# Agent Development Kit (ADK) vs Terse Durable Actors

> Agent Development Kit scores 72.4 (BB) to Terse Durable Actors's 69.6 (B) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/google-adk-vs-terse-durable-actors
- Markdown: https://www.anchorterminal.com/compare/google-adk-vs-terse-durable-actors.md (~5,350 tokens)
- Slim: https://www.anchorterminal.com/compare/google-adk-vs-terse-durable-actors.min.md (~1,130 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/google-adk-vs-terse-durable-actors.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-18

Agent Development Kit (ADK) scores 72.4 (BB) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 5 of 7 scored categories. Terse Durable Actors leads on agent ergonomics. Both do agent frameworks.

- Agent Development Kit (ADK): grade BB, 72.4/100, rank #217 of 1557. Markdown https://www.anchorterminal.com/tools/google-adk.md · JSON https://www.anchorterminal.com/api/v1/tools/google-adk.json
- Terse Durable Actors: grade B, 69.6/100, rank #331 of 1557. Markdown https://www.anchorterminal.com/tools/terse-durable-actors.md · JSON https://www.anchorterminal.com/api/v1/tools/terse-durable-actors.json
- Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md
- All 190 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md

## Which one, for what

### Agent Development Kit (ADK) (BB)

Good for: Teams on Google Cloud or working outside Python, and for anyone who wants approval, guardrail callbacks and evaluation in one framework.

Ahead on:
- Reliability, 80 against 51
- Schema & documentation, 87 against 81
- Security & auth, 92 against 49
- Maintenance & community, 90 against 83
- Transparency & trust, 69 against 53

Also in its favour:
- Agent-ready, a grade of BB or better
- No key needed to call it

Watch for: Six CVEs in 2026, three of them critical, one in tool confirmation itself

### Terse Durable Actors (B)

Good for: Stateful actors for chat, collaboration and multi-agent coordination, as an open-source alternative to Cloudflare Durable Objects per its README.

Ahead on:
- Agent ergonomics, 89 against 80

Also in its favour:
- Free to start without a card
- No incidents deducted, where Agent Development Kit (ADK) loses 12 points for them

Watch for: Version 0.18.7, with no stable release and no changelog file in the repository


## Why the edge

### Security & auth: Agent Development Kit (ADK) +43

- Agent Development Kit (ADK) (92): We found no usage telemetry in the docs or the Python source, and capturing message content in traces is opt-in (30). Tool confirmation for human approval, extended to workflow tool nodes in 2.11.0 and to any workflow node through `require_confirmation` in 2.12.0, the docs say to always pass tool_filter to McpToolset, 2.12.0 limits the mutating /dev and agent builder endpoints of adk web to local clients by default, and sandboxed code execution is recommended for model-written code (20). Before-tool callbacks, an after_tool_callback that screens tool output since 2.12.0, plugins, a Model Armor plugin, an optional ToolCallIntegrityPlugin since 2.11.0, and a safety page that covers indirect prompt injection through tool results (15). OpenTelemetry traces with Cloud Trace and about 20 third-party integrations (15). SECURITY.md routes reports to Google's g.co/vulnz with a one-day triage target, per the 1 October check, not re-read on 1 November (the repository still has no SECURITY.md file and GitHub's security page answered 403). Google as CNA has published six 2026 CVEs with fixed versions, the newest on 23 and 28 October, but there are no repository advisories and no bounty is mentioned in the policy (12). Framework reading, so SOC 2 isn't scored.
- 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. With the secret unset the API is unauthenticated, which SECURITY.md warns about (15 of 30). The invoke-only key and the MCP read-only hints give some least privilege, with no confirmation step before `invoke_actor` (10 of 20). The OpenAPI file marks actor output as untrusted and to be rendered as plain text, with no guidance for agents on injected instructions (6 of 15). Request history, actor logs, WebSocket sessions and state versions tied to the request that saved them (12 of 15). SECURITY.md gives a private reporting address, security@useterse.ai. No bug bounty, certification or published advisories found (6 of 20). On GKE the self-hosting guide runs actors in gVisor sandbox pods with per-actor storage credentials. Total 49.

