AutoGPT
Requestly
AutoGPT | Requestly | |
---|---|---|
180 | 34 | |
161,405 | 1,758 | |
0.7% | 4.7% | |
9.9 | 9.8 | |
4 days ago | 4 days ago | |
JavaScript | JavaScript | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AutoGPT
- Accessible AI for Everyone
-
AGI has, in some sense, been achieved: Tell me why I am wrong
Define agency. Does AutoGPT or BabyAGI fit the definition?
-
The Emergence of Autonomous Agents
This leap is evident in projects like BabyAGI and AutoGPT, showcasing how such agents can prioritize and execute tasks based on a pre-defined objective and the results of previous actions, such as sales prospecting or ordering pizza.
- An experimental open-source attempt to make GPT-4 autonomous
-
[Long read] Deep dive into AutoGPT: A comprehensive and in-depth step-by-step guide to how it works
A system and a user message are constructed from the task given by the user in code and passed to the LLM as input.
-
1000 Member Celebration and FAQ
A: How much do you know? If you can easily read code (in this example Python, but this will still benefit anyone who can read code), you should check out Auto-GPT. If you are looking to explore different options, check out this doc on AI Agents.
-
Agents: An Open-source Framework for Autonomous Language Agents - AIWaves Inc 2023
Also I think most agents I have seen have implemented some form of long-short term memory. Why does it say autogpt doesnt support it? https://github.com/Significant-Gravitas/Auto-GPT/tree/master/autogpts/autogpt/autogpt/memory
-
MetaGPT: The Next Evolution or Just More Hype?
In my newest experiment, I try out MetaGPT, which is supposed to be better than AutoGPT according to MetaGPT's paper.
-
List of Awesome AI Agents like AutoGPT and BabyAGI / Many open-source Agents with code included!
In my opinion the most interesting Agents: Auto-GPT Github: https://github.com/Significant-Gravitas/Auto-GPT BabyAGI Github: https://github.com/yoheinakajima/babyagi Voyager Github: https://github.com/MineDojo/Voyager / Paper: https://arxiv.org/abs/2305.16291 I would also add: ChemCrow: Augmenting large-language models with chemistry tools Github: https://github.com/ur-whitelab/chemcrow-public/ Paper: https://arxiv.org/abs/2304.05376
-
We've released Auto-GPT v0.4.5!
Check out the new Re-Arch README and ARCHITECTURE_NOTES.
Requestly
-
π₯π₯ Our awesome OSS friends π
Requestly- Makes frontend development cycle 10x faster with API Client, Mock Server, Intercept & Modify HTTP Requests and Session Replays.
-
Tell HN: The popular Chrome extension ModHeader is injecting ads into searches
[1]: https://github.com/requestly/requestly/
-
Tell HN: Service Workers === Browser Background Tasks
If you want to intercept and modify a incoming json response for some specific url pattern, would a service worker be a good way to do so?
To illustrate, assume I frequently browse example.com and want to trick my browser into thinking that I have "favorited" every post. It's trivial to write a for loop that iterates over response.json and sets `is_favorite = true`. But it's not as clear to me where this script should ideally live in order to have the logic always executed before the response is made available to the site.
Your comment made me think about whether I can replace my overkill solution (https://requestly.io/) with something lightweight.
-
Way or viewing network requests?
If you prefer open-source there is Requestly and Toolkit.
-
Is it a viable option to use a database to populate data used in a chrome extension?
If you don't know Requestly, It is an open-source Chrome/Firefox/Edge extension to intercept & modify HTTP requests & responses. One of the popular features is to modify HTTP headers. We also offer workspaces for easy collaboration between team members.
-
Open-Source alternative to Charles Proxy & Telerik Fiddler
Hey, open-source community, This is Sachin, One of the core maintainers of Requestly - An open-source alternative to Charles Proxy & Telerik Fiddler. In case you donβt know about Charles Proxy & Fiddler, both of them are two decades-old products used widely to Inspect & Modify HTTP traffic in web & mobile apps.
-
All browsers - is it possible to replace specific image url with another?
In /etc/hosts file you put only IP addresses and hostnames, i.e. 127.0.0.1 cdn.cloudflare.steamstatic.com. Then you have to set up a web server on localhost port 80 and put your image at http://localhost/steamcommunity/public/images/apps/753/1d0167575d746dadea7706685c0f3c01c8aeb6d8.jpg as well as other files from https://cdn.cloudflare.steamstatic.com. You also have to keep the URLs updated when they change upstream. It's not worth it. Better use a local proxy server like mitmproxy or requestly.
-
Userscripts: Is there a way to intercept all HTTP requests/responses so that I can modify them before they're sent/received?
Requestly founder here. You are essentially looking for Requestly - A Chrome/Firefox browser extension to Intercept & Modify HTTP requests. Using Requestly you can actually do the following things
-
Software Developer Mac Apps
For development/Debugging: 1. VSCode - Got used to the key bindings and integrated terminal, so now it's really hard to switch 2. Requestly - For easily setting up local debugging environments. I am less of a UI guy, so this allows me to use the live UI of a deployed site, and redirect whichever request I want to play with to my local server. 3. Wireshark - To better understand a network protocol.
-
General discussion thread
[0]: https://requestly.io
What are some alternatives?
langchain - β‘ Building applications with LLMs through composability β‘ [Moved to: https://github.com/langchain-ai/langchain]
Proxyman - Modern. Native. Delightful Web Debugging Proxy for macOS, iOS, and Android β‘οΈ
gpt4all - gpt4all: run open-source LLMs anywhere
frida-interception-and-unpinning - Frida scripts to directly MitM all HTTPS traffic from a target mobile application
llama.cpp - LLM inference in C/C++
httptoolkit - HTTP Toolkit is a beautiful & open-source tool for debugging, testing and building with HTTP(S) on Windows, Linux & Mac :tada: Open an issue here to give feedback or ask for help.
Auto-Vicuna
orbstack - Fast, light, simple Docker containers & Linux machines for macOS
JARVIS - JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
rrweb - record and replay the web
SuperAGI - <β‘οΈ> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
mitmproxy - An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.