# telemem

Long-term and multimodal memory for AI agents with isolated character profiles. Runs locally or via external model providers.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 494
- Author: TeleAI-UAGI
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/TeleAI-UAGI/telemem
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/telemem

## What it does

The server gives conversational agents persistent storage across sessions. It captures conversation history and stores facts in separate profiles for each character or persona. Video pipelines split recordings into frames, generate descriptions, and populate a vector index. Agents query visual scenes directly.

TeleMem mirrors the Mem0 call interface and response payloads. It exposes 8 tools prefixed with `mcp__telemem__*`. Fully local execution runs through Qwen and FAISS so data remains on the host machine. Connecting external model providers requires an `OPENAI_API_KEY` environment variable. The runtime launches directly with `uvx`.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `OPENAI_API_KEY`, `TELEMEM_CONFIG`, `TELEMEM_DEFAULT_USER_ID` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env OPENAI_API_KEY=<OPENAI_API_KEY> --env TELEMEM_CONFIG=<TELEMEM_CONFIG> --env TELEMEM_DEFAULT_USER_ID=<TELEMEM_DEFAULT_USER_ID> --transport stdio telemem -- uvx telemem
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from telemem <command>

### Codex

**Platform CLI**
```bash
codex mcp add telemem --env OPENAI_API_KEY=<OPENAI_API_KEY> --env TELEMEM_CONFIG=<TELEMEM_CONFIG> --env TELEMEM_DEFAULT_USER_ID=<TELEMEM_DEFAULT_USER_ID> -- uvx telemem
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from telemem <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "telemem": {
            "command": "uvx",
            "args": [
                "telemem"
            ],
            "env": {
                "OPENAI_API_KEY": "<OPENAI_API_KEY>",
                "TELEMEM_CONFIG": "<TELEMEM_CONFIG>",
                "TELEMEM_DEFAULT_USER_ID": "<TELEMEM_DEFAULT_USER_ID>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from telemem <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "telemem": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "telemem"
            ],
            "env": {
                "OPENAI_API_KEY": "<OPENAI_API_KEY>",
                "TELEMEM_CONFIG": "<TELEMEM_CONFIG>",
                "TELEMEM_DEFAULT_USER_ID": "<TELEMEM_DEFAULT_USER_ID>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from telemem <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e OPENAI_API_KEY=<OPENAI_API_KEY> -e TELEMEM_CONFIG=<TELEMEM_CONFIG> -e TELEMEM_DEFAULT_USER_ID=<TELEMEM_DEFAULT_USER_ID> telemem uvx telemem
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from telemem <command>

## When to use it
- isolate memory records for individual characters and NPCs
- store multi-turn conversation context across sessions
- index and search video frame captions alongside text
- replace Mem0 without rewriting existing memory data shapes

## Example prompts
- Search long-term memory for user database preferences mentioned earlier.
- Store a memory entry for character Alice regarding her favorite beverage.
- Look up saved video segments showing server setup errors.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md