toolsSource-backedReview first Safety ✓ Privacy ✓

Upsonic

Python framework for autonomous AI agents, traditional agents, custom tools, MCP tools, prebuilt autonomous agents, workspace-restricted file and shell operations, E2B sandbox execution, OCR, document processing, and vector storage integrations.

by Upsonic·added 2026-06-18·

CLI

HarnessCLI

Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

Upsonic autonomous agents can use file operations, shell operations, custom tools, MCP tools, document processing, OCR, vector stores, and external model providers; scope every capability before using private data.
The README says file and shell operations are restricted to the configured workspace and dangerous commands are blocked. Verify that boundary locally before relying on it for sensitive repositories or production systems.
MCP tools can connect agents to external data sources and services; review server provenance, tool names, read/write behavior, credentials, and approval flow before enabling them.
OCR and document loaders can parse invoices, PDFs, Office files, HTML, Markdown, JSON, YAML, XML, and other documents depending on installed extras; handle extracted text as sensitive.
Optional sandbox, vector database, storage, model, embedding, and telemetry dependencies can introduce additional network calls, costs, and retention behavior.

Privacy notes

Prompts, task descriptions, workspace files, shell output, custom tool inputs, MCP payloads, OCR text, document chunks, embeddings, vector records, model responses, traces, and logs may contain sensitive data.
Configured model providers, MCP servers, OCR services, E2B sandboxes, vector databases, storage backends, and observability or telemetry integrations may receive task data depending on selected extras.
The package dependency list includes Sentry SDK with OpenTelemetry support; review runtime telemetry configuration before production use.
Keep provider keys, sandbox tokens, vector database credentials, storage URLs, workspace paths, extracted document text, and generated agent outputs out of public prompts, logs, issues, and examples.

Prerequisites

Python 3.10 or newer.
An isolated virtual environment managed with uv, pip, or similar tooling.
Model provider credentials for the model route the agent will use.
A reviewed workspace directory for autonomous file and shell operations.
Optional E2B sandbox, MCP server, OCR engine, vector database, or storage backend credentials if those extras are enabled.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 15 minutes
Difficulty: intermediate

Tool listing metadata

Website: https://docs.upsonic.ai
Pricing: free
Disclosure: editorial
Application category: DeveloperApplication
Operating system: Cross-platform

Full copyable content

uv pip install upsonic

About this resource

Overview

Upsonic is a Python framework for building autonomous and traditional AI agents. It supports autonomous agents with configured workspaces, custom tools, MCP tools, prebuilt autonomous agents, OCR and document processing, sandbox providers, vector database integrations, storage extras, and model-provider extras.

This entry is relevant for Upsonic, Upsonic agent framework, Upsonic MCP tools, Upsonic autonomous agents, Python autonomous agent framework, OpenClaw agent framework, MCP agent framework, Upsonic OCR, E2B sandbox agent, and prebuilt autonomous agents searches.

Install

The README documents installing the PyPI package with uv:

uv pip install upsonic

For project-based development, install it into a virtual environment and add only the extras you need, such as MCP, OCR, vector databases, storage, model providers, or document loaders.

Core Capabilities

Area	Upsonic Coverage
Autonomous Agents	`AutonomousAgent` with workspace-scoped tasks
Traditional Agents	`Agent` and `Task` APIs for conventional tool-using agents
Custom Tools	Python functions exposed as agent tools through decorators
MCP Tools	Optional MCP extra for connecting agents to external MCP services
Prebuilt Agents	Community-contributed prebuilt autonomous agents with skills, prompts, and first messages
Sandboxes	E2B sandbox provider path for isolated cloud execution environments
OCR	Unified OCR interface with EasyOCR, RapidOCR, Tesseract, PaddleOCR, DeepSeek OCR, and DeepSeek via Ollama listed in the README
Documents	Optional loaders for CSV, Docling, DOCX, HTML, JSON, Markdown, PDF, text, XML, YAML, and related formats
Storage	Optional SQLite, Redis, Postgres, Mongo, Mem0, and vector database integrations
Models	Optional model-provider extras for Anthropic, Azure, Bedrock, Cohere, Google, Groq, Mistral, OpenAI, xAI, and related providers

MCP and OpenClaw Fit

Upsonic directly targets autonomous-agent builders and is source-tagged for MCP, Model Context Protocol, OpenClaw, Claude, computer use, RAG, and autonomous agents. The README positions it for building autonomous agents similar to OpenClaw and Claude Cowork, while also supporting more traditional agent systems.

