# Cipher

> Use this tool when you need to build AI agents that learn and remember context across conversations and sessions, providing persistent memory capabilities to solve problems like knowledge retention and context switching. It takes in inputs like conversation history and project data, and outputs a shared memory space that can be accessed across multiple sessions and team members. Ideal for developers, teams, and organizations seeking to create AI workflows with continuous learning and memory retention.

Canonical page: https://skillsregistry.net/skills/byterover-cipher  
JSON: https://api.skillsregistry.net/v1/skills/byterover-cipher

## Description

Memory-powered AI agent framework built by BYTEROVER that provides persistent memory capabilities across conversations and sessions using vector databases and embeddings. The implementation supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.), vector stores (Qdrant, Milvus, in-memory), and includes specialized workspace memory for team collaboration tracking project progress, bug reports, and member activities. Features include automatic memory extraction and storage, reasoning pattern recognition, knowledge graph integration, and MCP aggregator mode that exposes memory tools alongside connected MCP servers with conflict resolution, serving developers who need AI assistants that learn and remember context across coding sessions, teams requiring shared project memory, and organizations building AI workflows that benefit from persistent knowledge retention.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-05-27

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/byterover-cipher)
- **Repository:** <https://github.com/campfirein/byterover-cli>

## 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": "byterover-cipher"
    }
  }
}
```

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