Upsonic
Task oriented AI agent framework for digital workers and vertical AI agents
Stars: 6078
Upsonic offers a cutting-edge enterprise-ready framework for orchestrating LLM calls, agents, and computer use to complete tasks cost-effectively. It provides reliable systems, scalability, and a task-oriented structure for real-world cases. Key features include production-ready scalability, task-centric design, MCP server support, tool-calling server, computer use integration, and easy addition of custom tools. The framework supports client-server architecture and allows seamless deployment on AWS, GCP, or locally using Docker.
README:
Upsonic offers a cutting-edge enterprise-ready framework where you can orchestrate LLM calls, agents, and computer use to complete tasks cost-effectively. It provides more reliable systems, scalability, and a task-oriented structure that you need while completing real-world cases.
Key features:
- Production-Ready Scalability: Deploy seamlessly on AWS, GCP, or locally using Docker.
-
Task-Centric Design: Focus on practical task execution, with options for:
- Basic tasks via LLM calls.
- Advanced tasks with V1 agents.
- Complex automation using V2 agents with MCP integration.
- MCP Server Support: Utilize multi-client processing for high-performance tasks.
- Tool-Calling Server: Exception-secure tool management with robust server API interactions.
- Computer Use Integration: Execute human-like tasks using Anthropic’s ‘Computer Use’ capabilities.
- Easily adding tools: You can add your custom tools and MCP tools with a single line of code.
- Client-server architecture: Production-ready stateless enterprise-ready system
- Python 3.10 or higher
- Access to OpenAI or Anthropic API keys (Azure and Bedrock Supported)
pip install upsonic
from upsonic import UpsonicClient, ObjectResponse, Task, AgentConfiguration
from upsonic.client.tools import Search
# Create Client and and Set Configurations
client = UpsonicClient("localserver")
client.set_config("OPENAI_API_KEY", "YOUR_API_KEY")
# Generating Task and Agent
task1 = Task(description="Research latest news in Anthropic and OpenAI", tools=[Search])
product_manager_agent = AgentConfiguration(
job_title="Product Manager",
company_url="https://upsonic.ai",
company_objective="To build AI Agent framework that helps people get things done",
)
# Run and see the result
client.agent(product_manager_agent, task1)
result = task1.response
print(result)Create a client to manage tools and tasks:
from upsonic import UpsonicClient, ObjectResponse, Task, AgentConfiguration
from upsonic.client.tools import Search
# Create an Upsonic client instance
client = UpsonicClient("localserver")
client.set_config("OPENAI_API_KEY", "YOUR_API_KEY")
client.default_llm_model = "openai/gpt-4o"- deepseek-chat
client.set_config("DEEPSEEK_API_KEY", "YOUR_DEEPSEEK_API_KEY")
client.default_llm_model = "deepseek/deepseek-chat"- claude-3-5-sonnet
client.set_config("ANTHROPIC_API_KEY", "YOUR_ANTHROPIC_API_KEY")
client.default_llm_model = "claude/claude-3-5-sonnet"- gpt-4o-azure
client.set_config("AZURE_OPENAI_ENDPOINT", "YOUR_AZURE_OPENAI_ENDPOINT")
client.set_config("AZURE_OPENAI_API_VERSION", "YOUR_AZURE_OPENAI_API_VERSION")
client.set_config("AZURE_OPENAI_API_KEY", "YOUR_AZURE_OPENAI_API_KEY")
client.default_llm_model = "azure/gpt-4o"- claude-3-5-sonnet-aws
client.set_config("AWS_ACCESS_KEY_ID", "YOUR_AWS_ACCESS_KEY_ID")
client.set_config("AWS_SECRET_ACCESS_KEY", "YOUR_AWS_SECRET_ACCESS_KEY")
client.set_config("AWS_REGION", "YOUR_AWS_REGION")
client.default_llm_model = "bedrock/claude-3-5-sonnet"The task is based on the description. We have a mechanism to automatically generate sub-tasks from a high-level task description. For example, a task to track AI industry developments might be described as: "Research latest news in Anthropic and OpenAI." This will be turned into smaller, more manageable tasks ("Make a Google search for Anthropic and OpenAI," "Read the blogs," "Read the official descriptions of Anthropic and OpenAI").
