#Llmops

Showing 60 of 199 repositories tagged #llmops, ranked by stars

pathwaycom
pathwaycom
llm-app

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. ๐ŸณDocker-friendly.โšกAlways in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

Score
100
โ˜… 59.1k โ‘‚ 1.4k โ€”
Jupyter Notebook
BerriAI
BerriAI
litellm

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, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Score
100
โ˜… 53.2k โ‘‚ 9.6k +42/day
Python
langfuse
langfuse
langfuse

๐Ÿชข Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. ๐ŸŠYC W23

Score
99
โ˜… 30.9k โ‘‚ 3.2k +57/day
TypeScript
ComposioHQ
ComposioHQ
composio

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

Score
93
โ˜… 29.2k โ‘‚ 4.6k +7/day
TypeScript
mlflow
mlflow
mlflow

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Score
97
โ˜… 27.0k โ‘‚ 6.0k +5/day
Python
liguodongiot
liguodongiot
llm-action

ๆœฌ้กน็›ฎๆ—จๅœจๅˆ†ไบซๅคงๆจกๅž‹็›ธๅ…ณๆŠ€ๆœฏๅŽŸ็†ไปฅๅŠๅฎžๆˆ˜็ป้ชŒ๏ผˆๅคงๆจกๅž‹ๅทฅ็จ‹ๅŒ–ใ€ๅคงๆจกๅž‹ๅบ”็”จ่ฝๅœฐ๏ผ‰

Score
98
โ˜… 24.7k โ‘‚ 2.8k +31/day
HTML
promptfoo
promptfoo
promptfoo

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

Score
97
โ˜… 23.1k โ‘‚ 2.1k +112/day
TypeScript
jina-ai
jina-ai
serve

โ˜๏ธ Build multimodal AI applications with cloud-native stack

Score
28
โ˜… 21.9k โ‘‚ 2.2k +1/day
Python
comet-ml
comet-ml
opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Score
90
โ˜… 20.5k โ‘‚ 1.6k +62/day
Python
TransformerOptimus
TransformerOptimus
SuperAGI

<โšก๏ธ> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

Score
24
โ˜… 17.6k โ‘‚ 2.2k +10/day
Python
raga-ai-hub
raga-ai-hub
RagaAI-Catalyst

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

Score
83
โ˜… 16.1k โ‘‚ 3.6k โ€”
Python
vibrantlabsai
vibrantlabsai
ragas

Supercharge Your LLM Application Evaluations ๐Ÿš€

Score
66
โ˜… 14.7k โ‘‚ 1.5k +60/day
Python
bentoml
bentoml
OpenLLM

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Score
79
โ˜… 12.4k โ‘‚ 822 +6/day
Python
Portkey-AI
Portkey-AI
gateway

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Score
96
โ˜… 12.4k โ‘‚ 1.2k +46/day
TypeScript
tensorzero
tensorzero
tensorzero

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

Score
76
โ˜… 11.7k โ‘‚ 947 โ€”
Rust
dataelement
dataelement
bisheng

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

Score
86
โ˜… 11.5k โ‘‚ 1.9k โ€”
TypeScript
Arize-ai
Arize-ai
phoenix

AI Observability & Evaluation

Score
69
โ˜… 10.5k โ‘‚ 974 +5/day
Python
Netflix
Netflix
metaflow

Build, Manage and Deploy AI/ML Systems

Score
72
โ˜… 10.2k โ‘‚ 1.3k +1/day
Python
bentoml
bentoml
BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Score
62
โ˜… 8.7k โ‘‚ 981 +7/day
Python
0xPlaygrounds
0xPlaygrounds
rig

โš™๏ธ๐Ÿฆ€ Build modular and scalable LLM Applications in Rust

Score
100
โ˜… 7.9k โ‘‚ 876 +9/day
Rust
evidentlyai
evidentlyai
evidently

Evidently is โ€‹โ€‹an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

Score
100
โ˜… 7.7k โ‘‚ 875 +16/day
Jupyter Notebook
traceloop
traceloop
openllmetry

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Score
59
โ˜… 7.3k โ‘‚ 1.0k +14/day
Python
clearml
clearml
clearml

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

Score
52
โ˜… 6.8k โ‘‚ 781 +4/day
Python
katanemo
katanemo
plano

Plano is an AI-native proxy and data plane for agentic apps โ€” with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

Score
83
โ˜… 6.7k โ‘‚ 444 +71/day
Rust
GoogleCloudPlatform
GoogleCloudPlatform
agent-starter-pack

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

Score
55
โ˜… 6.5k โ‘‚ 1.5k +4/day
Python
maximhq
maximhq
bifrost

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 ยตs overhead at 5k RPS.

