Apache-2.0 code-first toolkit for building, running, evaluating, and deploying AI agents, workflows, tools, sessions, and multi-agent systems.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
78
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
Registry metadata indicates a reviewed listing.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 16/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
Listing has review metadata.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Required evidence gates are covered (5/6 signals complete).
Source repository/provenance is listed.
Required in this preset
Review metadata is present.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
5/6 steps complete with no blocking gaps for this preset.
triage
Source/provenance metadata is available.
triage
Review metadata is available.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
5 prerequisites to line up before setup. Have accounts and credentials ready first.
Safety & privacy surface
6 safety and 5 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.
Disclosure: editorial
## Editorial notes
Google Agent Development Kit is useful when Claude-adjacent teams need a code-first framework for building agents, composing deterministic workflows, defining tools, testing agent behavior, evaluating tool-use trajectories, and deploying agent services. It supports local CLI and web development loops, workflow composition, task delegation, sessions, state, memory, callbacks, observability, evaluation, and deployment paths for Google Cloud and container-friendly infrastructure.
This is distinct from the existing tools entries. It is not a model library like Transformers, a data layer like Datasets, a distributed runtime like Accelerate, or an evaluation-metrics library like Evaluate. Google ADK is an agent application framework: it organizes agent code, tools, workflows, runtime behavior, evaluation cases, deployment surfaces, and integrations around production-oriented agent systems.
## Source notes
- The official repository describes ADK as an open-source, code-first Python framework for building, evaluating, and deploying AI agents with flexibility and control.
- The ADK 2.0 README documents workflow runtime support for routing, fan-out/fan-in, loops, retry, state management, dynamic nodes, human-in-the-loop, and nested workflows.
- The README documents the Task API for structured agent-to-agent delegation, multi-turn task mode, controlled output, mixed delegation patterns, and task agents as workflow nodes.
- The README lists Python 3.11 or newer as the current requirement and installs the Python package with `pip install google-adk`.
- The README shows `Agent`, `Workflow`, `adk run`, and `adk web` examples for local agent development.
- The canonical documentation site is `https://adk.dev/`; the older `https://google.github.io/adk-docs/` documentation URL currently redirects there.
- The documentation describes ADK as a toolkit for building, managing, evaluating, and deploying AI-powered agents, with quickstarts for Python, TypeScript, Go, Java, and Kotlin.
- The Python quickstart documents `adk create`, root agent structure, tool definitions, Gemini API key setup, command-line runs, and the ADK web interface.
- The Python quickstart warns that ADK Web is for development and debugging rather than production deployments.
- The evaluation docs describe testing final responses, trajectories, tool use, intermediate agent responses, eval sets, custom metrics, and CLI, web, or pytest-based evaluation.
- The deployment docs describe Agent Runtime on Agent Platform, Cloud Run, Google Kubernetes Engine, and other container-friendly infrastructure.
- The repository is `google/adk-python`, is Apache-2.0 licensed, and is active.
## Duplicate check
Checked current `content/tools/`, `content/mcp/`, agents, hooks, rules, skills, commands, guides, open pull requests, live issue state, and repository-wide content for `Google Agent Development Kit`, `Google ADK`, `google/adk-python`, `google.github.io/adk-docs`, `adk.dev`, `agent development kit`, `adk run`, and `adk web`. No dedicated Google ADK tools entry, source URL duplicate, target file, or open duplicate PR was found.
## Disclosure
Editorial listing. No paid placement or affiliate link is used. Google Agent Development Kit is Apache-2.0 open-source software; Google Cloud services, Gemini APIs, model providers, deployment targets, MCP tools, A2A integrations, and third-party systems may have separate licenses, billing, terms, privacy obligations, and access controls.Google Agent Development Kit is useful when Claude-adjacent teams need a code-first framework for building agents, composing deterministic workflows, defining tools, testing agent behavior, evaluating tool-use trajectories, and deploying agent services. It supports local CLI and web development loops, workflow composition, task delegation, sessions, state, memory, callbacks, observability, evaluation, and deployment paths for Google Cloud and container-friendly infrastructure.
