TEN Framework
An open-source framework for building autonomous AI agents that interact with the real world through tools and memory.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for TEN Framework, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
TEN Framework is an open-source modular system for building autonomous AI agents capable of reasoning, memory management, and tool usage. Designed to reflect real-world constraints, it incorporates a Thought-Emission-Norm (TEN) architecture, encouraging agents to think before acting. The framework supports open-ended planning, persistent memory storage, and tool augmentation. Developers can use TEN to experiment with agent autonomy and deploy agents that simulate complex decision-making workflows.
Key features
- autonomous agents
- memory-augmented agents
- AI planning
- open-ended tasks
- tool-use
- agent architecture
Use cases
- Creating autonomous agents that use memory and tools to solve tasks.
- Building experimental AI agents with a focus on decision-making and planning.
- Deploying agents that emulate human-like reasoning processes.
- Extending or researching agent autonomy with modular plug-ins.