### Reliability: Agent Development Kit (ADK) +29

- Agent Development Kit (ADK) (80): Official packages on PyPI (Requires-Python >=3.11 since 2.12.0, constraint files for 3.11 to 3.15) and npm (20). The continuous-integration workflow passes on main, per the 1 October check, not re-read on 1 November (25). 300 open issues and 261 open pull requests, per the 1 October check, not re-read on 1 November (12). The changelog calls out breaking changes, but they keep shipping in minor releases of a post-1.0 package (2.6.0 on 2026-07-29 and 2.7.0 on 2026-08-13), 2.12.0 on 2026-10-13 dropped Python 3.10 with no line in its changelog, and 2.8.0 reverted an A2A guard that had broken every tool confirmation. On 8 October the changelog relabelled the 2.11.0 dev UI config change a bug fix and the 2.9.0 resumption changes behaviour changes. 2.13.0 (22 October) marks one more breaking change, the telemetry schema default, in a minor release (8). 2.12.0, past 1.0 (15).
- Terse Durable Actors (51): Graded as local software, the runtime and SDKs you run yourself. The README and the Python SDK README install with `bunx durable-actors` or `uvx --from 'durable-actors[cli]'` and state Bun 1.4.2+ and Python 3.11+, and the release workflow publishes to npm. The registry pages were not read (15 of 20). A public CI workflow runs Rust, Python, TypeScript and example builds on every push and pull request. Whether it passes on main was not checked (15 of 25). 23 issues were open on 18 November 2026, mostly improvements and feature requests, with a few bug reports such as a constructor that keeps its SQLite writes after throwing (17 November) and alarms that run more than once (11 November) (18 of 25). Release notes are generated from pull-request labels on GitHub Releases, which were not read, and no changelog file or breaking-change notes were found in the repository (3 of 15). Version 0.18.7, not 1.0 or declared stable (0). Total 51.

### Transparency & trust: Agent Development Kit (ADK) +16

- Agent Development Kit (ADK) (69): Apache-2.0 (30). Google's general privacy policy applies and the observability docs say content capture is opt-in, but there's no ADK-specific statement of what, if anything, leaves the machine (15). Breaking changes are dated in the changelog and 1.x still gets releases, with no written support window (12). We found no telemetry statement either way on adk.dev (10).
- Terse Durable Actors (53): MIT, copyright 2026 Terse (30). Self-hosted state stays in your PostgreSQL database and GCS bucket per the self-hosting guide. Terse's terms and privacy policy, both dated 14 May 2026, describe an earlier product of flows and workspaces, give no retention periods and don't mention Terse Cloud (10 of 30). No deprecation policy found, and SECURITY.md says older releases get no backports (0 of 20). SDK invocation telemetry is off by default and writes to standard error when enabled, and request spans and platform events are exported only to a collector the operator configures. No call to Terse's own hosts was found in the runtime or SDK source (18 of 20). Total 58.

### Agent ergonomics: Terse Durable Actors +9

- Agent Development Kit (ADK) (80): An agent with one MCP server is about 15 lines with the built-in McpToolset, and tool_filter limits which tools load, with no dynamic filtering or deferred loading that we saw (20). RunConfig caps model calls per run, and the context compression page documents token-based and sliding-window compaction through EventsCompactionConfig, plus context caching (20). No exception reference or MCP error handling documented (5). Invocations are resumable, model calls take retry options, and 2.11.0 adds an abort_signal for graceful cancellation (20). An agent needs a name, a model and an instruction, in Python, TypeScript, Go, Java or Kotlin (15).
- Terse Durable Actors (89): Ten MCP tools with one-line descriptions (25). Cursor paging with stated limits (1 to 100, or 1 to 500 for requests) and filters by actor, outcome, log level, text and time window (20). Errors carry a code and a message, start limits return named codes with `Retry-After`, and invalid MCP input says which characters are allowed (14 of 20). Nine tools carry `readOnlyHint` and `invoke_actor` carries `destructiveHint`, but invocations have no idempotency key (15 of 20). Local development needs one command and no credential, with official TypeScript and Python SDKs and generated typed clients (15). Total 89.

### Maintenance & community: Agent Development Kit (ADK) +7

- Agent Development Kit (ADK) (90): 2.13.0 on 2026-10-23 (30). 15 Python releases in the 90 days from 3 August across the 1.x and 2.x lines, from 2.6.2 to 2.13.0, the newest 1.x being 1.39.1 on 2026-08-27 (20). 300 open issues and 261 open pull requests per the 1 October check, and we couldn't see reply times (15). Python is current, @google/adk is at 2.4.0 on npm, the Go module at v1.9.0 (tagged 15 October) and the Java artefact at 1.13.0 (21 October) (15). CI passes per the 1 October check, and 2.7.0 fixed zizmor findings in the workflows (10).
- Terse Durable Actors (83): v0.18.7 tagged on 18 November 2026, the day of the check (30). 118 tags since v0.1.0 on 2 September 2026, with eight between 15 and 18 November (20). 23 open issues, three of them with long threads (7, 9 and 15 replies) and most with none. Pull requests from five outside contributors were merged between 2 October and 3 November 2026, and CONTRIBUTING.md says GitHub issues are triaged into the team's tracker (10 of 25). Current official TypeScript and Python SDKs at 0.18.7. The MCP endpoint is self-hosted and not in the official registry, which was not searched (15). CI with pinned action versions and lockfiles for Bun, Cargo and uv (8 of 10). Total 83.

