moresearch

tokencost

Easy token price estimates for 400+ LLMs. TokenOps.

go-libp2p-pubsub

The PubSub implementation for go-libp2p

langgraph

llama2.c

Inference Llama 2 in one file of pure C

llamafile-rag-example

llm-cost-estimator

A simple cost estimator for batch text generation with OpenAI LLMs

experiments

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

moresearch/langgraph

moresearch/autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

moresearch/go-libp2p-pubsub

The PubSub implementation for go-libp2p

moresearch/llama2.c

Inference Llama 2 in one file of pure C

moresearch/llamafile-rag-example

moresearch/MetaGPT

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

moresearch/ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

moresearch/thinkgpt

Agent techniques to augment your LLM and push it beyong its limits

moresearch/airllm

AirLLM 70B inference with single 4GB GPU

moresearch/Algorithmic-Behavioral-Economics-Lab

moresearch/ArxivDigest

ArXiv Digest and Personalized Recommendations using Large Language Models

moresearch/auction-arena

Source code for our paper: "Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena"

moresearch/chat.petals.ml

Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client

moresearch/ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

moresearch/cli

GitHub’s official command line tool

moresearch/CMAT

Small is Beautiful

moresearch/devgpt

moresearch/experiments

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

moresearch/generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

moresearch/modwm

mo's own dwm custimization

moresearch/moresearch.github.io

moresearch/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

moresearch/nanogpt.mlflow

Model based on Andre Karpathy's tutorial. Integrated with MLFlow, for better analysis and optimisation. (MacBook Air M1)

moresearch/OD-SWE-bench

Enhanced fork of SWE-bench, tailored for OpenDevin's ecosystem.

moresearch/ollama-chat

ChatGPT-like chat bot webapp built with React, Express and TailwindCSS using ollama.ai as backend.

moresearch/OpenDevin

🐚 OpenDevin: Code Less, Make More

moresearch/py-libp2p

The Python implementation of the libp2p networking stack 🐍 [under development]

moresearch/real-time-embeddings

Real time embeddings with Bytewax, unstructured and redis for retrieval augmented generation

moresearch/SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

moresearch/SWE-bench

SWE-Bench: Can Language Models Resolve Real-world Github Issues?