Authorization notice. Talk with Me is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Remote script. Tool calls run on the MCP servers you list, so only add servers you trust and that you have checked.
Who it is forA developer who wants personas to act on live data, such as reading a web page or querying a database, through servers they run or trust.
The problemA plain chat model cannot read current web pages or query your own data sources.
The outcomePersonas with tool calls enabled can use configured MCP tools during a reply, and the app can show those tool calls.
What you need first
- Python 3.10 or newer
- A locally running llama.cpp server with an OpenAI-compatible API (the README mentions the --api flag)
- A clone of the TalkWithMe repository and its dependencies installed from requirements.txt
Steps
- Start one or more MCP servers that expose the Streamable HTTP transport.
- Add each server to the mcp.servers list in settings.yaml, and keep max_tool_iterations at the default of 8 unless you need a change.
- Restart the app, because the mcp section is only read on startup.
- Open the Personas editor and set allow_tool_calls to true for the persona that should use tools.
- Run
uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload, then ask the persona to fetch a web page and check the tool call in the chat.
Prompt for your agent
Use the TalkWithMe repo to configure MCP server <mcp-server-url> in settings.yaml, enable tool calls for the persona <persona-name>, and restart the app. Ask the persona to use the tool on <test-input> and report the tool call shown in the chat. Verify that the tool result appears in the reply.
Caveat. The README says the mcp section has no UI and must be edited in settings.yaml, with a restart after each change.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page