This is distinct from the existing tools entries. It is not a model library like Transformers, a data layer like Datasets, a distributed runtime like Accelerate, or an evaluation-metrics library like Evaluate. Google ADK is an agent application framework: it organizes agent code, tools, workflows, runtime behavior, evaluation cases, deployment surfaces, and integrations around production-oriented agent systems.
pip install google-adk.Agent, Workflow, adk run, and adk web examples for local agent development.https://adk.dev/; the older https://google.github.io/adk-docs/ documentation URL currently redirects there.adk create, root agent structure, tool definitions, Gemini API key setup, command-line runs, and the ADK web interface.google/adk-python, is Apache-2.0 licensed, and is active.Checked current content/tools/, content/mcp/, agents, hooks, rules, skills, commands, guides, open pull requests, live issue state, and repository-wide content for Google Agent Development Kit, Google ADK, google/adk-python, google.github.io/adk-docs, adk.dev, agent development kit, adk run, and adk web. No dedicated Google ADK tools entry, source URL duplicate, target file, or open duplicate PR was found.
Editorial listing. No paid placement or affiliate link is used. Google Agent Development Kit is Apache-2.0 open-source software; Google Cloud services, Gemini APIs, model providers, deployment targets, MCP tools, A2A integrations, and third-party systems may have separate licenses, billing, terms, privacy obligations, and access controls.
Show that Google Agent Development Kit is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/tools/google-agent-development-kit)Google Agent Development Kit side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
Next steps differ across entries — use the actions in the table below to copy install commands and source links per resource.
| Field | Apache-2.0 code-first toolkit for building, running, evaluating, and deploying AI agents, workflows, tools, sessions, and multi-agent systems. Open dossier | Open-source Python multi-agent framework for building agent societies, role-playing agents, stateful ChatAgent workflows, RAG agents, synthetic data generation, MCP-enabled use cases, and research-scale agent experiments. Open dossier | Agent orchestration framework for building stateful, controllable, multi-step LLM and agent workflows. Open dossier | Official Python framework for building multi-agent workflows with agents, tools, handoffs, guardrails, sessions, tracing, realtime voice agents, MCP tools, hosted tools, human-in-the-loop flows, and sandbox agents. Open dossier |
|---|---|---|---|---|
| Next stepsDiffers | ||||
| Trust | ||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| SubmitterDiffers | oktofeesh1 | — | — | — |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety · Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | ||||
| Category | tools | tools | tools | tools |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | CAMEL-AI | LangChain | OpenAI | |
| Added | 2026-06-04 | 2026-06-18 | 2026-04-27 | 2026-06-18 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓ADK agents can call tools, APIs, workflows, and other agents, so permissions, confirmations, allowlists, budgets, and human-review paths should be designed before connecting real systems. The ADK 2.0 README notes breaking changes to the agent API, event model, and session schema; teams should pin versions and test session compatibility before upgrading production agents. The Python quickstart writes model credentials to a local `.env` file; projects should keep secrets out of git, logs, traces, shared notebooks, and generated support artifacts. The ADK web UI is documented for development and debugging, not production deployment; production agents should use hardened deployment paths with explicit auth and network controls. Agent evaluations should test final responses, tool-use trajectory, intermediate agent responses, failure paths, and unsafe action attempts before exposing autonomous workflows. Deployments on Agent Runtime, Cloud Run, GKE, or containers need operational controls for cost, quota, prompt injection, tool misuse, logging, incident response, and rollback. | ✓CAMEL agents can coordinate multi-step tasks, call tools, use web/search integrations, connect to MCP examples, and run with provider credentials; review tool permissions before giving agents write access or account access. Large-scale agent societies and role-playing workflows can generate high volumes of model calls, tool calls, logs, synthetic data, and intermediate artifacts; set budgets, rate