Transformershuggingface/transformers
A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
PythonDeep learningNLPSpeech168.1k updated today
LLM and agent libraries
58 libraries, 48 updated this year
Tools for applications built on large language models. Hugging Face Transformers loads and fine-tunes open models, Haystack and txtai assemble retrieval-augmented generation pipelines, and vector databases such as Milvus, Qdrant, Chroma and Weaviate store the embeddings those pipelines search.
58 libraries
PythonDeep learningNLPSpeechmilvusmilvus-io/milvus
Milvus is open source vector database for production AI, written in Go and C++, scalable and blazing fast for billions of embedding vectors.
MLOps
46.5k updated 1d ago
Qdrantqdrant/qdrant
Qdrant is open source vector similarity search engine with extended filtering support, written in Rust.
Deep learningMLOps
35.2k updated 1d ago
Chromachroma-core/chroma
Open-source search and retrieval database for AI applications. Vector, full-text, regex, and metadata search. Self-host or Cloud available.
MLOps
29.6k updated 1d ago
MLFlowmlflow/mlflow
Platform to manage the ML lifecycle, including experimentation, reproducibility and deployment. Framework and language agnostic, take a look at all the built-in integrations.
MLOps
28.5k updated today
Haystackdeepset-ai/haystack
A framework for building industrial-strength applications with Transformer models and LLMs.
PythonNLP26.8k updated today
promptfoopromptfoo/promptfoo
Open-source LLM evaluation and red teaming framework. Test prompts, models, agents, and RAG pipelines. Run adversarial attacks (jailbreaks, prompt injection) and integrate security testing into CI/CD.
MLOps
26.4k updated today
Opikcomet-ml/opik
Open source engineering platform to debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. (Source Code)
General22.9k updated today
CometLLMcomet-ml/comet-llm
Track, log, visualize and evaluate your LLM prompts and prompt chains.
PythonNLP22.9k updated today
Weaviatesemi-technologies/weaviate
Weaviate is an open source vector search engine and vector database. Weaviate uses machine learning to vectorize and store data, and to find answers to natural language queries. With Weaviate you can also bring your custom ML models to production scale.
NLPMLOps
16.9k updated today
13k updated 2d ago
PhoenixArize-ai/phoenix
Uncover insights, surface problems, monitor and fine tune your generative LLM, CV and tabular models.
C++General12k updated today
Kedroquantumblacklabs/kedro
Kedro is a data and development workflow framework that implements best practices for data pipelines with an eye towards productionizing machine learning models.
MLOps
11k updated 1d ago
RunAnywhereRunanywhereAI/runanywhere-sdks
Open-source SDK for running LLMs and multimodal models on-device across iOS, Android, and cross-platform apps.
MLOps
10.3k updated 3d ago
PyODyzhao062/pyod
> Python Outlier Detection, comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. Featured for Advanced models, including Neural Networks/Deep Learning and Outlier Ensembles.
PythonGeneralDeep learning10.1k updated 12d ago
PraisonAIMervinPraison/PraisonAI
Production-ready Multi-AI Agents framework with self-reflection. Fastest agent instantiation (3.77μs), 100+ LLM support via LiteLLM, MCP integration, agentic workflows (route/parallel/loop/repeat), built-in memory, Python & JS SDKs.
MLOps
9.3k updated today
Hubactiveloopai/Hub
Fastest unstructured dataset management for TensorFlow/PyTorch. Stream & version-control data. Store even petabyte-scale data in a single numpy-like array on the cloud accessible on any machine. Visit activeloop.ai for more info.
PythonGeneralDeep learningVisionMLOps9.3k updated 5mo ago
BentoMLbentoml/bentoml
Toolkit for package and deploy machine learning models for serving in production
PythonGeneralDeep learningMLOps8.9k updated 1d ago
Speedsternebuly-ai/nebullvm
Automatically apply SOTA optimization techniques to achieve the maximum inference speed-up on your hardware.
C++GeneralDeep learning8.3k updated 2y ago
Evidentlyevidentlyai/evidently
Interactive reports to analyze machine learning models during validation or production monitoring.
PythonGeneralMLOps8k updated 25d ago
ClearMLclearml/clearml
Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution.
PythonGeneralDeep learningMLOps6.9k updated 1d ago
shimmyMichael-A-Kuykendall/shimmy
Python-free Rust inference server for NLP models with OpenAI API compatibility and hot model swapping.
RustNLP6k updated 5d ago
Infinityinfiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast vector and full-text search. Developed using C++20
Deep learningMLOps
4.7k updated 7d ago
AgentfieldAgent-Field/agentfield
Open source Kubernetes-style control plane for deploying AI agents as distributed microservices, with built-in service discovery, durable workflows, and observability.
MLOps
2.6k updated today
Agentic Context Enginekayba-ai/agentic-context-engine
In-context learning framework that allows agents to learn from execution feedback.
C++General2.6k updated 1mo ago
Future AGIfuture-agi/future-agi
Open-source, self-hostable platform to evaluate, trace, and guard LLM applications and AI agents.
