From 8fb326560a1cc9a0742ad0de5d0db01d1d4eba96 Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Sat, 28 Oct 2023 12:05:42 -0400 Subject: [PATCH 1/9] add AgentForge --- README.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/README.md b/README.md index 8d5904b..2cd1c7c 100644 --- a/README.md +++ b/README.md @@ -70,6 +70,20 @@ Adala: Autonomous Data (Labeling) Agent framework - [GitHub](https://github.com/HumanSignal/Adala) +## [AgentForge](https://github.com/DataBassGit/AgentForge) +A low-code framework designed for the swift creation, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures, compatible with various LLM models. + +
+ +### Description + +- Facilitates building custom agents and cognitive architectures with ease. +- Supports multiple LLM models including OpenAI, Anthropic's Claude, and local Oobabooga, allowing flexibility in running different models for different agents based on specific requirements. +- Provides customizable agent memory management and on-the-fly prompt editing for rapid development and testing. +- Comes with a database-agnostic design ensuring seamless extensibility, with straightforward integration with different databases like ChromaDB for various AI projects. + +
+ ## [AgentGPT](https://agentgpt.reworkd.ai/) A browser-based implementation of AutoGPT, accessible via a no-code platform
From da483976ef77cf14776a4d5f1e5f5a777dab5180 Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Thu, 9 Nov 2023 15:24:32 -0500 Subject: [PATCH 2/9] add ChatDev --- README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/README.md b/README.md index 2cd1c7c..89cf00e 100644 --- a/README.md +++ b/README.md @@ -609,6 +609,25 @@ Exploration of Large Scale Language Model Society](https://ghli.org/camel.pdf)
+## [ChatDev](https://github.com/OpenBMB/ChatDev) +A set of communicative agents for software development + +
+ +### Description +- ChatDev is a virtual software company driven by a multitude of intelligent agents assuming different roles such as CEO, CPO, CTO, programmer, reviewer, tester, and art designer, each represented by unique icons. +- These agents collaborate in a structured organizational environment, fulfilling the company's mission to "revolutionize the digital world through programming." They engage in functional seminars focusing on design, coding, testing, and documentation. +- ChatDev aims to provide an accessible, modular, and extensible platform based on large language models, facilitating the study of collective intelligence in a controlled setting. +- The framework allows for extensive customization, empowering users to tailor the software development process, define phases, and establish specific roles within the virtual company. +- ChatDev is committed to open-source principles, encouraging contributions from the community and sharing advancements transparently. + +### Links +- [Paper - ChatDev: Communicative Agents for Software Development](https://arxiv.org/abs/2307.07924) +- [Local demo](https://github.com/OpenBMB/ChatDev/blob/main/wiki.md#local-demo) +- [GitHub](https://github.com/OpenBMB/ChatDev) + +
+ ## [ChemCrow](https://github.com/ur-whitelab/chemcrow-public) A chemistry agent that performs tasks across synthesis, drug discovery, and materials design From b2f90bf4df04532ed177c9f0636260456039d89a Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Wed, 15 Nov 2023 05:25:45 -0500 Subject: [PATCH 3/9] add AgentVerse --- README.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/README.md b/README.md index 89cf00e..49c8da8 100644 --- a/README.md +++ b/README.md @@ -143,6 +143,20 @@ A browser-based implementation of AutoGPT, accessible via a no-code platform - [Tweet](https://twitter.com/wangchunshu/status/1702512370785100133) +## [AgentVerse](https://github.com/OpenBMB/AgentVerse) +A platform designed for deploying multiple LLM-based agents in various applications, focusing on task-solving and simulation frameworks. +
+ +### Description +- Assembles multiple agents to collaboratively accomplish tasks. +- Allows custom environments for observing or interacting with multiple agents. + +### Links +- Paper: [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://arxiv.org/abs/2308.10848) +- [GitHub](https://github.com/OpenBMB/AgentVerse) +- [Contact](agentverse2@gmail.com) + +
## [AI Legion](https://github.com/eumemic/ai-legion) A platform for agents to work together, similar in spirit to AutoGPT and Baby AGI, but written in TypeScript From 1bef2d240bdd14b95830dec587bcb7cdb5e4ea4b Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Wed, 15 Nov 2023 05:27:44 -0500 Subject: [PATCH 4/9] Update README.md --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 49c8da8..9e23b78 100644 --- a/README.md +++ b/README.md @@ -153,8 +153,10 @@ A platform designed for deploying multiple LLM-based agents in various applicati ### Links - Paper: [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://arxiv.org/abs/2308.10848) -- [GitHub](https://github.com/OpenBMB/AgentVerse) - [Contact](agentverse2@gmail.com) +- [Twitter](https://twitter.com/Agentverse71134) +- [Discord](https://discord.gg/gDAXfjMw) +- [Hugging Face](https://huggingface.co/spaces/AgentVerse/agentVerse) From ddd3c13c1cb10477e4fec5e28835ea71f08188b1 Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Wed, 15 Nov 2023 05:45:02 -0500 Subject: [PATCH 5/9] add agent4rec --- README.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/README.md b/README.md index 9e23b78..253bf04 100644 --- a/README.md +++ b/README.md @@ -70,6 +70,20 @@ Adala: Autonomous Data (Labeling) Agent framework - [GitHub](https://github.com/HumanSignal/Adala) +## [Agent4Rec](https://github.com/LehengTHU/Agent4Rec) +Agent4Rec is a recommender system simulator that utilizes 1,000 LLM-empowered generative agents. These agents, initialized from the MovieLens-1M dataset, exhibit diverse social traits and preferences. + +
+ +### Description +- These agents are initialized from the [MovieLens-1M](https://grouplens.org/datasets/movielens/1m/) dataset, embodying varied social traits and preferences. +- Each agent interacts with personalized movie recommendations in a page-by-page manner and undertakes various actions such as watching, rating, evaluating, exiting, and interviewing. + +### Links +- [Paper](https://arxiv.org/abs/2310.10108) + +
