gptme
gptme copied to clipboard
ErikBjare
A CLI and web UI to interact with LLMs in a Chat-style interface, with code execution capabilities and other tools.
pip install as per README and then `OPENAI_API_KEY=sk-lol OPENAI_BASE_URL=http://127.0.0.1:8080/v1 gptme-serve` Web UI at http://127.0.0.1:5000/ shows: ``` Not Found The requested URL was not found on the server. If you entered...
Related issues: - https://github.com/ErikBjare/gptme/issues/61 - https://github.com/ErikBjare/gptme/issues/75 Questions - Should these subagents be ran in the background? Waking the main agent when done? From my notes I should add a function...
If no argument is given, it should automatically start a new conversation, and not list past conversations (but there should be a CLI option + /command to list them).
Seen this before, this is just one particular case I stumbled upon: ``` YELLOW = \"\033[93m\" ``` With the error: ``` Failed to parse TOML: Invalid character '0' in string...
Just something I had in my working tree and needed to stash somewhere. Probably far from usable. Edit: there's a better way to do this in gptengineer.app
Aider has this: > Use Meta-ENTER (Esc+ENTER in some environments) to enter multiline chat messages. Or enter { alone on the first line to start a multiline message and }...
After the Cognition Labs announcement of Devin yesterday (https://twitter.com/cognition_labs/status/1767548763134964000), which was very reminiscent of gptme, I noticed that they have this "Planner" module which has a `Current focus: ...` and...
Since the OpenAI API now has vision in beta, and we could use LLaVa locally. Might be a lot of work, or might be super easy. Question is, what would...
Tools currently need to be registered in `gptme/tools/__init__.py`. It'd be nice if we didn't have to enumerate them and enable/disable them in config or with a CLI param. So that...