OmniAgent

An agent capable of omni-self-evolving and dynamically hardening security

Website  •   Docs (on the way)  •   English  •   中文 

OmniAgent is an open-source self-evolving Agent framework inspired by OpenClaw. It's the only agent that implements full-dimensional self-evolution (OmniEvolve):

• Proactive Memory: A dual-path alignment mechanism based on explicit interactive feedback and implicit LLM induction enables proactive memory and self-evolving
• Skill Self-Evolution: Through automatic creation, inspection, and repair of skills during interaction, skills evolve in real-time
• Context Self-Evolution: Built on a multi-layer information stack architecture, leveraging real-time user interaction feedback and LLM summarization feedback to continuously update memory and user preferences — achieving self-evolving Personalization Context
• BrainModel Self-Evolution: Through a novel online reinforcement learning feedback loop, the BrainModel iterates dynamically during interaction

Together, these enable full-dimensional (Skill, Context, BrainModel) self-evolution of the Agent. Additionally, Hyper Harness and Deep Reflexion modules enhance system safety and task success rate:

• Hyper-Harness: An efficient, safe, and intelligent execution scaffold that provides systematic support for complex tasks
• Deep Reflexion: A dual-layer reflective architecture — real-time risk interception and failure-to-insight conversion — providing a robust guarantee for task success rate

OmniAgent V.S. OpenClaw V.S. Hermes

| Dimension | OpenClaw | Hermes | * OmniAgent | | :--- | :--- | :--- | :--- | | Skill Evolution | Static skills, no evolution | Periodic post-execution evolution (slow to take effect) | Real-time self-evolution during execution (fast to take effect) | | Skill Injection | User Message | User Message | User Message (saves 90% token cost) | | Context Evolution | Static context assembly, no evolution (weak) | Prompt-instruction-based evolution (weak) | Real-time interaction feedback + LLM summarization self-evolution (strong) | | BrainModel Evolution | Fixed model, no evolution | Fixed model, no evolution | Self-deployed model, online RL evolution | | Harness Safety | Static security scanning (bypassable) | Skill trust-level policy, static scanning (bypassable) | Tool & Skill trust-level policy + four-layer dynamic security scanning (unbypassable) | | Hyper-Harness | None (slow) | None (slow) | Dynamic multi-agent + dynamic concurrent tool execution (fast) | | Agent-Loop | ReAct single loop (low success rate) | ReAct single loop (low success rate) | Dual-layer Deep Reflexion loop (high success rate) |

Core Features

OmniEvolve (Full-Dimensional Self-Evolution): The agent evolves continuously through interaction, and safety hardens dynamically.

• Proactive Memory: Based on a multi-layer inform