limits, and stop conditions before long runs. RAG, document, media, browser, communication, and data-tool extras may access local files, third-party APIs, vector stores, notebooks, or generated datasets; isolate experiments from production systems. CAMEL examples include MCP-oriented use cases, but MCP does not make connected tools safe by default. Scope server permissions, credentials, filesystem access, and approval gates separately. Do not treat generated code, generated datasets, citations, research summaries, or multi-agent decisions as verified until they have been reviewed against source data and policy requirements. | — missing | ✓Agents can call function tools, hosted tools, MCP tools, realtime tools, and sandbox agents; treat every tool as an API endpoint with explicit authorization, input validation, rate limits, and side-effect controls. Sandbox agents can inspect files, run commands, apply patches, and carry workspace state across longer tasks; restrict workspace scope and require human approval before destructive or high-impact actions. Guardrails are useful runtime checks, but they do not replace permission checks, least-privilege credentials, audit logs, or human review for risky operations. Handoffs and agents-as-tools can delegate work across agents; document which agent owns each tool, decision, retry, rollback, and escalation path. Realtime voice agents and human-in-the-loop flows need clear consent, interruption, recording, and operator takeover behavior. |
| Privacy notes | ✓ADK workflows can process prompts, chat histories, session state, tool arguments, tool outputs, traces, logs, evaluation cases, model responses, API keys, and deployment metadata. Local `.env` files, generated agent projects, debug logs, web UI sessions, traces, eval sets, and test files can retain sensitive user, project, or credential data. Google AI Studio, Gemini APIs, Agent Runtime, Cloud Run, GKE, observability integrations, MCP tools, A2A integrations, and third-party model providers may process prompts, outputs, traces, credentials, or service metadata depending on configuration. Evaluation datasets can include user queries, expected tool calls, intermediate agent responses, final answers, initial session state, and custom metrics that may reveal private workflows. Teams should define who can inspect sessions, traces, eval sets, tool outputs, deployment logs, API keys, and model-provider artifacts before using ADK for production agents. | ✓Prompts, model responses, agent messages, tool arguments, tool outputs, retrieved documents, search results, logs, generated datasets, traces, and errors may include user or workspace data. Model providers, search providers, MCP servers, vector stores, web tools, document parsers, browser tools, and observability integrations may receive data from CAMEL workflows. Keep provider API keys, OAuth tokens, MCP server credentials, vector database URLs, generated logs, and synthetic datasets out of committed examples, screenshots, public issues, and shared notebooks. If `CAMEL_MODEL_LOG_ENABLED` or other logging/tracing integrations are enabled, review request/response logs and model configuration logs before sharing or retaining them. | ✓LangGraph sends prompts and graph state to your configured model provider (including Claude); persisted state and checkpoints can contain message and tool-call data. | ✓Prompts, instructions, tool arguments, tool outputs, session history, traces, realtime audio events, sandbox files, logs, provider responses, and errors may contain user or workspace data. Do not expose secrets, tokens, private file paths, customer records, credentials, internal identifiers, or raw exceptions through traces, logs, prompts, tool schemas, or examples. When using MCP servers, hosted tools, Redis sessions, SQL-backed sessions, or observability systems, review each service's retention, access control, and third-party data handling separately. If sandbox agents operate on repositories or user files, define which files can be mounted, modified, committed, uploaded, logged, or returned to the model. |
| Prerequisites |
|
| — none listed |
|
| Install | — | | — | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Python multi-agent framework for agent societies, ChatAgent workflows, RAG, tool use, MCP examples, data generation, and large-scale agent research.
Stateful orchestration framework for LLM agents.
Source-backed guides for putting this to work.
Use Agent Skills in the Claude Agent SDK: filesystem discovery via settingSources, the skills option to enable or filter, and tool access.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.