Phoenix is a Hermes Agent plugin that automatically adds model routing tiers, risk guardrails, three-layer memory, self-healing, loop guarding, hallucination verification, fallback, and version-compatibility checks without modifying Hermes core.
32
No data
5
0
NOASSERTION
2026-08-02
It turns Hermes Agent into a production-hardened assistant by solving pain points such as costly over-routing, repeated errors, unchecked long tasks, and hallucination risk, all through official plugin hooks and backed by 166 automated tests and real-incident-driven safety design.
不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/记忆/自愈，官方钩子接入，不改 Hermes 核心代码
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.