# Define a new Task
description = "Research latest news in Anthropic and OpenAI"The output is essential for deploying an AI agent across apps or as a service. In Upsonic, we use Pydantic BaseClass as input for the task system. This allows you to configure the output exactly how you want it, such as a list of news with title, body, and URL. You can create a flexible yet robust output mechanism that improves interoperability between the agent and your app.
# Example ObjectResponse usage
class News(ObjectResponse):
title: str
body: str
url: str
tags: list[str]
class ResponseFormat(ObjectResponse):
news_list: list[News]Our Framework officially supports Model Context Protocol (MCP) and custom tools. You can use hundreds of MCP servers at https://glama.ai/mcp/servers or https://smithery.ai/ We also support Python functions inside a class as a tool. You can easily generate your integrations with that.
@client.mcp()
class HackerNewsMCP:
command = "uvx"
args = ["mcp-hn"]
@client.tool()
class MyTools:
def our_server_status():
return True
tools = [Search, MyTools] # HackerNewsMCPAfter defining these terms, you are ready to generate your first task. This structure is a key component of the Upsonic task-oriented structure. Once you define a task, you can run it with agents or directly via an LLM call to obtain the result over the Task object. The automatic sub-task mechanism is also essential for enhancing quality and precision.
This simplicity is a hallmark of Upsonic.
task1 = Task(description=description, response_format=ResponseFormat, tools=tools)Agents are the standard way to configure an LLM for your employees to work on your requests. It is essential to consider the goals and context of tasks. In Upsonic, we have an automatic characterization mechanism that enriches the given information by researchers agents working on Upsonic. For example, a Product Manager Agent can be configured with job title, company URL, and company objectives. Representing agents as roles like it supports practical agents aligned with their unique objectives.
product_manager_agent = AgentConfiguration(
job_title="Product Manager",
company_url="https://upsonic.ai",
company_objective="To build AI Agent framework that helps people get things done",
)Define the task and the agent, then combine them and run. The Upsonic Server will prepare and run the task. This standard method simplifies the use of agents in your SaaS applications or your new vertical AI agents. 🤖 You are now completely ready to run your first agent.
client.agent(product_manager_agent, task1)
result = task1.response
for i in result.news_list:
print()
print("News")
print("Title: ", i.title)
print("Body: ", i.body)
print("URL: ", i.url)
print("Tags: ", i.tags)LLMs have always been intelligent. We know exactly when to call an agent or an LLM. This creates a smooth transition from LLM to agent systems. The call method works like an agent, based on tasks and optimizing cost and latency for your requirements. Focus on the task. Don't waste time with complex architectures.
client.call(task1)Humans have an incredible capacity for context length, which reflects their comprehensive context awareness and consistently produces superior results. In Upsonic, our memory system adeptly handles complex workflows, delivering highly personalized outcomes. It seamlessly remembers prior tasks and preferences, ensuring optimal performance. You can confidently set up memory settings within AgentConfiguration, leveraging the agent_id system. Agents, each with their distinct personality, are uniquely identified by their ID, ensuring precise and efficient execution.
agent_id_ = "product_manager_agent"
product_manager_agent = AgentConfiguration(
agent_id_=agent_id_
...
memory=True
)The Knowledge Base provides private or public content to your agent to ensure accurate and context-aware tasks. For example, you can provide a PDF and URL to the agent. The Knowledge Base seamlessly integrates with the Task System, requiring these sources.
from upsonic import KnowledgeBase
my_knowledge_base = KnowledgeBase(files=["sample.pdf", "https://upsonic.ai"])
task1 = Task(
...
context[my_knowledge_base]
)Chaining tasks is essential for complex workflows where one task's output informs the next. You can assign a task to another as context for performing the job. This will prepare the response of task 1 for task 2.
task1 = Task(
...
