AI Skill Hub 推荐使用:开源AI工作流:Jido工作室 是一款优质的Agent工作流。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
Jido工作室是一款开源的AI工作流工具,基于Elixir开发,提供可嵌入的代理工作室,用于管理Jido的实时视图仪表板。它突出了AI工作流的可定制性和可扩展性,适用于各种AI应用场景。
开源AI工作流:Jido工作室 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Jido工作室是一款开源的AI工作流工具,基于Elixir开发,提供可嵌入的代理工作室,用于管理Jido的实时视图仪表板。它突出了AI工作流的可定制性和可扩展性,适用于各种AI应用场景。
开源AI工作流:Jido工作室 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 克隆仓库 git clone https://github.com/agentjido/jido_studio cd jido_studio # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
# 查看帮助 jido_studio --help # 基本运行 jido_studio [options] <input> # 详细使用说明请查阅文档 # https://github.com/agentjido/jido_studio
# jido_studio 配置说明 # 查看配置选项 jido_studio --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export JIDO_STUDIO_CONFIG="/path/to/config.yml"
Embeddable agent studio for Phoenix applications — a standalone LiveView dashboard for managing and debugging Jido AI agents.
Inspired by Mastra Studio and modeled after Oban Web, Jido Studio is a self-contained Hex package that mounts directly into your Phoenix router with zero asset pipeline integration.
/catalog; /registry remains compatible)Interact workbench for non-chat/runtime-driven interactionProduct Agents and Internal Agents using agent_interactions.internal_agent_tagsnode=all or node=<name>) on demanddef deps do
[
{:jido_studio, "~> 0.1.0"}
]
end
Then fetch dependencies:
mix deps.get
Add jido_studio to your dependencies:
def deps do
[
{:jido_studio, "~> 0.1.0"}
]
end
Use this sequence for a clean first-time setup.
After mount, Studio surfaces a Setup Assistant on Home with a re-entry card in Settings. Checks cover:
Profiles are guidance-only presets shown in-app:
Local Dev Fast StartChat Demo ShowcaseTeam Durable OpsApply profile snippet means show/copy snippet text with "What changes?" and rollback notes. Studio does not mutate host config files.
Mount the studio in your Phoenix router:
```elixir
Studio Playground seeds non-chat examples under dev/studio_playground/lib/studio_playground/demo_agents/non_chat_agents.ex:
StudioPlayground.DemoAgents.SignalRunnerAgent — Signal-first route execution example for introspection and guarded dispatchStudioPlayground.DemoAgents.DeviceControlAgent — Schema-driven control flows with richer action payloadsThese examples are registered in dev/studio_playground/lib/studio_playground/demo_agents.ex so they appear in the active/discovered lists by default.
Studio supports optional package-specific admin pages through extensions. Built-in extension routes are only compiled when their backing package is available.
Current built-in extension:
jido_messaging -> Messaging / Rooms pageOptional extension modules can also be registered from the host app:
config :jido_studio,
extension_modules: [MyAppWeb.Studio.Extensions.Custom]
For jido_messaging room listing, you can provide an explicit provider if your API differs:
config :jido_studio,
messaging_room_provider: {MyApp.MessagingAdmin, :list_rooms}
Set your Jido supervisor module so Studio can show running instances (without this, Studio still shows discovered modules only):
```elixir
config :jido_studio, jido_instance: MyApp.Jido
Optional override for multi-runtime installs:
elixir config :jido_studio, :jido_instances, [ %{key: "primary", module: MyApp.Jido, label: "Primary"}, %{key: "batch", module: MyApp.BatchJido, label: "Batch Runtime"} ]
When `:jido_instances` is present, Studio shows a runtime selector in the sidebar.
When it is absent, Studio derives a single runtime from `:jido_instance` and keeps the UI simplified.
Default observability persistence is ETS and needs no extra setup:
elixir config :jido_studio, :persistence, adapter: JidoStudio.Persistence.ETS, opts: []
Optional next-wave debug/observability defaults:
elixir config :jido_studio, live_ops: [ enabled: true, auto_follow_default: true, scope_keys: [:project_id, :user_id], event_stream_limit: 100, agent_list_poll_ms: 2_000, viewer_tracking: true ], delegation: [ enabled: true ], tracing: [ hide_internal_default: true, chunk_span_sampling: 1.0, max_span_rows: 5_000 ], evals: [ enabled: true, rule_sets: [:default] ], agent_interactions: [ enabled: true, default_tab: :auto, runner_timeout_ms: 5_000, runner_history_limit: 20, internal_agent_tags: ["internal"] ]
Studio now ships a built-in Presence default (`JidoStudio.Presence`) so viewer tracking works out-of-the-box.
If your host app already has its own Presence module, you can override it:
elixir config :jido_studio, pubsub: MyApp.PubSub, live_ops: [ enabled: true, viewer_tracking: true, presence_module: MyApp.Presence ] ```
Switch the persistence adapter:
config :jido_studio, :persistence,
adapter: JidoStudio.Persistence.Ecto,
opts: [repo: MyApp.Repo, prefix: "public"]
Copy the provided migration template into your host app and run:
mix ecto.migrate
Template:
priv/ecto/migrations/20260215000000_create_jido_studio_persistence_tables.exsconfig :jido_studio, auto_start_runtime: false
elixir
Jido工作室是一款开源的AI工作流工具,提供了可嵌入的代理工作室和实时视图仪表板,适用于各种AI应用场景。然而,它的开发语言为Elixir,可能会对一些开发者造成挑战。总体而言,Jido工作室是一个值得关注的AI工作流工具。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,开源AI工作流:Jido工作室 是一款质量良好的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | jido_studio |
| 原始描述 | 开源AI工作流:Embeddable agent studio for Jido - a standalone LiveView dashboard for managing 。⭐13 · Elixir |
| Topics | workflowelixir |
| GitHub | https://github.com/agentjido/jido_studio |
| License | Apache-2.0 |
| 语言 | Elixir |
收录时间:2026-05-22 · 更新时间:2026-05-23 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端