# saige

> saige — urmzd-saige. Use this tool when you need to streamline AI agent management and integrate multiple providers into a single interface. Saige solves the problem of fragmented AI workflows by unifying access to knowledge graphs, RAG pipelines, and AI providers like Ollama, OpenAI, Anthropic, and Google. It accepts various inputs, including git repositories, and outputs streamlined AI workflows through its SDK, CLI, and MCP server.

Canonical page: https://skillsregistry.net/skills/urmzd-saige  
JSON: https://api.skillsregistry.net/v1/skills/urmzd-saige

## Description

Go SDK, CLI and MCP server for streaming agents, tools, memory, retrieval and evaluations, with pluggable model providers and durable execution.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-11-08

## Source

- **Source listing:** [GitHub](https://github.com/urmzd/saige)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "urmzd-saige"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/urmzd-saige` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/urmzd-saige/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt