GFgfortaine·Nov 7, 2024Submission
3 points · Open discussionmicrosoft
autogen
Python2023–2024
microsoft / autogen
autogen
A programming framework for agentic AI
15Distinct people
16Mentions
0Explicit recommenders
61.8KGitHub stars
What to know before exploring
What it is
A programming framework for agentic AI
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 1:49:46 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 month16 dated mentions
Observed mentions: 2023-09-26 11:55:40 UTC to 2024-11-07 01:45:24 UTC.
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 |
|---|---|---|---|---|---|
| Sep 2023 | 2023-09-01 00:00:00 UTC | 2023-10-01 00:00:00 UTC | 1 | 0 | 1 |
| Oct 2023 | 2023-10-01 00:00:00 UTC | 2023-11-01 00:00:00 UTC | 7 | 2 | 5 |
| Nov 2023 | 2023-11-01 00:00:00 UTC | 2023-12-01 00:00:00 UTC | 3 | 0 | 3 |
| Dec 2023 | 2023-12-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2024 | 2024-01-01 00:00:00 UTC | 2024-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2024 | 2024-02-01 00:00:00 UTC | 2024-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 2024 | 2024-03-01 00:00:00 UTC | 2024-04-01 00:00:00 UTC | 2 | 0 | 2 |
| Apr 2024 | 2024-04-01 00:00:00 UTC | 2024-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2024 | 2024-05-01 00:00:00 UTC | 2024-06-01 00:00:00 UTC | 0 | 0 | 0 |
| Jun 2024 | 2024-06-01 00:00:00 UTC | 2024-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2024 | 2024-07-01 00:00:00 UTC | 2024-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2024 | 2024-08-01 00:00:00 UTC | 2024-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2024 | 2024-09-01 00:00:00 UTC | 2024-10-01 00:00:00 UTC | 2 | 1 | 1 |
| Oct 2024 | 2024-10-01 00:00:00 UTC | 2024-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2024 | 2024-11-01 00:00:00 UTC | 2024-12-01 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
16 sourcesHave you tried trying an agentic approach, i.e. https://github.com/microsoft/autogen
In LLMs struggle to explain themselvesI am still playing around with the project but FYI, the parsing for the github repo URL at https://glide.agenticlabs.com/ will fail if there's a trailing slash in the repo link i.e. https://github.com/microsoft/autogen/ won't work but https://github.com/microsoft/autogen will.
In Launch HN: Glide (YC W24) – AI-assisted technical design docsEach of those is great, and more sophisticated strategies are being developed all the time: incorporating static analysis at inference time to ensure code is more than just syntactically correct [0]; to multi-LLM call agent-based frameworks [1]; decomposing hard tasks into many "easier" LLM tasks [2]; analyzing internal activations to identify potential hallucinations [3]; activation steering to control generations [4]; and "Language Model Arithmetic" to compose biases for style, vocab, etc [5].
But each also either requires tight integration with an LLM inference/serving engine (to access low-level internals of an inference engine); or adds a lot of overhead (many individual LLM calls) if they don't have tight integration.
The AI Controller Interface is creating an abstraction layer that exposes the low-level primitives so that all the a
Read the rest
bove strategies can be implemented without each one needing to dive into the internals of every LLM engine. AICI doesn't support all the necessary primitives for all of these yet (e.g., we don't know what the right way is to represent internal activations); and not everything will end up fitting in a WASM module anyway.
Its a start at thinking about a new layer in the inference stack
[0] https://arxiv.org/abs/2306.10763
[1] https://github.com/microsoft/autogen
[2] https://arxiv.org/abs/2305.14292
[3] https://arxiv.org/abs/2312.02073
[4] https://arxiv.org/abs/2308.10248
[5] https://arxiv.org/abs/2311.14479
When I saw this, I figured it was a clear step back from simply using plugins in the main ChatGPT view. It's basically plugins, but with extra prompting and you can only use one at a time.
But if you look at projects like Autogen ( https://github.com/microsoft/autogen ), you see one master agent coordinating other agents which have a narrower scope. But you have to create the prompts for the agents yourself.
