If you like Emacs, why not make Emacs your harness?
https://github.com/karthink/gptel
In Pi's Minimalism Is Its Advantagekarthink
gptel
Emacs Lisp2023–2026
karthink / gptel
gptel
A simple, extensible LLM client for Emacs
39Distinct people
43Mentions
1Explicit recommenders
3.6KGitHub stars
What to know before exploring
What it is
A simple, extensible LLM client for Emacs
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
gptel in emacs does this. You can run the same prompt against different models in separate emacs windows (local or via api w/ keys) at the same time to compare outputs. I…
peterb used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- lizqwerscott/mcp.el · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year43 dated mentions
Observed mentions: 2023-03-22 04:09:50 UTC to 2026-08-05 06:52:46 UTC.
* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 8 | 1 | 7 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 15 | 1 | 14 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 15 | 0 | 15 |
| 2026 (partial) | 2026-01-01 00:00:00 UTC | 2027-01-01 00:00:00 UTC | 5 | 0 | 5 |
From the project README
An excerpt from the repository, fetched Nov 13, 2026.
Read the project’s introduction
gptel: A simple LLM client for Emacs
gptel is a simple Large Language Model chat client for Emacs, with support for multiple models and backends. It works in the spirit of Emacs, available at any time and uniformly in any buffer.
General usage: (YouTube Demo, 18 min)
Advanced usage: (YouTube Demo, 28 min)
intro-demo.mp4
intro-demo-2.mp4
In-place usage
gptel-rewrite-demo-1.mp4
Tool use
gptel-tool-use-filesystem-confirm-demo-2.mp4
gptel-tool-use-feed-search-demo.mp4
See also this youtube demo (2 minutes) by Armin Darvish.
Interact with LLMs from anywhere in Emacs (any buffer, shell, minibuffer, wherever).
LLM responses are in Markdown or Org markup.
Supports multiple independent conversations, one-off ad hoc interactions and anything in between.
Supports tool-use to equip LLMs with agentic capabilities.
Supports Model Context Protocol (MCP) integration using mcp.el.
Supports multi-modal input (include images, documents).
Supports “reasoning” content in LLM responses.
Save chats as regular Markdown/Org/Text files and resume them later.
Edit your previous prompts or LLM responses when continuing a conversation. These will be fed back to the model.
Supports introspection, so you can see exactly what will be sent. Inspect and modify queries before sending them.
Pause multi-stage requests at an intermediate stage and resume them later.
Don’t like gptel’s workflow? Use it to create your own for any supported model/backend with a simple API.
gptel uses Curl if available, but falls back to the built-in url-retrieve to work without external dependencies.
Contents
Installation
Straight
Manual
Doom Emacs
Spacemacs
Setup
OpenAI
Other LLM backends
(Optional) Securing API keys with =authinfo=
(Optional) Reading API keys from environment variables
OpenAI (ChatGPT plus/pro subscription)
Azure
GPT4All
Ollama
Open WebUI
Gemini
Llama.cpp or Llamafile
Kagi (FastGPT & Summarizer)
together.ai
Anyscale
Perplexity
Anthropic (Claude)
Groq
Mistral Le Chat
OpenRouter
PrivateGPT
DeepSeek
Sambanova (Deepseek)
Cerebras
Novita AI
xAI
AI/ML API
GitHub CopilotChat
AWS Bedrock
Moonshot (Kimi)
Usage
In any buffer:
In a dedicated chat buffer:
Including media (images, documents or plain-text files) with requests
Save and restore your chat sessions
Setting options (backend, model, request parameters, system prompts and more)
Include more context with requests
Handle “reasoning” content
Tool use
Defining gptel tools
Selecting tools
LLM tool collections
Model Context Protocol (MCP) integration
Rewrite, refactor or fill in a region
Extra Org mode conveniences
Introspection (examine, debug or modify requests)
FAQ
Chat buffer UI
I want the window to scroll automatically as the response is inserted
I want the cursor to move to the next prompt after the response is inserted
I want to change the formatting of the prompt and LLM response
How does gptel distinguish between user prompts and LLM responses?
Transient menu behavior
I want to set gptel options but only for this buffer
I want the transient menu options to be saved so I only need to set them once
Using the transient menu leaves behind extra windows
Can I change the transient menu key bindings?
