evanho

WrenAI

🚀 Open-source SQL AI Agent for Text-to-SQL. Make Text2SQL Easy! 🙌

ai-agent-roadmap

Explore the latest AI Agent Framework!

GTBench

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

aphrodite-engine

Large-scale LLM inference engine

Stirling-PDF

#1 Locally hosted web application that allows you to perform various operations on PDF files

memgraph

Open-source graph database, tuned for dynamic analytics environments. Easy to adopt, scale and own.

Scrapegraph-ai

Python scraper based on AI

openflow

Scalable, secure workflow solution

anything-llm

The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.

Memary

The Open Source Memory Layer For Autonomous Agents

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

sammo

A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Few-shot-NL2SQL-with-prompting

PET-SQL

PET-SQL: A Prompt-enhanced Two-stage Text-to-SQL Framework with Cross-consistency

graindb

jsonrepair

Repair invalid JSON documents

awesome-reasoning

a curated list of data for reasoning ai

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

local-rag

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

chainlit

Build Conversational AI in minutes ⚡️

taipy

Turns Data and AI algorithms into production-ready web applications in no time.

CausalInferenceIntro

Causal Inference for the Brave and True的中文翻译版。全部代码基于Python，适用于计量经济学、量化社会学、策略评估等领域。英文版原作者：Matheus Facure

LLMRoofline

Compare different hardware platforms via the Roofline Model for LLM inference tasks.

strictjson

A Strict JSON Framework for LLM Outputs

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

query_transformations

promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.