Search

More Filters

Show More
Add Listing
Go Back

portia sdk python

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Portia SDK Python is an open source developer framework for building predictable, stateful, authenticated multi-agent workflows. It is designed for developers who need production-ready control over agent behaviour, allowing as much or as little oversight as required across multi-agent deployments. The SDK provides primitives to author, run and monitor agent plans, to enrich run state during execution, and to define deterministic tasks and human:agent clarifications for interactive flows. It emphasizes production concerns such as attribution of runs to end users, secure handling of credentials, large-input memory storage, and support for multiple LLM providers. The repository includes a CLI, examples, and configuration options to connect cloud tool registries, local tools or MCP servers, and is intended to accelerate building, testing and operating agentic systems in real environments.

Links

Stars
436
App URL
https://github.com/portiaAI/portia-sdk-python
Github Repository
https://github.com/portiaAI/portia-sdk-python/blob/main/README.md

App Details

Features
The README highlights iterative control over agent reasoning and runtime intervention via Plan and PlanBuilder primitives and PlanRunState instrumentation. It supports deterministic tasks and human confirmations using ExecutionHooks and clarifications. Extensive tool integration is provided through flexible tool registries, MCP server support and a Portia cloud registry of prebuilt tools. A browser tool is available for web navigation and handling login/captcha scenarios. Authentication features manage API and web credentials within agent runs. Production features include EndUser-level attribution, automatic storage of large inputs/outputs in agent memory, pluggable LLM support, and optional Redis caching. The project ships examples, a CLI, and configuration options for storage and logging to aid debugging and observability.
Use Cases
This SDK helps developer teams build, test and operate multi-agent workflows with a focus on predictability, security and production readiness. It reduces engineering overhead by providing plan authoring tools, run state tracking and built-in hooks for deterministic tasks and human approvals. Tool registries and MCP integration simplify connecting external services, and the browser tool handles complex web interactions. Authentication and EndUser attribution make it easier to run agents that require user credentials while remaining auditable. Built-in memory for large inputs and outputs and support for any LLM provider enable flexible deployment choices. The included CLI, examples and configuration defaults accelerate onboarding and validation so teams can iterate quickly and move agents into monitored production runs.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*