proteus-ai
by alishangtian
Overview
A workflow execution engine that orchestrates multi-agent systems, integrates various tools, and provides a sandboxed environment for code execution to solve complex tasks.
Installation
docker-compose up -d --buildEnvironment Variables
- API_KEY
- MODEL_NAME
- LONG_CONTEXT_MODEL
- CONTEXT_LENGTH_THRESHOLD
- BASE_URL
- REQUEST_TIMEOUT
- MAX_RETRIES
- STREAM_CHUNK_SIZE
- SERPER_API_KEY
- FILE_WRITE_PATH
- CAIYUN_TOKEN
- CAIYUN_API_VERSION
- DATA_PATH
- LLM_RETRY_COUNT
- LLM_RETRY_DELAY
- TOOL_RETRY_COUNT
- TOOL_RETRY_DELAY
- ITERATION_RETRY_DELAY
- CRYPTO_SECRET_KEY
- REDIS_HOST
- REDIS_PORT
- REDIS_DB
- REDIS_PASSWORD
- SESSION_MODEL
- SESSION_EXPIRE_MINUTES
- SANDBOX_HOST
- SANDBOX_PORT
- SANDBOX_ERQUEST_TIMEOUT
- SANDBOX_API_KEY
- MCP_CONFIG_PATH
- WEB_CRAWLER_CACHE_TTL
- WEBCRAWLER_WAIT_SELECTORS
- WEBCRAWLER_CONTENT_SELECTORS
- BROWSER_AGENT_THREADS
- BROSWER_EXECUTABLE_PATH
- BROSWER_USER_DATA_DIR
- BROSWER_PROFILE_DIRECTORY
- BROSWER_USE_MODEL
- BROSWER_BASE_URL
- BROSWER_USE_API_KEY
- BROSWER_GENERATE_GIF
- MYSQL_HOST
- MYSQL_PORT
- MYSQL_USER
- MYSQL_PASSWORD
- MYSQL_DATABASE
- PROTEUS_CONFIG_DIR
- PROTEUS_SKILLS_DIR
- LANGFUSE_PUBLIC_KEY
- LANGFUSE_SECRET_KEY
- LANGFUSE_HOST
- LANGFUSE_ENABLED
- LANGFUSE_DEBUG
Security Notes
The primary security risk lies in the PythonExecuteNode, which sends arbitrary Python/Shell code to an external sandbox service (running in-process `exec`). Although the sandbox attempts to apply safety checks and resource limits, `exec` is notoriously difficult to fully secure against malicious code. There is a potential for sandbox escapes, resource exhaustion, or unintended side effects if a sophisticated attacker provides malicious input. Additionally, web crawling nodes and interactions with external MCP servers introduce dependencies on the security of third-party services and require robust input validation to prevent issues like SSRF or data leakage. File writing operations also require careful handling to avoid path traversal vulnerabilities.
Similar Servers
MaxKB
MaxKB (Max Knowledge Brain) is an enterprise-grade intelligent agent platform designed to lower the technical barrier and deployment costs of AI implementation, helping businesses quickly integrate mainstream large language models, build proprietary knowledge bases, and offer a progressive upgrade path from RAG to complex workflow automation and advanced agents for various application scenarios like smart customer service and office assistants.
npcpy
Core library of the NPC Toolkit that supercharges natural language processing pipelines and agent tooling. It's a flexible framework for building state-of-the-art applications and conducting novel research with LLMs. Supports multi-agent systems, fine-tuning, reinforcement learning, genetic algorithms, model ensembling, and NumPy-like operations for AI models (NPCArray). Includes a built-in Flask server for deploying agent teams via REST APIs, and multimodal generation (image, video, audio).
mcpstore
Orchestrate Microservice Context Protocol (MCP) services and adapt them for integration with various AI frameworks like LangChain, managing tools and their lifecycle.
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.