bug-ops/zeph — Rust AI agent where every context token earns its place.

Description and use

**bug‑ops/zeph** is a Rust‑based AI agent that treats each context token as a first‑class citizen, combining self‑learning skills, a temporal graph memory, and cascade quality routing to deliver secure, high‑quality responses (OWASP AI security). It supports hybrid inference across multiple back‑ends—including Ollama, Claude, Gemini, OpenAI, and GGUF—while offering unified deployment via a single binary with MCP + ACP orchestration. The project targets orchestration, AI/ML, and frontend integration use cases.

Problem

bug-ops/zeph helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Early or unclear: treat as research material until maintenance, releases, docs, and issue activity are verified.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Rust AI agent where every context token earns its place. Self-learning skills, temporal graph memory, cascade quality routing, OWASP AI security. Hybrid inference: Ollama · Claude · Gemini · OpenAI · GGUF. MCP + ACP. One binary.

Source