# agentic-rag

> agentic-rag — phense-agentic-rag. Use this tool when you need to retain and retrieve knowledge from previous interactions, enabling persistent memory for AI agents like Claude Code. It solves the problem of knowledge loss between sessions by storing information in a local database with advanced search capabilities. With automatic session mining and knowledge graph curation, it provides a powerful interface for inputting and outputting session knowledge, making it ideal for applications requiring contextual understanding and information retention.

Canonical page: https://skillsregistry.net/skills/phense-agentic-rag  
JSON: https://api.skillsregistry.net/v1/skills/phense-agentic-rag

## Description

Enables persistent, searchable memory for Claude Code by storing session knowledge in a local PostgreSQL + pgvector database, with hybrid vector and full-text search, automatic session mining, and knowledge graph curation.

## Trust

- **Trust score (0–1):** 0.21
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/puhowqr2cj)
- **Repository:** <https://github.com/phense/agentic-rag>

## 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": "phense-agentic-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/phense-agentic-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/phense-agentic-rag/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