)
task2 = Task(
...
context[task1]
)Agent and characterization are based on LLM itself. We are trying to characterize the developer, PM, and marketing. Sometimes, we need to give a human name. This is required for tasks like sending personalized messages or outreach. For these requirements, we have name and contact settings in AgentConfiguration. The agent will feel like a human as you specify.
product_manager_agent = AgentConfiguration(
...
name="John Walk"
contact="[email protected]"
)Distribute tasks effectively across agents with our automated task distribution mechanism. This tool matches tasks based on the relationship between agent and task, ensuring collaborative problem-solving across agents and tasks.
client.multi_agent([agent1, agent2], [task1, task2])Computer use can able to human task like humans, mouse move, mouse click, typing and scrolling and etc. So you can build tasks over non-API systems. It can help your linkedin cases, internal tools. Computer use is supported by only Claude for now.
from upsonic.client.tools import ComputerUse
...
tools = [ComputerUse]
...LLM's by their nature oriented to finish your process. By the way its mean sometimes you can get empty result. Its effect your business logic and your application progress. We support reflection mechanism for that to check the result is staisfying and if not give a feedback. So you can use the reflection for preventing blank messages and other things.
product_manager_agent = AgentConfiguration(
...
reflection=True
)The context windows can be small as in OpenAI models. In this kind of situations we have a mechanism that compresses the message, system_message and the contexts. If you are working with situations like deepsearching or writing a long content and giving it as context of another task. The compress_context is full fit with you. This mechanism will only work in context overflow situations otherwise everything is just normal.
product_manager_agent = AgentConfiguration(
...
compress_context=True
)We use anonymous telemetry to collect usage data. We do this to focus our developments on more accurate points. You can disable it by setting the UPSONIC_TELEMETRY environment variable to false.
import os
os.environ["UPSONIC_TELEMETRY"] = "False"- Dockerized Server Deploy
- Verifiers For Computer Use
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for Upsonic
Similar Open Source Tools
Upsonic
Upsonic offers a cutting-edge enterprise-ready framework for orchestrating LLM calls, agents, and computer use to complete tasks cost-effectively. It provides reliable systems, scalability, and a task-oriented structure for real-world cases. Key features include production-ready scalability, task-centric design, MCP server support, tool-calling server, computer use integration, and easy addition of custom tools. The framework supports client-server architecture and allows seamless deployment on AWS, GCP, or locally using Docker.
ell
ell is a lightweight, functional prompt engineering framework that treats prompts as programs rather than strings. It provides tools for prompt versioning, monitoring, and visualization, as well as support for multimodal inputs and outputs. The framework aims to simplify the process of prompt engineering for language models.
py-vectara-agentic
The `vectara-agentic` Python library is designed for developing powerful AI assistants using Vectara and Agentic-RAG. It supports various agent types, includes pre-built tools for domains like finance and legal, and enables easy creation of custom AI assistants and agents. The library provides tools for summarizing text, rephrasing text, legal tasks like summarizing legal text and critiquing as a judge, financial tasks like analyzing balance sheets and income statements, and database tools for inspecting and querying databases. It also supports observability via LlamaIndex and Arize Phoenix integration.
LeanCopilot
Lean Copilot is a tool that enables the use of large language models (LLMs) in Lean for proof automation. It provides features such as suggesting tactics/premises, searching for proofs, and running inference of LLMs. Users can utilize built-in models from LeanDojo or bring their own models to run locally or on the cloud. The tool supports platforms like Linux, macOS, and Windows WSL, with optional CUDA and cuDNN for GPU acceleration. Advanced users can customize behavior using Tactic APIs and Model APIs. Lean Copilot also allows users to bring their own models through ExternalGenerator or ExternalEncoder. The tool comes with caveats such as occasional crashes and issues with premise selection and proof search. Users can get in touch through GitHub Discussions for questions, bug reports, feature requests, and suggestions. The tool is designed to enhance theorem proving in Lean using LLMs.
marvin
Marvin is a lightweight AI toolkit for building natural language interfaces that are reliable, scalable, and easy to trust. Each of Marvin's tools is simple and self-documenting, using AI to solve common but complex challenges like entity extraction, classification, and generating synthetic data. Each tool is independent and incrementally adoptable, so you can use them on their own or in combination with any other library. Marvin is also multi-modal, supporting both image and audio generation as well using images as inputs for extraction and classification. Marvin is for developers who care more about _using_ AI than _building_ AI, and we are focused on creating an exceptional developer experience. Marvin users should feel empowered to bring tightly-scoped "AI magic" into any traditional software project with just a few extra lines of code. Marvin aims to merge the best practices for building dependable, observable software with the best practices for building with generative AI into a single, easy-to-use library. It's a serious tool, but we hope you have fun with it. Marvin is open-source, free to use, and made with 💙 by the team at Prefect.