This GPTs setup will crowd-source a ton of data on creating agents which serve a single task. Then they can train a model that's very good at creating other agents. Altman nods to this immediately after the GPTs feature is shown, repeating that OpenAI does not train on API usage.
Prediction: next year's dev day, which Altman hints will make today's conference look "quaint" by comparison, will basically be an app built around the autog
Read the rest
en concept, but which you can spin up using very simple prompts to complete very complex tasks. Probably on top of a mixture of GPT 4 & 5.
I haven't tried any of them but there's semantic-kernel and autogen by Microsoft, and Haystack.
https://github.com/microsoft/semantic-kernel
https://github.com/microsoft/autogen
https://haystack.deepset.ai/
In New: LangChain templates – fastest way to build a production-ready LLM appAutoGen (https://github.com/microsoft/autogen) is orthogonal: it's designed for agents to converse with each other.
The original comparison to LangChain from Microsoft was Guidance (https://github.com/guidance-ai/guidance) which appears to have shifted development a bit. I haven't had much experience with it but from the examples it still seems like needless overhead.
In New: LangChain templates – fastest way to build a production-ready LLM appNot using neighbour, but Autogen has a multi-agent pipeline where if a question is not answered by top K docs, the agent can request "UPDATE CONTEXT" and pull the next set of results.
See example 5 here:
https://github.com/microsoft/autogen/blob/main/notebook/agen...
In Show HN: Demystifying Advanced RAG PipelinesHere's that group research notebook: https://github.com/microsoft/autogen/blob/main/notebook/agen...
And the chess one: https://github.com/microsoft/autogen/blob/main/notebook/agen...
In Autogen: Enable next-gen large language model applications>The ChatGPT "AI" isn't an autonomous thinker performing its own actions based on reasoning of what's fed to it.
Yes it is. Or it very well could be. Agency is trivial to implement in LLMs.
https://github.com/microsoft/autogen
https://arxiv.org/abs/2307.07924
The intelligence and tool access of the LLM in question is the only thing stopping things from being particularly dangerous (to humanity).
In GPT-4 vision prompt injectionAutogen: Enable next-gen large language model applications
163 points · Open discussionThe AutoGen Framework Developed by Microsoft is Powerful; a Multi-Agent Framework Making Customization of a Series of Work Tasks Easy. https://github.com/microsoft/autogen
As an example, if we want to implement a web scraper program to collect and save webpage images, handing this task over to ChatGPT would result in a string of executable code but with potential problems such as execution errors or missing dependencies. This requires multiple conversations with ChatGPT to create a complete program. Of course, we could set up a more complex prompt to instruct ChatGPT to execute code plugins, but with the AutoGen framework, it can be simplified to just a few lines of code:
1) Define an Assistant Agent that solves problems.
2) Define a UserProxy Agent that substitutes human inquiries and executes programs on the local machine.
Neither of th
Read the rest
ese agents requires a prompt. When we hand over the web scraper task to UserProxy, it understands the task, inquires of Assistant how to proceed, and following Assistant's instructions, UserProxy installs dependencies locally, creates files, executes code, and reports detailed error messages to Assistant if any problems arise. This process repeats until the final result is obtained. When the task is completed, the target image is saved to the local disk.
AutoGen has a wide range of capabilities, and best practices can be found in the project's notebook: https://github.com/microsoft/autogen/tree/main/notebook
P.S. To ensure safety, it is recommended to perform program execution in a Docker environment. UserProxy has a code_execution_config configuration, which can be set to True for use_docker. Additionally, there is a human_input_mode parameter that can be set to NEVER to automate the entire process or to wait for human input, allowing for people to participate in the task execution process and avoid mistakes.
AutoGen: A Multi-Agent Framework for Streamlining Task Customization
1 points · Open discussionCorresponding Google Colab notebook: https://colab.research.google.com/github/githubpradeep/noteb...
Autogen repo: https://github.com/microsoft/autogen
In Making memes with Autogen AI (open source LLM agent framework) [video]Showing the 15 most recent of 16 sources. Enable JavaScript to search and browse every indexed mention.