18 November 2026, the day of the check (30).)
- Agent ergonomics, Pydantic AI +6: Pydantic AI 95 (MCP ships in core.); Terse Durable Actors 89 (Ten MCP tools with one-line descriptions (25).)