PythonGeneral2.2k updated today
MCP Memory Servicedoobidoo/mcp-memory-service
Universal memory service with semantic search, autonomous consolidation, and multi-client support for AI applications.
PythonGeneral2k updated today
nndeploynndeploy/nndeploy
An Easy-to-Use and High-Performance AI deployment framework.
C++GeneralDeep learning1.9k updated 2mo ago
NobodyWhonobodywho-ooo/nobodywho
The simplest way to run an LLM locally. Supports tool calling and grammar constrained sampling.
PythonNLP1.6k updated today
Agentic Radarsplx-ai/agentic-radar
Open-source CLI security scanner for agentic workflows. Scans your workflow’s source code, detects vulnerabilities, and generates an interactive visualization along with a detailed security report. Supports LangGraph, CrewAI, n8n, OpenAI Agents, and more.
Data & vizMLOps
1.1k updated 11mo ago
Aqueductaqueducthq/aqueduct
Aqueduct enables you to easily define, run, and manage AI & ML tasks on any cloud infrastructure.
MLOps
518 updated 3y ago
Localforgerockbite/localforge
Is an open source on-prem AI coding autonomous assistant that lives inside your repo, edits and tests files at SSD speed. Think Claude Code but with UI. plug in any LLM (OpenAI, Gemini, Ollama, etc.) and let it work for you.
MLOps
401 updated 1y ago
Upginiupgini/upgini
Free automated data & feature enrichment library for machine learning - automatically searches through thousands of ready-to-use features from public and community shared data sources and enriches your training dataset with only the accuracy improving features.
PythonGeneralMLOps358 updated 4d ago
VeritasGraphbibinprathap/VeritasGraph
Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.
PythonNLP325 updated today
Flamavortico/flama
Ignite your models into blazing-fast machine learning APIs with a modern framework.
PythonData & viz304 updated 11d ago
Agentic Signalcode-forge-temple/agentic-signal
Visual AI agent workflow automation platform with local LLM integration. Build intelligent workflows using drag-and-drop, no cloud required.
MLOps
179 updated 26d ago
tiny-audioalexkroman/tiny-audio
Minimal, hackable PyTorch/Hugging Face codebase for training LLM-based speech recognition by connecting a frozen pretrained speech encoder to a pretrained LLM through a small trained projector, with word timestamps, speaker diarization and a free course.
PythonSpeech175 updated 1d ago
Neurolinkjuspay/neurolink
Enterprise-grade LLM integration framework for building production-ready AI applications with built-in hallucination prevention, RAG, and MCP support.
PythonGeneral157 updated today
113 updated 3y ago
fennpyfenn/fenn
A simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.
PythonDeep learning81 updated 2mo ago
Neofuzzx-tabdeveloping/neofuzz
Blazing fast, lightweight and customizable fuzzy and semantic text search in Python with fuzzywuzzy/thefuzz compatible API.
PythonNLP52 updated 1y ago
Local LLM NPCcode-forge-temple/local-llm-npc
Godot 4.x asset that enables NPCs to interact with players using local LLMs for structured, offline-first learning conversations in games.
MLOps
51 updated 8mo ago
ClawMoatdarfaz/clawmoat
Open-source runtime security scanner for AI agents. Detects prompt injection, jailbreak, PII leakage, memory poisoning, and tool misuse. Zero deps, MIT licensed.
MLOps
45 updated 2mo ago
HyperAgencyvuics/h9y
Agentic AI operating system (h9y.ai) that replaces brittle/fragmented automations with long-lived, self-improving systems. Open-source, self-hosted/cloud, visual workflow, omni-channel, decentralized, extensible.
MLOps
37 updated 4d ago
notorchariannamethod/notorch
Neural networks framework in pure C: training and inference, no dependencies.
CGeneralDeep learning29 updated 4d ago
Keras GPT Copilotfabprezja/keras-gpt-copilot
A python package that integrates an LLM copilot inside the keras model development workflow.
LuaGeneralDeep learning28 updated 3y ago
deepseek-v4-flash-0731-in-cshyringo/deepseek-v4-flash-0731-in-c
A native C CPU inference engine for running the 284B-A13B DeepSeek-V4-Flash-0731 on one laptop, reaching up to 1.12 token/s on tested hardware while streaming the 167 GB checkpoint from disk with a tested 8 GB memory path and no GPU or Python.
CGeneral27 updated 1mo ago
shimmytokMichael-A-Kuykendall/shimmytok
Pure-Rust tokenizer for GGUF models, compatible with llama.cpp tokenization.
RustNLP25 updated 6d ago
autobatcherdoublewordai/autobatcher
Drop-in AsyncOpenAI replacement that transparently batches requests via the Batch API for cheaper LLM inference.
PythonGeneral24 updated today
qwen3.8-27b-in-cshyringo/qwen3.8-27b-in-c
A native C inference engine for running Qwen3.8-27B locally on a single laptop CPU, with direct GGUF loading and a tested 8 GB memory path.
CGeneral22 updated 1mo ago