web-llm
WebLLM is a modular and customizable javascript package that directly brings language model chats directly onto web browsers with hardware acceleration. Everything runs inside the browser with no server support and is accelerated with WebGPU. WebLLM is fully compatible with OpenAI API. That is, you can use the same OpenAI API on any open source models locally, with functionalities including json-mode, function-calling, streaming, etc. We can bring a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration.
magic-cli
Magic CLI is a command line utility that leverages Large Language Models (LLMs) to enhance command line efficiency. It is inspired by projects like Amazon Q and GitHub Copilot for CLI. The tool allows users to suggest commands, search across command history, and generate commands for specific tasks using local or remote LLM providers. Magic CLI also provides configuration options for LLM selection and response generation. The project is still in early development, so users should expect breaking changes and bugs.
paper-qa
PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and includes a process of embedding docs, queries, searching for top passages, creating summaries, using an LLM to re-score and select relevant summaries, putting summaries into prompt, and generating answers. The tool can be used to answer specific questions related to scientific research by leveraging citations and relevant passages from documents.
tonic_validate
Tonic Validate is a framework for the evaluation of LLM outputs, such as Retrieval Augmented Generation (RAG) pipelines. Validate makes it easy to evaluate, track, and monitor your LLM and RAG applications. Validate allows you to evaluate your LLM outputs through the use of our provided metrics which measure everything from answer correctness to LLM hallucination. Additionally, Validate has an optional UI to visualize your evaluation results for easy tracking and monitoring.
Bard-API
The Bard API is a Python package that returns responses from Google Bard through the value of a cookie. It is an unofficial API that operates through reverse-engineering, utilizing cookie values to interact with Google Bard for users struggling with frequent authentication problems or unable to authenticate via Google Authentication. The Bard API is not a free service, but rather a tool provided to assist developers with testing certain functionalities due to the delayed development and release of Google Bard's API. It has been designed with a lightweight structure that can easily adapt to the emergence of an official API. Therefore, using it for any other purposes is strongly discouraged. If you have access to a reliable official PaLM-2 API or Google Generative AI API, replace the provided response with the corresponding official code. Check out https://github.com/dsdanielpark/Bard-API/issues/262.
neo4j-graphrag-python
The Neo4j GraphRAG package for Python is an official repository that provides features for creating and managing vector indexes in Neo4j databases. It aims to offer developers a reliable package with long-term commitment, maintenance, and fast feature updates. The package supports various Python versions and includes functionalities for creating vector indexes, populating them, and performing similarity searches. It also provides guidelines for installation, examples, and development processes such as installing dependencies, making changes, and running tests.
allms
allms is a versatile and powerful library designed to streamline the process of querying Large Language Models (LLMs). Developed by Allegro engineers, it simplifies working with LLM applications by providing a user-friendly interface, asynchronous querying, automatic retrying mechanism, error handling, and output parsing. It supports various LLM families hosted on different platforms like OpenAI, Google, Azure, and GCP. The library offers features for configuring endpoint credentials, batch querying with symbolic variables, and forcing structured output format. It also provides documentation, quickstart guides, and instructions for local development, testing, updating documentation, and making new releases.
BentoVLLM
BentoVLLM is an example project demonstrating how to serve and deploy open-source Large Language Models using vLLM, a high-throughput and memory-efficient inference engine. It provides a basis for advanced code customization, such as custom models, inference logic, or vLLM options. The project allows for simple LLM hosting with OpenAI compatible endpoints without the need to write any code. Users can interact with the server using Swagger UI or other methods, and the service can be deployed to BentoCloud for better management and scalability. Additionally, the repository includes integration examples for different LLM models and tools.
raptor
RAPTOR introduces a novel approach to retrieval-augmented language models by constructing a recursive tree structure from documents. This allows for more efficient and context-aware information retrieval across large texts, addressing common limitations in traditional language models. Users can add documents to the tree, answer questions based on indexed documents, save and load the tree, and extend RAPTOR with custom summarization, question-answering, and embedding models. The tool is designed to be flexible and customizable for various NLP tasks.
semantic-cache
Semantic Cache is a tool for caching natural text based on semantic similarity. It allows for classifying text into categories, caching AI responses, and reducing API latency by responding to similar queries with cached values. The tool stores cache entries by meaning, handles synonyms, supports multiple languages, understands complex queries, and offers easy integration with Node.js applications. Users can set a custom proximity threshold for filtering results. The tool is ideal for tasks involving querying or retrieving information based on meaning, such as natural language classification or caching AI responses.