### Schema & documentation: Agent Development Kit (ADK) +6

- Agent Development Kit (ADK) (87): An API reference on adk.dev (25). llms.txt with about 250 entries and Markdown versions of each page (10). The docs explain the agent types and when to use workflow agents, but say little about when not to use ADK (15). Tools are typed functions, and McpToolset keeps the server's schemas (12). Examples throughout, but the MCP page has no error handling section and we found no exception reference (10). Dated changelog and release notes (15).
- 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). Markdown docs in the repository, an AGENTS.md and an agent skill for setting up projects (10). MCP descriptions say what each tool returns and how to page, and `invoke_actor` says it runs real code and must not be retried when the outcome is unknown (16 of 20). Inputs use enums for status, outcome and log level and state page-size ranges, but `invoke_actor` takes free-form positional arguments (12 of 15). Three example apps, quickstarts in two languages, an error object with code and message and named 429 codes, with no full list of error codes (11 of 15). Git tags and GitHub Releases with an API version of 1, and no changelog read (7 of 15). Total 81.

## Score by category

| Category | Weight | Agent Development Kit (ADK) | Terse Durable Actors | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 80 | 51 | Agent Development Kit (ADK) +29 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 87 | 81 | Agent Development Kit (ADK) +6 |
| Agent ergonomics | 13% | 80 | 89 | Terse Durable Actors +9 |
| Security & auth | 14% | 92 | 49 | Agent Development Kit (ADK) +43 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 90 | 83 | Agent Development Kit (ADK) +7 |
| Transparency & trust | 7% | 69 | 53 | Agent Development Kit (ADK) +16 |
| Negative events | ≤15 | -12 | 0 | |
| **Total** | | **72.4 · BB** | **69.6 · B** | |

## Facts side by side

| Fact | Agent Development Kit (ADK) | Terse Durable Actors |
| --- | --- | --- |
| Kind | Agent framework | Agent framework |
| Vendor | Google | Terse |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  | Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Tools exposed | none | 10 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-23 | 2026-11-18 |
| Terms last updated | no document linked | 2026-05-14 |
| Privacy policy last updated | 2026-10-01 | 2026-05-14 |
| Customer content may train models | yes | not found in the text |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | yes |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | 22k stars | 368 stars |
| Agent reviews | 3/5 (8) | none |

## How the scores have moved

### Agent Development Kit (ADK)

- +3.7 on 13 November 2026 (B to BB): checklist
- -5.0 on 1 November 2026 (BB to B): negative event
- +0.1 on 27 October 2026: checklist

### Terse Durable Actors

- +8.9 on 18 November 2026 (C to B): terms, pricing, new evidence

## Verdicts

**Agent Development Kit (ADK).** Python, TypeScript, Go, Java and Kotlin, with tool confirmation and context compaction built in. Google has published six CVEs against ADK in 2026, three of them critical, one in tool confirmation itself, and minor 2.x releases keep carrying breaking changes.

**Terse Durable Actors.** Durable Actors gives coding agents ten compact MCP tools with read-only and destructive hints, a public OpenAPI 3.1 file and typed TypeScript and Python clients, under MIT with near-daily releases. It is pre-1.0 at 0.18.7, one server secret controls everything unless an invoke-only key is added, and Terse's policies predate Terse Cloud.

## Before you call either

### Agent Development Kit (ADK)

1. Run Python 2.7.0 or later and Java 1.13.0 or later, which fix the adk web code-injection CVE, the tool-confirmation forgery and the Java dev server's cross-origin flaw
2. Always pass tool_filter to McpToolset
3. Pin a 2.x minor and read the changelog before each bump. 2.12.0 needs Python 3.11 or later, which its changelog doesn't say
4. Set EventsCompactionConfig on the App for long sessions so context doesn't grow without limit
5. Keep ADK Web off public interfaces
6. Set `ADK_TELEMETRY_SCHEMA_VERSION_OPT_IN=otel_semconv_1_36` on 2.13.0 or later if dashboards or alerts read the `call_llm` span

### Terse Durable Actors

1. Call `list_projects` first and pass its `projectId` to every other tool
2. Never retry `invoke_actor` when the outcome is unknown, because calls are not deduplicated and run real code
3. Set `DURABLE_ACTORS_SECRET` before exposing a server beyond localhost, and send it as a bearer token
4. Give backends that only call actors the invoke-only key, not the server secret
5. On 429 `actor_start_rate_limited`, wait for the `Retry-After` seconds before starting another actor

## Questions

### Which is better for AI agents, Agent Development Kit (ADK) or Terse Durable Actors?

Agent Development Kit (ADK) scores 72.4 (BB) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 5 of 7 scored categories. Terse Durable Actors leads on agent ergonomics.

