OpenBMB (Open Lab for Big Model Base) aims to build foundation models and systems towards AGI.
78
Public repositories
146,795
Total stars
6,624
Followers
OpenBMB maintains a substantial public GitHub presence, focusing on foundation models and systems aimed at advancing artificial general intelligence (AGI). The organization develops a wide range of repositories primarily in Python, JavaScript, and TypeScript, with notable projects such as ChatDev and VoxCPM showcasing their commitment to innovation in AI technologies.
Top languages
Public repositories
ChatDev
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
MiniCPM
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
XAgent
An Autonomous LLM Agent for Complex Task Solving
ToolBench
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
UltraRAG
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
AgentVerse
🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
PilotDeck
Task-oriented AI Agent productivity platform
BMTools
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
CPM-Bee
百亿参数的中英文双语基座大模型
AgentCPM-GUI
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
EdgeClaw
EdgeClaw: Edge-Cloud Collaborative Personal AI Assistant based on OpenClaw
VisCPM
[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列
RepoAgent
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
VisRAG
Parsing-free RAG supported by VLMs
ProAgent
An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation
IoA
An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
AgentCPM
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
BMTrain
Efficient Training (including pre-training and fine-tuning) for Big Models
BMInf
Efficient Inference for Big Models
DeepThinkVLA
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
CPM-Live
Live Training for Open-source Big Models
InfiniteBench
Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718
UltraFeedback
A large-scale, fine-grained, diverse preference dataset (and models).
BMList
A List of Big Models
Eurus
No description provided for this repository.
MiniCPM-V-Apps
MiniCPM-V apps — fully offline multimodal chat on iOS / Android / HarmonyOS
UltraEval-Audio
Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。
AppCopilot
A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models
BMPrinciples
A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future
MiniCPM-Desk-Pet
a local-first desktop pet powered by MiniCPM5
ModelCenter
Efficient, Low-Resource, Distributed transformer implementation based on BMTrain
UltraEval
[ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.
CPM.cu
CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and quantization.
RAGEval
No description provided for this repository.
MiniCPM-o-Demo
Official PyTorch+CUDA Full-functional Web Demo for MiniCPM-o 4.5
ForgeTrain
No description provided for this repository.
RLPR
Extrapolating RLVR to General Domains without Verifiers
OlympiadBench
[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
WorkflowLLM
An open platform for enhancing the capability of LLMs in workflow orchestration.
ClawXRouter
No description provided for this repository.
BMCook
Model Compression for Big Models
infllmv2_cuda_impl
No description provided for this repository.
MobileCPM
A Toolkit for Running On-device Large Language Models (LLMs) in APP
Tell_Me_More
Repo for paper "Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents"
ParamMute
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
DecT
Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding
ClawXMemory
ClawXMemory: A Multi-Level Memory Plugin for OpenClaw with Long-Term Context
MoRE
[SIGIR '26] Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
ArcLight
ArcLight: A Lightweight LLM Inference Framework
MetaMem
[ACL '26] This is the code repo for our ACL '26 Findings paper "MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization"
CPO
No description provided for this repository.
UltraLink
An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
DEBATER
This is the code repo for our paper "Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search".
cpm_kernels
No description provided for this repository.
RAG-DDR
This is the code repo for the paper "RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards".
XAgent-doc
Document for XAgent.
ConsJudge
No description provided for this repository.
OpenAct
No description provided for this repository.
BMInf-demos
BMInf demos.
sglang
SGLang is a fast serving framework for large language models and vision language models.
SciCore-Mol
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
OmniEvalKit
OmniEvalKit is an evaluation framework designed for omni-modal large language models, with a focus on audio and audio-visual understanding. Based on OmniEvalKit, you can quickly reproduce benchmarks, implement your own models or datasets, and conduct fair comparisons with other open-source models. MiniCPM-o is evaluated using this framework.
DecorateLM
No description provided for this repository.
Scicore-Omics
SciCore-Omics the first tri-modal foundation model linking histology images, spatial transcriptomics, and biological language.
RaD-Agent
The official implementation of the Rational Decision-Making Agent with Internalized Utility Judgment
Omni-DuplexEval
No description provided for this repository.
General-Model-License
No description provided for this repository.
PAGER
No description provided for this repository.
AceBench
No description provided for this repository.
voxcpm2-demopage
No description provided for this repository.
SOAR-Toolkit
No description provided for this repository.
VoxCPM-demopage
Demo page for VoxCPM
Locret
No description provided for this repository.
HerculesBench
No description provided for this repository.
sparse_kernel
No description provided for this repository.
openbmb.github.io
No description provided for this repository.
Frequently asked questions
What does OpenBMB build on GitHub?
OpenBMB builds a variety of projects on GitHub, focusing on foundation models and systems for artificial general intelligence. Their notable repositories include ChatDev, VoxCPM, and MiniCPM, which contribute to advancements in AI research and applications.
Which programming languages does OpenBMB use?
OpenBMB primarily uses Python, JavaScript, TypeScript, HTML, Cuda, and C++ for their development work. These languages support their diverse range of projects, including machine learning and AI-focused applications.
Are OpenBMB's repositories public?
Yes, OpenBMB's repositories are public on GitHub. This transparency allows others in the community to access and collaborate on their projects, facilitating knowledge sharing and innovation in the field of AI.
Is this exposure intended?
Monitor OpenBMB with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account