Use it when you want a Python framework with a small agent API and optional MCP tooling, rather than a full desktop client or visual workflow platform.

Use Cases

Build a Python autonomous agent that works inside a specific workspace.
Add custom Python functions as reviewed tools.
Connect MCP tools to an agent workflow.
Start from a prebuilt autonomous agent and adapt its prompt, skill, and first message.
Run OCR over invoices, PDFs, or scanned documents before agent processing.
Add vector storage or document loaders for RAG workflows.
Evaluate E2B sandbox execution for safer autonomous work.
Compare Upsonic with OpenClaw, Hermes Agent, Qwen-Agent, AG2, CAMEL-AI, LangGraph, CrewAI, and mcp-agent.

Source Review

Verified on 2026-06-18:

GitHub reports Upsonic/Upsonic as an MIT-licensed repository with active development, 7,800+ stars, and latest release v0.77.3.
The README describes Upsonic as a Python framework for building autonomous agents like OpenClaw and Claude Cowork, as well as traditional agent systems.
The README documents installation through uv pip install upsonic.
The README shows AutonomousAgent and Task usage with a configured workspace and states that file and shell operations are restricted to that workspace while path traversal and dangerous commands are blocked.
The README documents custom tools, MCP tools, prebuilt autonomous agents, E2B sandbox provider guidance, OCR and document processing, and supported OCR engines.
pyproject.toml declares the upsonic package at version 0.77.3, Python >=3.10, MIT license, core dependencies, and optional extras for MCP, storage, vector databases, models, embeddings, OCR, and document loaders.
PyPI reports upsonic version 0.77.3.

Safety and Privacy

The main safety question is not whether Upsonic can run an agent; it is what workspace, tools, MCP servers, OCR engines, model providers, storage backends, and sandboxes the agent is allowed to use. Start with a disposable workspace, small tool set, and non-production credentials.

For document and RAG workflows, extracted text and embeddings can be more sensitive than the original file names suggest. Define retention, deletion, model-provider routing, and vector-store access rules before indexing private documents.

Duplicate Check

Checked current content/tools/, content/mcp/, content/agents/, content/skills/, guides, collections, README output, open pull requests, and repository-wide content for Upsonic/Upsonic, Upsonic, Upsonic agent framework, Upsonic MCP tools, Upsonic autonomous agents, Python autonomous agent framework, OpenClaw agent framework, MCP agent framework, Upsonic OCR, E2B sandbox agent, and prebuilt autonomous agents. No dedicated Upsonic tools entry, exact source URL duplicate, target file, or open duplicate PR was found.

#upsonic #ai-agents #autonomous-agents #python #mcp #agent-framework #openclaw #ocr #rag #sandboxes

Source citations

Add this badge to your README

Show that Upsonic is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/tools/upsonic.svg)](https://heyclau.de/entry/tools/upsonic)

