Stars
Open-source release accompanying Gao et al. 2025
🎯 A unified personal data hub built on MCP that allows AI assistants to access your digital life from Steam, YouTube, Bilibili and more platforms for truly personalized interactions.
ICML'2022: Black-Box Tuning for Language-Model-as-a-Service & EMNLP'2022: BBTv2: Towards a Gradient-Free Future with Large Language Models
A unified evaluation framework for large language models
An Automatic Prompt Optimization Framework for Large Language Models
Task-Aware Agent-driven Prompt Optimization Framework
Original Implementation of Prompt Tuning from Lester, et al, 2021
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Model Context Protocol Servers
Code and data for NAACL 2025 paper "IHEval: Evaluating Language Models on Following the Instruction Hierarchy"
A modular graph-based Retrieval-Augmented Generation (RAG) system
Train your AI self, amplify you, bridge the world
[ICML 2025] Official implementation for paper "A Comprehensive Analysis on LLM-based Node Classification Algorithms"
Designing Multi-Agent Systems with Zero Supervision
Published as a conference paper at EMNLP (Findings) 2025
[ICLR 2025] "GraphRouter: A Graph-based Router for LLM Selections", Tao Feng, Yanzhen Shen, Jiaxuan You
DSPy: The framework for programming—not prompting—language models
NIPS 24: Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
The code for NeurIPS 2025 paper "A-MEM: Agentic Memory for LLM Agents"
[EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents