# SafeFlo

> SafeFlo — g1ngercy-safeflo. Use this tool when you need to orchestrate AI agents locally and transparently, solving problems related to secure and reliable coordination of multiple agents. SafeFlo provides a platform with memory, planning, and coordination capabilities, accepting inputs from git and outputting coordinated agent actions. It is ideal for use cases requiring autonomous and predictable AI agent management without network dependencies.

Canonical page: https://skillsregistry.net/skills/g1ngercy-safeflo  
JSON: https://api.skillsregistry.net/v1/skills/g1ngercy-safeflo

## Description

Local MCP server giving Claude Code persistent agent memory: hybrid FTS5 + vector search, episodic/semantic/procedural lifecycle, no network calls, no install scripts.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/G1ngercy/SafeFlo)

## 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": "g1ngercy-safeflo"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/g1ngercy-safeflo` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/g1ngercy-safeflo/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