How it compares

Upsonic side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	Upsonic Python framework for autonomous AI agents, traditional agents, custom tools, MCP tools, prebuilt autonomous agents, workspace-restricted file and shell operations, E2B sandbox execution, OCR, document processing, and vector storage integrations. Open dossier	CAMEL-AI CAMEL Open-source Python multi-agent framework for building agent societies, role-playing agents, stateful ChatAgent workflows, RAG agents, synthetic data generation, MCP-enabled use cases, and research-scale agent experiments. Open dossier	AG2 Agent Framework Open-source Python AgentOS and multi-agent framework, evolved from AutoGen, for building conversable agents, group chats, swarms, human-in-the-loop workflows, tool use, RAG, code execution, and provider-backed agent systems. Open dossier	AgentScope Apache-2.0 Python framework for building visible, controllable, production AI agents and multi-agent services with event streaming, permission controls, workspaces, sandbox backends, middleware, MCP support, Mem0 memory, agent teams, and multi-tenant multi-session serving. Open dossier
Trust
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	Upsonic	CAMEL-AI CAMEL	AG2 Agent Framework	AgentScope
Category	tools	tools	tools	tools
Source	source-backed	source-backed	source-backed	source-backed
Author	Upsonic	CAMEL-AI	AG2	AgentScope
Added	2026-06-18	2026-06-18	2026-06-18	2026-06-18
Platforms	CLI	CLI	CLI	CLI
Source repo	—	—	—	—
Safety notes	✓Upsonic autonomous agents can use file operations, shell operations, custom tools, MCP tools, document processing, OCR, vector stores, and external model providers; scope every capability before using private data. The README says file and shell operations are restricted to the configured workspace and dangerous commands are blocked. Verify that boundary locally before relying on it for sensitive repositories or production systems. MCP tools can connect agents to external data sources and services; review server provenance, tool names, read/write behavior, credentials, and approval flow before enabling them. OCR and document loaders can parse invoices, PDFs, Office files, HTML, Markdown, JSON, YAML, XML, and other documents depending on installed extras; handle extracted text as sensitive. Optional sandbox, vector database, storage, model, embedding, and telemetry dependencies can introduce additional network calls, costs, and retention behavior.	✓CAMEL agents can coordinate multi-step tasks, call tools, use web/search integrations, connect to MCP examples, and run with provider credentials; review tool permissions before giving agents write access or account access. Large-scale agent societies and role-playing workflows can generate high volumes of model calls, tool calls, logs, synthetic data, and intermediate artifacts; set budgets, rate limits, and stop conditions before long runs. RAG, document, media, browser, communication, and data-tool extras may access local files, third-party APIs, vector stores, notebooks, or generated datasets; isolate experiments from production systems. CAMEL examples include MCP-oriented use cases, but MCP does not make connected tools safe by default. Scope server permissions, credentials, filesystem access, and approval gates separately. Do not treat generated code, generated datasets, citations, research summaries, or multi-agent decisions as verified until they have been reviewed against source data and policy requirements.	✓AG2 agents can converse, call tools, execute code, use retrieval systems, run browser workflows, and coordinate group chats; require explicit permissions and approval gates for high-impact actions. The upstream install docs and examples commonly involve provider credentials; keep API keys, config files, notebooks, and `.env` files out of commits and support tickets. Code execution, Docker, Jupyter, browser-use, and RAG extras can touch local files, network services, notebooks, databases, and external websites; scope them tightly before granting agent access. Multi-agent conversations can continue through nested chats, swarms, group chats, and custom reply handlers; define termination, escalation, retry, and human takeover behavior. Track the release roadmap before upgrading because deprecations and the v1.0 transition can change which APIs should be used for new work.	✓AgentScope examples can give agents Bash, file-read, file-write, edit, search, MCP, and custom tools. Scope tool permissions and approval rules before connecting a real project or account. The README demonstrates permission control, including bypass mode. Do not use bypass-style behavior on production systems, sensitive files, paid APIs, cloud resources, or unreviewed tool chains without compensating controls. Workspace support can run tools and code through local, Docker, or E2B backends; review filesystem mounts, network access, secrets, resource limits, and cleanup behavior. Agent teams, background tasks, and multi-session services can continue work after the initial request; define cancellation, timeout, wakeup, escalation, and audit behavior. Mem0 memory, Redis-backed sessions, MCP configuration, OpenTelemetry, FastAPI services, and model-provider integrations all need version pinning, credential isolation, and security review before production use.
Privacy notes	✓Prompts, task descriptions, workspace files, shell output, custom tool inputs, MCP payloads, OCR text, document chunks, embeddings, vector records, model responses, traces, and logs may contain sensitive data. Configured model providers, MCP servers, OCR services, E2B sandboxes, vector databases, storage backends, and observability or telemetry integrations may receive task data depending on selected extras. The package dependency list includes Sentry SDK with OpenTelemetry support; review runtime telemetry configuration before production use. Keep provider keys, sandbox tokens, vector database credentials, storage URLs, workspace paths, extracted document text, and generated agent outputs out of public prompts, logs, issues, and examples.	✓Prompts, model responses, agent messages, tool arguments, tool outputs, retrieved documents, search results, logs, generated datasets, traces, and errors may include user or workspace data. Model providers, search providers, MCP servers, vector stores, web tools, document parsers, browser tools, and observability integrations may receive data from CAMEL workflows. Keep provider API keys, OAuth tokens, MCP server credentials, vector database URLs, generated logs, and synthetic datasets out of committed examples, screenshots, public issues, and shared notebooks. If `CAMEL_MODEL_LOG_ENABLED` or other logging/tracing integrations are enabled, review request/response logs and model configuration logs before sharing or retaining them.	✓Prompts, messages, tool arguments, tool outputs, code snippets, notebook state, retrieved documents, vector-store contents, provider responses, traces, and execution logs may contain sensitive user or workspace data. Do not expose secrets, API keys, private file paths, customer records, internal documents, database rows, or raw exceptions through agent messages, logs, notebooks, screenshots, or public examples. Provider extras and retrieval integrations can route data through OpenAI, Anthropic, Google, AWS, local model servers, databases, vector stores, browser automation, or other third-party services. If AG2 is used for code execution or browser automation, define which files, domains, credentials, downloads, screenshots, and logs can be read or retained.	✓AgentScope workflows can process prompts, model responses, tool arguments, tool outputs, workspace files, code, credentials accidentally present in context, event streams, web UI state, logs, traces, memory records, session state, and tenant metadata. Long-term memory through Mem0 and multi-session service storage can persist user facts, intermediate outputs, retrieved context, and tool results beyond a single conversation. Docker, E2B, MCP servers, model providers, Redis, OpenTelemetry exporters, FastAPI deployments, and web UI integrations may send or store data outside the local Python process depending on configuration. Do not expose private prompts, API keys, unpublished code, customer data, tenant identifiers, session transcripts, or workspace artifacts in public issues, examples, screenshots, logs, or generated reports.
Prerequisites	Python 3.10 or newer. An isolated virtual environment managed with uv, pip, or similar tooling. Model provider credentials for the model route the agent will use. A reviewed workspace directory for autonomous file and shell operations.	Python 3.10 through 3.14 and an isolated Python environment managed with pip, uv, or another package manager. A configured model provider such as OpenAI or another provider supported by the selected CAMEL model route. Provider API keys, search credentials, vector database credentials, or tool-specific secrets stored outside source control. Optional extras for web tools, document tools, RAG, model platforms, storage backends, dev tools, or research tools only when those integrations are required.	Python 3.10 or newer and a Python environment managed with pip, uv, or another package manager. Model provider credentials for the selected provider extra, such as OpenAI, Anthropic, Gemini, Bedrock, Mistral, Ollama, Groq, xAI, or another supported route. A secrets strategy for provider keys, AG2 config files, `.env` files, notebooks, and example `OAI_CONFIG_LIST`-style credentials. A reviewed execution boundary for code execution, Docker, Jupyter, browser-use, RAG, retrieval, database, and external tool extras.	Python 3.11 or newer and an isolated Python environment managed with pip, uv, or another package manager. Model provider credentials for the selected model backend, such as DashScope, OpenAI-compatible APIs, Anthropic, Gemini, Ollama, xAI, or another supported route. A permission policy for tools such as Bash, Grep, Glob, Read, Write, Edit, MCP tools, custom functions, and long-running background tasks. A workspace isolation decision for local, Docker, E2B, or other sandbox backends before running code or file tools.
Install	`uv pip install upsonic`	`pip install camel-ai`	`pip install 'ag2[openai]'`	`pip install agentscope`
Config	—	—	—	—
Citations	Source repositorygithub.com 2026-06-19T03:16:13+00:00 Documentationdocs.upsonic.ai	Source repositorygithub.com 2026-06-19T03:16:13+00:00 Documentationdocs.camel-ai.org	Source repositorygithub.com 2026-06-19T03:16:13+00:00 Documentationdocs.ag2.ai	Source repositorygithub.com 2026-06-19T03:16:13+00:00 Documentationdocs.agentscope.io
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Featured in

Best list: Best RAG frameworks

Signals

Loading live community signals…