+ ## [AgentForge](https://github.com/DataBassGit/AgentForge) A low-code framework designed for the swift creation, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures, compatible with various LLM models. From b3b9a77fb82590ebeaf4b213bf9d8a24773844fb Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Thu, 16 Nov 2023 15:11:36 -0500 Subject: [PATCH 6/9] add MemGPT --- README.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/README.md b/README.md index 253bf04..841d60d 100644 --- a/README.md +++ b/README.md @@ -1246,6 +1246,22 @@ Inspired by privateGPT, allows using your own documents as an information source - [YouTube - LocalGPT: OFFLINE CHAT FOR YOUR FILES [Installation & Code Walkthrough]](https://www.youtube.com/watch?v=MlyoObdIHyo&ab_channel=PromptEngineering) +## [MemGPT](https://github.com/cpacker/MemGPT) +A system that intelligently manages different memory tiers in LLMs to effectively provide the extended context within the LLM's limited context window. + +
+ +### Description +- Chat with your data - talk to your local files or SQL database +- Create perpetual chatbots with self-editing memory + +### Links +- [Paper](https://arxiv.org/abs/2310.08560) +- [Documentation](https://memgpt.readthedocs.io/) +- [Discord](https://discord.gg/9GEQrxmVyE) +- [HuggingFace](https://huggingface.co/MemGPT) + +
## [Mentat](https://github.com/biobootloader/mentat) Mentat is the AI tool that assists you with any coding task, right from your command line. From be19dee60887889694d6473f5aa709d08b815fda Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Thu, 16 Nov 2023 16:20:32 -0500 Subject: [PATCH 7/9] add LLM Agents --- README.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/README.md b/README.md index 841d60d..7d4cef1 100644 --- a/README.md +++ b/README.md @@ -1176,6 +1176,24 @@ Plan-Validate-Solve (PVS) Agent for accurate, reliable and reproducable workflow +## [LLM Agents](https://github.com/mpaepper/llm_agents) +A minimalistic library for building agents that leverage large language models to automate tasks through a loop of commands and tool integrations. + +
+ +### Description +- Executing Python code in a REPL environment. +- Conducting searches on Google and Hacker News. +- Iterating through a cycle of Thought, Action, Observation, and New Thought based on the output of integrated tools. +- Dynamically appending new information to the prompt for informed decision-making by the agent. + +### Links + +- [GitHub](https://github.com/mpaepper/llm_agents) +- [Blog](https://www.paepper.com/blog/posts/intelligent-agents-guided-by-llms/) + +
+ ## [Local GPT](https://github.com/PromtEngineer/localGPT) LocalGPT is an open-source initiative that allows you to converse with your documents without compromising your privacy From bff17d95d345c7b43b7a6f0b75dbfabac939e983 Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Thu, 16 Nov 2023 16:24:00 -0500 Subject: [PATCH 8/9] add ReactAgent --- README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/README.md b/README.md index 7d4cef1..c3149c0 100644 --- a/README.md +++ b/README.md @@ -2701,6 +2701,25 @@ Questflow is a marketplace for autonomous AI workers with no-code. +## [ReactAgent](https://github.com/eylonmiz/react-agent) +A React.js Autonomous LLM Agent. +
+ +### Description +- Generate React Components from user stories +- Compose React Components from existing components +- Use a local design system to generate React Components +- Use React, TailwindCSS, Typescript, Radix UI, Shadcn UI +- Built with Atomic Design Principles + +### Links +- [Documentation](https://docs.reactagent.io/) +- [Demo](https://www.loom.com/share/658adb2869174e81a39a0a2cdcfec4eb) +- [Discord](https://discord.gg/57JjYNKe) +- [GitHub](https://github.com/eylonmiz/react-agent) + +
+ ## [Saga](https://saga.so/ai) A digital AI assistant, an AI-powered workspace integrating notes, tasks, and tools From 60ff45be31d0859f1566400422e252dd87955a45 Mon Sep 17 00:00:00 2001 From: JIMMY ZHAO Date: Sat, 18 Nov 2023 23:52:17 -0500 Subject: [PATCH 9/9] add JARVIS --- README.md | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/README.md b/README.md index c3149c0..4ad1034 100644 --- a/README.md +++ b/README.md @@ -1122,6 +1122,26 @@ the design of agents, chains, tools, retrieval functions, and collaborative work +## [JARVIS](https://github.com/microsoft/JARVIS) + +JARVIS is a system to connect LLMs with the ML community. + +
+ +### Description + + +- Task Planning: Using ChatGPT to analyze the requests of users to understand their intention, and disassemble them into possible solvable tasks. +- Model Selection: To solve the planned tasks, ChatGPT selects expert models hosted on Hugging Face based on their descriptions. +- Task Execution: Invokes and executes each selected model, and returns the results to ChatGPT. +- Response Generation: Use ChatGPT to integrate the prediction of all models, and generate responses. + +### Links + +- [Paper](https://arxiv.org/abs/2303.17580) + +
+ ## [Langroid](https://github.com/langroid/langroid) Multi-Agent framework for building LLM Applications.