### Are Agent Development Kit (ADK) and Terse Durable Actors open source?

Yes. Agent Development Kit (ADK) is open source (Apache-2.0). Terse Durable Actors is open source (MIT).


## For agents

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

## Other comparisons with Agent Development Kit (ADK) or Terse Durable Actors

- [AgentOS vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/agentos-vs-google-adk.md)
- [AgentOS vs Terse Durable Actors](https://www.anchorterminal.com/compare/agentos-vs-terse-durable-actors.md)
- [Agno vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/agno-vs-google-adk.md)
- [Agno vs Terse Durable Actors](https://www.anchorterminal.com/compare/agno-vs-terse-durable-actors.md)
- [BoxLang AI vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/boxlang-ai-vs-google-adk.md)
- [BoxLang AI vs Terse Durable Actors](https://www.anchorterminal.com/compare/boxlang-ai-vs-terse-durable-actors.md)
- [Claude Agent SDK vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-google-adk.md)
- [Claude Agent SDK vs Terse Durable Actors](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-terse-durable-actors.md)
- [CrewAI vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/crewai-vs-google-adk.md)
- [CrewAI vs Terse Durable Actors](https://www.anchorterminal.com/compare/crewai-vs-terse-durable-actors.md)
- [Cursor Agent SDK vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-google-adk.md)
- [Cursor Agent SDK vs Terse Durable Actors](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-terse-durable-actors.md)
- [Docker Agent vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/docker-agent-vs-google-adk.md)
- [Docker Agent vs Terse Durable Actors](https://www.anchorterminal.com/compare/docker-agent-vs-terse-durable-actors.md)
- [Agent Development Kit (ADK) vs guilds.run](https://www.anchorterminal.com/compare/google-adk-vs-guilds-run.md)
- [Agent Development Kit (ADK) vs LangGraph](https://www.anchorterminal.com/compare/google-adk-vs-langgraph.md)
- [Agent Development Kit (ADK) vs LlamaIndex Framework](https://www.anchorterminal.com/compare/google-adk-vs-llamaindex.md)
- [Agent Development Kit (ADK) vs Mastra](https://www.anchorterminal.com/compare/google-adk-vs-mastra.md)
- [Agent Development Kit (ADK) vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework.md)
- [Agent Development Kit (ADK) vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/google-adk-vs-openai-agents-sdk.md)
- [Agent Development Kit (ADK) vs Pydantic AI](https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai.md)
- [Agent Development Kit (ADK) vs smolagents](https://www.anchorterminal.com/compare/google-adk-vs-smolagents.md)
- [Agent Development Kit (ADK) vs Strands Agents](https://www.anchorterminal.com/compare/google-adk-vs-strands-agents.md)
- [Agent Development Kit (ADK) vs TradingAgents](https://www.anchorterminal.com/compare/google-adk-vs-tradingagents.md)
- [Agent Development Kit (ADK) vs AI SDK](https://www.anchorterminal.com/compare/google-adk-vs-vercel-ai-sdk.md)
- [guilds.run vs Terse Durable Actors](https://www.anchorterminal.com/compare/guilds-run-vs-terse-durable-actors.md)
- [LangGraph vs Terse Durable Actors](https://www.anchorterminal.com/compare/langgraph-vs-terse-durable-actors.md)
- [LlamaIndex Framework vs Terse Durable Actors](https://www.anchorterminal.com/compare/llamaindex-vs-terse-durable-actors.md)
- [Mastra vs Terse Durable Actors](https://www.anchorterminal.com/compare/mastra-vs-terse-durable-actors.md)
- [Microsoft Agent Framework vs Terse Durable Actors](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-terse-durable-actors.md)
- [OpenAI Agents SDK vs Terse Durable Actors](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-terse-durable-actors.md)
- [Pydantic AI vs Terse Durable Actors](https://www.anchorterminal.com/compare/pydantic-ai-vs-terse-durable-actors.md)
- [smolagents vs Terse Durable Actors](https://www.anchorterminal.com/compare/smolagents-vs-terse-durable-actors.md)
- [Strands Agents vs Terse Durable Actors](https://www.anchorterminal.com/compare/strands-agents-vs-terse-durable-actors.md)
- [Terse Durable Actors vs TradingAgents](https://www.anchorterminal.com/compare/terse-durable-actors-vs-tradingagents.md)
- [Terse Durable Actors vs AI SDK](https://www.anchorterminal.com/compare/terse-durable-actors-vs-vercel-ai-sdk.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
