Understand the project
Practical overview
When it fits
Use it when an agent project needs an integrated framework for construction, tool access and runtime controls rather than only a model SDK or prompt layer.
Who it is for
- Python developers building custom AI agents
- Teams creating tool-connected agent applications
- Developers needing memory, security and tracing around agent runtimes
- Builders designing multi-tenant agent systems
Documented uses
- Build agents and the tools they use
- Create reasoning and context-engineering workflows
- Connect agents to tools through MCP or an HTTP tool server
- Add persistent memory, security scanning, caching and tracing
- Develop governed and multi-tenant agent applications
Before you choose
Requirements & limits
The repository is public, identifies an Apache-2.0 license, and provides a pip installation example. The quick-start materials indicate Python 3.10+.
- Python is the primary implementation language.
- The framework combines agent construction and runtime services in one package.
- MCP and HTTP tool-server configuration is shown in the quick-start example.
- Memory, guardrails, caching and tracing are configured as agent options.
- The evidence names OpenAI, Anthropic, Gemini, Ollama and LangChain-based models as supported model contexts.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 3 October 2026
- Original website title
- promptise-com/Foundry · Official homepage title · retained in its source language