Search

More Filters

Show More
Add Listing
Go Back

TaskWeaver

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

TaskWeaver is a code-first agent framework designed to plan and execute data analytics tasks by generating and running code snippets. It interprets natural language requests, decomposes complex tasks, and orchestrates plugins implemented as Python functions to perform data operations. The framework preserves both chat history and code execution history, including in-memory data structures such as DataFrames, which makes it suited for workflows that require handling rich, high-dimensional tabular data. TaskWeaver supports multiple interaction modes including a command line interface, a demo Web UI, and import as a library. It requires Python 3.10 or newer and relies on user-provided LLM configuration. The repo includes sample plugins, demo examples like anomaly detection and time series forecasting, documentation, and instructions for containerized code execution using Docker.

Links

Stars
5858
App URL
https://github.com/microsoft/TaskWeaver
Github Repository
https://github.com/microsoft/TaskWeaver/blob/main/README.md

Categorization

App Details

Features
TaskWeaver provides planning and task decomposition, reflective execution that lets agents adjust plans during runtime, and stateful execution that preserves code state and intermediate data. It supports a plugin system for custom algorithms and integrations, rich data handling with Python data structures such as DataFrames, and code verification to detect potential issues before execution. The project includes shared memory between roles, experience selection, multiple roles including Planner and an experimental Recepta reasoning role, and integration with observability tooling. Execution runs in isolated containers by default and there is an all-in-one Docker image. The repo includes detailed logs for debugging, supports multiple LLM backends such as OpenAI, and provides sample plugins built on packages like Langchain.
Use Cases
TaskWeaver helps developers and data practitioners build agents that can plan, generate, verify, and execute data analysis workflows while maintaining execution state and intermediate results. By preserving code execution history and in-memory data, it enables more expressive interactions than text-only agent systems and simplifies working with complex data types. The plugin architecture allows encapsulating domain-specific algorithms and data access logic, accelerating integration with databases and libraries. Containerized execution and session isolation improve reproducibility and security. Built-in examples, documentation, a Web UI demo, and CLI entry points lower the barrier to experiment and extend the framework for anomaly detection, forecasting, and other data tasks.

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*