(Doom Emacs) Sending a query from the gptel menu fails because of a key conflict with Org mode
Miscellaneous
I want to use gptel in a way that’s not supported by gptel-send or the options menu
(ChatGPT) I get the error “(HTTP/2 429) You exceeded your current quota”
Why another LLM client?
Additional Configuration
Option presets
Applying presets to requests automatically
Alternatives
Packages using gptel
Acknowledgments
Installation
Note: gptel requires Transient 0.7.8 or higher. Transient is a built-in package and Emacs does not update it by default. Ensure that package-install-upgrade-built-in is true, or update Transient manually.
Release version: M-x package-install ⏎ gptel in Emacs.
Development snapshot: Add MELPA or NonGNU-devel ELPA to your list of package sources, then install with M-x package-install ⏎ gptel.
Optional: Install markdown-mode.
Straight
(straight-use-package 'gptel)
Manual
Note: gptel requires Transient 0.7.8 or higher. Transient is a built-in package and Emacs does not update it by default. Ensure that package-install-upgrade-built-in is true, or update Transient manually.
Clone or download this repository and run M-x package-install-file⏎ on the repository directory.
Doom Emacs
In packages.el
(package! gptel :recipe (:nonrecursive t))
In config.el
(use-package! gptel
:config
(setq! gptel-api-key "your key"))
“your key” can be the API key itself, or (safer) a function that returns the key. Setting gptel-api-key is optional, you will be asked for a key if it’s not found.
Alternatively, Doom Emacs provides a built-in :tools llm module powered by gptel. Enable it in your init.el in the doom! block:
(doom! :tools llm)
This installs gptel with preconfigured keybindings (<leader> o l), m
Read the full README on GitHubWhat Hacker News says
43 sourcesInteresting. Tnx.
In case anyone else wondered about using gptel to edit thinking (eg vis Qwen3.6's `preserve thinking`), [1] explains:
> In a multi-turn request, from the time you run `gptel-send`, everything the LLM sends is passed back to it [...during tool calls...] includes multiple reasoning blocks. [...But...] subsequent gptel-send calls read their input from the buffer contents (or active region, etc), so the reasoning blocks in the buffer will not [] be sent as "reasoning_content".
But in org mode, those are apparently `#+being_reasoning` blocks (`gptel-include-reasoning`?), so editable thought might be an easy addition?
A caution, fwiw, that any llms which respond with interleaved content and reasoning blocks, currently only work when not streaming, and fixing that is non-trivial.[also 1]
[1] https://github.com/karthink/gptel/is
Read the rest
I use KVM/QEMU on Linux. I have a set of scripts that I use to create a new directory with a VM project and that also installs a debian image for the VM. I have an ./pull_from_vm and ./push_to_vm that I use to pull and push the git code to and from the vm. As well as a ./claude to start claude on the vm and a ./emacs to initialize and start emacs on the vm after syncing my local .spacemacs directory to the vm (I like this because of customized emacs muscle memory and because I worry that emacs can execute arbitrary code if I use it to ssh to the VM client from my host).
I try not to run LLM's directly on my own host. The only exception I have is that I do use https://github.com/karthink/gptel on my own machine, because it is just too damn useful. I hope I don't self own myself with that someday.
In Let's discuss sandbox isolationA year ago I added memory to my Emacs helper [0]. It was just lines in org-mode. I thought it was so stupid. It worked though. Sort of.
That's how a trillion dollar company also does it, turns out.
0: https://github.com/karthink/gptel
In Ex-GitHub CEO launches a new developer platform for AI agentsActually, this is a copy of the older version of interface with a few lines dropped. I failed to generate a decent gif last night, will add a screenshot.
Admittedly, while working on this, I did consult my LLMs advisor through gptel(https://github.com/karthink/gptel) with a few custom tools setup, which I cannot recommend enough.
In Show HN: Micropolis/SimCity Clone in Emacs LispI use gptel[0] with my denote[1] notes, and a tool that can search/retrieve tags/grep/create notes (in a specific sub folder). It's been good enough as a memory for me.