storm
STORM is a LLM system that writes Wikipedia-like articles from scratch based on Internet search. While the system cannot produce publication-ready articles that often require a significant number of edits, experienced Wikipedia editors have found it helpful in their pre-writing stage. **Try out our [live research preview](https://storm.genie.stanford.edu/) to see how STORM can help your knowledge exploration journey and please provide feedback to help us improve the system 🙏!**
For similar tasks
unstract
Unstract is a no-code platform that enables users to launch APIs and ETL pipelines to structure unstructured documents. With Unstract, users can go beyond co-pilots by enabling machine-to-machine automation. Unstract's Prompt Studio provides a simple, no-code approach to creating prompts for LLMs, vector databases, embedding models, and text extractors. Users can then configure Prompt Studio projects as API deployments or ETL pipelines to automate critical business processes that involve complex documents. Unstract supports a wide range of LLM providers, vector databases, embeddings, text extractors, ETL sources, and ETL destinations, providing users with the flexibility to choose the best tools for their needs.
mslearn-knowledge-mining
The mslearn-knowledge-mining repository contains lab files for Azure AI Knowledge Mining modules. It provides resources for learning and implementing knowledge mining techniques using Azure AI services. The repository is designed to help users explore and understand how to leverage AI for knowledge mining purposes within the Azure ecosystem.
nous
Nous is an open-source TypeScript platform for autonomous AI agents and LLM based workflows. It aims to automate processes, support requests, review code, assist with refactorings, and more. The platform supports various integrations, multiple LLMs/services, CLI and web interface, human-in-the-loop interactions, flexible deployment options, observability with OpenTelemetry tracing, and specific agents for code editing, software engineering, and code review. It offers advanced features like reasoning/planning, memory and function call history, hierarchical task decomposition, and control-loop function calling options. Nous is designed to be a flexible platform for the TypeScript community to expand and support different use cases and integrations.
LLMs-in-Finance
This repository focuses on the application of Large Language Models (LLMs) in the field of finance. It provides insights and knowledge about how LLMs can be utilized in various scenarios within the finance industry, particularly in generating AI agents. The repository aims to explore the potential of LLMs to enhance financial processes and decision-making through the use of advanced natural language processing techniques.
docq
Docq is a private and secure GenAI tool designed to extract knowledge from business documents, enabling users to find answers independently. It allows data to stay within organizational boundaries, supports self-hosting with various cloud vendors, and offers multi-model and multi-modal capabilities. Docq is extensible, open-source (AGPLv3), and provides commercial licensing options. The tool aims to be a turnkey solution for organizations to adopt AI innovation safely, with plans for future features like more data ingestion options and model fine-tuning.
sophia
Sophia is an open-source TypeScript platform designed for autonomous AI agents and LLM based workflows. It aims to automate processes, review code, assist with refactorings, and support various integrations. The platform offers features like advanced autonomous agents, reasoning/planning inspired by Google's Self-Discover paper, memory and function call history, adaptive iterative planning, and more. Sophia supports multiple LLMs/services, CLI and web interface, human-in-the-loop interactions, flexible deployment options, observability with OpenTelemetry tracing, and specific agents for code editing, software engineering, and code review. It provides a flexible platform for the TypeScript community to expand and support various use cases and integrations.
Upsonic
Upsonic offers a cutting-edge enterprise-ready framework for orchestrating LLM calls, agents, and computer use to complete tasks cost-effectively. It provides reliable systems, scalability, and a task-oriented structure for real-world cases. Key features include production-ready scalability, task-centric design, MCP server support, tool-calling server, computer use integration, and easy addition of custom tools. The framework supports client-server architecture and allows seamless deployment on AWS, GCP, or locally using Docker.
clearml
ClearML is an auto-magical suite of tools designed to streamline AI workflows. It includes modules for experiment management, MLOps/LLMOps, data management, model serving, and more. ClearML offers features like experiment tracking, model serving, orchestration, and automation. It supports various ML/DL frameworks and integrates with Jupyter Notebook and PyCharm for remote debugging. ClearML aims to simplify collaboration, automate processes, and enhance visibility in AI projects.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.