Agent SDK and Runtime · Public

agents

Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.

Agent SDKTool callsHandoffsTracingEvaluation boundaries

Best fitDevelopers building observable, testable, multi-tool agent applications.

Check whether this project matches your task before installing it.

What it can doAgent runtime preflights, tool permissions, state/handoff boundaries, trace acceptance, and evaluation checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot5.1k stars

594 forks · 69 contributors

Doramagic.ai Last verification date: 2026-07-30 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-07-30

What is agents?

agents is an Agent SDK or runtime for tool calls, state, handoffs, tracing, and evaluation boundaries.
Best fit: Developers building observable, testable, multi-tool agent applications.
Not for: Not for one prompt, simple API calls, or environments that cannot isolate tool permissions.
Capability added to an AI workflow: Agent runtime preflights, tool permissions, state/handoff boundaries, trace acceptance, and evaluation checks
First safe verification step: Verify one minimal agent loop with fake tools and temporary credentials first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/cloudflare/agents, https://github.com/cloudflare/agents#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers building observable, testable, multi-tool agent applications.

Match the project to your task before installing it.

CapabilityAgent runtime preflights, tool permissions, state/handoff boundaries, trace acceptance, and evaluation checks

Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.

Repositorycloudflare/agents

5.1k stars · 594 forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Core Agent Runtime, State & Routing

Related topics: AI Chat, Think Framework & Sub-agent Orchestration, Voice Pipeline, WebSockets & Frontend Clients

Source: https://github.com/cloudflare/agents / Human Manual

AI Chat, Think Framework & Sub-agent Orchestration

Related topics: Core Agent Runtime, State & Routing, MCP, Code Mode, Tools & Extensibility, Voice Pipeline, WebSockets & Frontend Clients

Source: https://github.com/cloudflare/agents / Human Manual

MCP, Code Mode, Tools & Extensibility

Related topics: AI Chat, Think Framework & Sub-agent Orchestration

Source: https://github.com/cloudflare/agents / Human Manual

Voice Pipeline, WebSockets & Frontend Clients

Related topics: Core Agent Runtime, State & Routing, AI Chat, Think Framework & Sub-agent Orchestration

Source: https://github.com/cloudflare/agents / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

Sources: https://github.com/cloudflare/agents, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars5.1k stars

Forks594 forks

Contributors69 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using agents with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
A header value for "x-partykit-props" contains non-ASCII characters
github / github_issue
02
Feature request: first-class detached ("background") sub-agent runs with
github / github_issue
03
McpAgent: ctx.waitUntil(agent.destroy()) on session teardown logs "waitU
github / github_issue
04
Expose client-facing chat sanitization hooks separate from persistence s
github / github_issue
05
[retracted]
github / github_issue
06
Think.onStart bricks the DO with SQLITE_NOMEM on large sessions (eager f
github / github_issue
07
[voice] audible click at every audio chunk seam (w/ working fix)
github / github_issue
08
useAgent: RPC calls issued during initial connect can hang forever (resp
github / github_issue
09
[email protected]
github / github_release
10
[email protected]
github / github_release
11
@cloudflare/[email protected]
github / github_release
12
@cloudflare/[email protected]
github / github_release

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

npm install agents

Official start command · https://github.com/cloudflare/agents#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

agents Manual

The Core Agent Runtime is the foundation of the Cloudflare Agents SDK, published as the agents package (v0.16.0) and implemented on top of Cloudflare Durable Objects (packages/agents/packa...

Open the full manual

https://github.com/cloudflare/agents Project Manual
Table of Contents
Core Agent Runtime, State & Routing
Related Pages
Overview
Lifecycle and Hooks
State, SQL, and Replicas
Routing and Naming Strategies

Core Agent Runtime, State & Routing

Related topics: AI Chat, Think Framework & Sub-agent Orchestration, Voice Pipeline, WebSockets & Frontend Clients

Source: https://github.com/cloudflare/agents / Human Manual

AI Chat, Think Framework & Sub-agent Orchestration

Related topics: Core Agent Runtime, State & Routing, MCP, Code Mode, Tools & Extensibility, Voice Pipeline, WebSockets & Frontend Clients

Source: https://github.com/cloudflare/agents / Human Manual

MCP, Code Mode, Tools & Extensibility

Related topics: AI Chat, Think Framework & Sub-agent Orchestration

Source: https://github.com/cloudflare/agents / Human Manual

Voice Pipeline, WebSockets & Frontend Clients

Related topics: Core Agent Runtime, State & Routing, AI Chat, Think Framework & Sub-agent Orchestration

Source: https://github.com/cloudflare/agents / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

high

Maintenance risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: [email protected]

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: [email protected]

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: [email protected]

medium

Configuration risk requires verification

Upgrade or migration may change expected behavior: @cloudflare/[email protected]

medium

Configuration risk requires verification

Upgrade or migration may change expected behavior: @cloudflare/[email protected]

medium

Configuration risk requires verification

Developers may misconfigure credentials, environment, or host setup: McpAgent: ctx.waitUntil(agent.destroy()) on session teardown logs "waitUntil() tasks did not complete" when the SSE client has already disconnected (0.13.3)

medium

Configuration risk requires verification

Developers may misconfigure credentials, environment, or host setup: [retracted]