0: https://github.com/karthink/gptel
1: https://protesilaos.com/emacs/denote
In Show HN: Stop Claude Code from forgetting everythingI've been looking for this too. It seems to me as though all the ide's are trying to sell the llms as a service or trying to lock you in by downloading llms through their ide. I have been downloading llm's from huggingface as gguf files and would like to use those downloads (and running them through https://github.com/oobabooga/text-generation-webui). It is possible to run those llms as a local api using something like llama-cpp-python (https://pypi.org/project/llama-cpp-python/) and would prefer to use something like that method. Zed (https://zed.dev/), which is now available on windows might be able to do it, but i'd rather use something (foss) that doesn't have a pricing model (the development focus will always be upon those who pay). tbh i'm getting a bit sick of changing ide's, as their support changes, and really would prefer not to
Read the rest
use (microsoft) visual studio code which seems to be cornering the market. Starting to think i'm going to try to learn emacs, with https://github.com/karthink/gptel looking as if it would meet my needs.
The beauty of Emacs though is that it puts the user in full control. There is nothing in the world stopping anyone from modifying anything in Emacs (at least on the Elisp layer), hence packages like this.
VS Code on the other hand is designed to fracture [1]. MS can and has given proprietary API access to their blessed tools, forcing others to go through their much less capable extension API, hence the plethora of vscode forks. Even if you had the most motivated, excited group of people wanting to work on the latest and greatest LLM interactions with VS code, they would most likely be forced to fork. On the other hand, it just takes one motivated Elisp dev to implement whatever they want and make any external package they want integrate with it.
Also, I think the derision from the Emacs community may be a bit overblown. I'm constantly see
Read the rest
ing AI/LLM related plugins appearing for Emacs and they tend to get decent traction (e.g. https://github.com/karthink/gptel).
[1] https://ghuntley.com/fracture/
gptel in emacs does this. You can run the same prompt against different models in separate emacs windows (local or via api w/ keys) at the same time to compare outputs. I highly recommended it. https://github.com/karthink/gptel
In Ollama's new appInstall the latest emacs release and you will be able to do `M-x eglot` – this by default knows about language servers for many programming languages, so if you e.g. do this while in a C++ file in some project, it will start clang or ccls (whatever's in PATH); the language server will then be active for all files in that project and you can use `M-.` (xref-find-definitions), `M-,` (xref-go-back), `M-?` (xref-find-references). Try also `M-x eglot-code-actions` on a symbol to see all available actions (renaming, add imports, refactoring etc.; what you get here depends on the language server).
I also use this plugin https://github.com/minad/consult which has the command `consult-ripgrep`, very useful for e.g. looking up all occurrences of the symbol at point (and text navigation across multiple files).
For "AI", start with https://github.com
Read the rest
/karthink/gptel/ (its README lists alternative packages, as you can see there is no lack of llm support in emacs, both chat, "agents" and more specific use-cases)
> Here my problem with this: I don't want to be jumping an editor/IDE every 6 months, learning new key bindings and even more importantly, getting used to a completely new look.
You're basically advocating for GNU Emacs: https://github.com/karthink/gptel
In Kiro: A new agentic IDEI've recently started using gptel and really like it, but the main feature I've wanted that it's missing is inline code completion (like GitHub Copilot). I saw that this was previously being [worked on](https://github.com/karthink/gptel/discussions/206) in the gptel repo but was paused, so I decided to give it a shot and made `gptel-autocomplete` (disclosure: most of it was written by Claude Sonnet 4).
It took some experimenting to get decent code completion results from a chat API that isn't built for standalone code completion responses, but I found some techniques that worked well (details in the README).
In Gptel-autocomplete: Inline code completion in Emacs using gptel> I would be interested especially in Emacs integrations.
gptel can use MCP server tools in Emacs by integrating with the mcp.el package, here's a demo: https://i.imgur.com/WTuhPuk.mp4.
mcp.el: https://github.com/lizqwerscott/mcp.el
Relevant gptel README section (you'll have to unfold the details block):
https://github.com/karthink/gptel?tab=readme-ov-file#model-c...
In MCP explained without hype or fluffSounds similar to gptel[1] for Emacs. It provides a solid foundation for more complex compositions like gptel-aibo[2] or mcp.el [3].
Yours is the full agent, though... Nice.
[1] https://github.com/karthink/gptel
[2] https://github.com/dolmens/gptel-aibo
[3] https://github.com/lizqwerscott/mcp.el
In Zed: High-performance AI Code Editor`gptel` supports perplexity, among many others.
https://github.com/karthink/gptel
In Perplexingly Book-Learned EmacsShowing the 15 most recent of 43 sources. Enable JavaScript to search and browse every indexed mention.