Build your own AI product, whatever your experience.
Let your familiar coding assistant guide development. Tansr SDK connects models, tools, sessions and permissions to turn your idea into an AI product that runs.
Reuse the SDK Harness, the shared foundation for running agents, with agent loops, tool calls, sessions and permissions. Spend less effort rebuilding common infrastructure and focus on business features and product experience.
Keep your existing architecture, user identity system and data. Use the SDK and runtime services to add agent capabilities and bring AI into your business workflows.
Support ongoing operations with application, organization, permission and usage management, connecting existing systems and team workflows. Your business retains control of authorization and delivery standards; Tansr provides reusable agent capabilities.
Requires local file and terminal access, plus Node.js >=22.19.
Choose a scope in your terminal, then confirm the paths to install.
Copying does not install the Skill. Verify actual loading before step two.
Desktop user Skills use ~/.workbuddy/skills. The project .codebuddy/skills path follows the verified runtime entry; verify the actual SKILL.md read, as desktop listing is not guaranteed. Discovery does not prove selection.
Build for everyone: turn your idea into an app for your phone or computer in just two steps.
The choice of over 1300+ developers
The shortest path to intelligent software
A leader in Agent SDK standardization
For SDK applications only
SDK application pricing
Choose an operating scale for agent applications built with the SDK. Adjudication, memory, context, tools and media capabilities span the plans; individuals and organizations each hold their own plan and wallet.
Standalone use of CLI, serve, ACP or headless does not require this subscription. Services delivered through platform applications are subject to their individual or organization owner's application limits. Model and media calls are still billed by usage.
免费版
全量模型免费用！
Free
Valid for 365 days from claim
Included operating limits:
10 concurrency slots
Up to 2 applications
Up to 3 developer seats per organization
Up to 10 distinct end users per month
One claim per individual or organization, including across catalog updates. Owners with active, grace-period or scheduled plans cannot claim.
¥20.00 in model credit on claim (CNY, not withdrawable)
200,000 LLM tokens of bonus usage allowance. Granted once per individual or organization when claimed; expires after 7 days or with the free plan, whichever comes first.
最快的验证你的创作想法，创业思路。
Administrator-supplied catalog text is shown in its original language; translations are not available for these fields.
¥6400.00 in model credit per purchase (CNY, not withdrawable)
100,000,000 LLM tokens of bonus usage allowance. Granted once per purchase order, available when that plan takes effect and expires after 30 days or when that plan expires, whichever comes first.
Administrator-supplied catalog text is shown in its original language; translations are not available for these fields.
Create your first 1 applications free of subscription charges. More than 5 applications requires Individual developer or above. Select individual or organization ownership before claiming or purchasing. All prices are in Chinese yuan (CNY).
Bonus tokens offset settled usage and cannot be redeemed for cash. Applies only to platform-paid LLM usage settled in Chinese yuan (CNY). Input, output, cache-read and cache-write tokens are counted without duplication. Images, video, speech recognition (ASR), speech synthesis (TTS), search, bring-your-own-key (BYOK) calls and client-reported usage are excluded.
We plan to release the Tansr Agent SDK source under the MIT license.
MIT
Review the source
Inspect how the SDK runs, handles data and applies permissions. Make technical decisions with the implementation in view.
Adapt it to your product
Modify and integrate the released source under the MIT license, including in commercial products.
Keep the code in your hands
Retain and maintain your own copy of the released code, giving your team more control over its future.
The plan covers the SDK source intended for release. MIT permits use, modification and redistribution while requiring copyright and license notices to be retained. Hosted platform services and model usage remain governed by their own terms.
Build a desktop assistant, a file workflow or an agent inside your service. The harness handles the execution loop while you build the product experience.
Agent loop and model switching
An Agent Harness SDK connects model calls, tool execution and results in a multi-step agent loop. Use platform-configured, authorized models and switch through aliases within a session.
Install the npm package with TypeScript definitions. Run the SDK in the Electron main process and connect your interface over IPC, or embed it in a Node.js server.
Connect your business functions with defineTool, existing services through MCP, and domain knowledge through defineSkill or skill directories. File operations remain subject to capabilities and runtime permissions.
Resume conversations with history snapshots and an injected store. Stream text and tool status into your interface with SessionView. Your application chooses where to persist conversation history.
Connect capability switches, runtime rules and approval callbacks. In token mode, keep appkey credentials on your backend, issue short-lived tokens to clients and let the platform manage upstream keys.
Track consumption with live usage events, per-user queries and developer cost reconciliation. The SDK provides metering; developers implement their own end-user pricing and payment flow.
It runs the model and tool loop, manages conversational context and sessions, and applies configured permission rules. Your application provides its business functions, user interface, identity and storage choices.
Can I keep long-lived API keys out of my desktop client?
In token mode, your backend keeps the appkey credentials and issues short-lived tokens after authenticating a user. Upstream model keys stay on the platform. Follow the token-server example for the complete integration.
Can I bill my own users from Token usage?
Use live usage events, per-user counters and developer cost reconciliation as inputs. You implement end-user prices, invoicing and payments. SDK application plans and model or media usage are separate charges.