Score
100
โ˜… 6.4k โ‘‚ 868 +14/day
Go
Helicone
Helicone
helicone

๐ŸงŠ Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 ๐Ÿ“

Score
95
โ˜… 5.9k โ‘‚ 623 +13/day
TypeScript
coze-dev
coze-dev
coze-loop

Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

Score
80
โ˜… 5.6k โ‘‚ 773 +12/day
Go
Giskard-AI
Giskard-AI
giskard-oss

๐Ÿข Open-Source Evaluation & Testing library for LLM Agents

Score
45
โ˜… 5.5k โ‘‚ 482 +5/day
Python
zenml-io
zenml-io
zenml

ZenML ๐Ÿ™: One AI Platform from Pipelines to Agents. https://zenml.io.

Score
48
โ˜… 5.5k โ‘‚ 634 โ€”
Python
superduper-io
superduper-io
superduper

Superduper: End-to-end framework for building custom AI applications and agents.

Score
21
โ˜… 5.3k โ‘‚ 542 +2/day
Python
PacktPublishing
PacktPublishing
LLM-Engineers-Handbook

The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

Score
94
โ˜… 5.2k โ‘‚ 1.2k +27/day
Python
tencentmusic
tencentmusic
cube-studio

cube studioๅผ€ๆบไบ‘ๅŽŸ็”Ÿไธ€็ซ™ๅผๆœบๅ™จๅญฆไน /ๆทฑๅบฆๅญฆไน /ๅคงๆจกๅž‹AIๅนณๅฐ๏ผŒmlops็ฎ—ๆณ•้“พ่ทฏๅ…จๆต็จ‹๏ผŒ็ฎ—ๅŠ›็งŸ่ตๅนณๅฐ๏ผŒnotebookๅœจ็บฟๅผ€ๅ‘๏ผŒๆ‹–ๆ‹‰ๆ‹ฝไปปๅŠกๆตpipeline็ผ–ๆŽ’๏ผŒๅคšๆœบๅคšๅกๅˆ†ๅธƒๅผ่ฎญ็ปƒ๏ผŒ่ถ…ๅ‚ๆœ็ดข๏ผŒๆŽจ็†ๆœๅŠกVGPU่™šๆ‹ŸๅŒ–๏ผŒ่พน็ผ˜่ฎก็ฎ—๏ผŒๆ ‡ๆณจๅนณๅฐ่‡ชๅŠจๅŒ–ๆ ‡ๆณจ๏ผŒdeepseek็ญ‰ๅคงๆจกๅž‹sftๅพฎ่ฐƒ/ๅฅ–ๅŠฑๆจกๅž‹/ๅผบๅŒ–ๅญฆไน ่ฎญ็ปƒ๏ผŒvllm/ollama/mindieๅคงๆจกๅž‹ๅคšๆœบๆŽจ็†๏ผŒ็งๆœ‰็Ÿฅ่ฏ†ๅบ“๏ผŒAIๆจกๅž‹ๅธ‚ๅœบ๏ผŒๆ”ฏๆŒๅ›ฝไบงcpu/gpu/npu ๆ˜‡่…พ็”Ÿๆ€๏ผŒๆ”ฏๆŒRDMA๏ผŒๆ”ฏๆŒpytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano็ญ‰ๅˆ†ๅธƒๅผ

Score
100
โ˜… 5.1k โ‘‚ 884 +3/day
Python
truefoundry
truefoundry
cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

Score
38
โ˜… 4.4k โ‘‚ 390 +1/day
Python
decodingai-magazine
decodingai-magazine
llm-twin-course

๐Ÿค– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป for ๐—ณ๐—ฟ๐—ฒ๐—ฒ how to ๐—ฏ๐˜‚๐—ถ๐—น๐—ฑ an end-to-end ๐—ฝ๐—ฟ๐—ผ๐—ฑ๐˜‚๐—ฐ๐˜๐—ถ๐—ผ๐—ป-๐—ฟ๐—ฒ๐—ฎ๐—ฑ๐˜† ๐—Ÿ๐—Ÿ๐—  & ๐—ฅ๐—”๐—š ๐˜€๐˜†๐˜€๐˜๐—ฒ๐—บ using ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€ best practices: ~ ๐˜ด๐˜ฐ๐˜ถ๐˜ณ๐˜ค๐˜ฆ ๐˜ค๐˜ฐ๐˜ฅ๐˜ฆ + 12 ๐˜ฉ๐˜ข๐˜ฏ๐˜ฅ๐˜ด-๐˜ฐ๐˜ฏ ๐˜ญ๐˜ฆ๐˜ด๐˜ด๐˜ฐ๐˜ฏ๐˜ด

Score
94
โ˜… 4.4k โ‘‚ 733 +2/day
Python
Agenta-AI
Agenta-AI
agenta

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Score
93
โ˜… 4.3k โ‘‚ 565 +14/day
TypeScript
predibase
predibase
lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Score
89
โ˜… 3.8k โ‘‚ 323 +2/day
Python
memodb-io
memodb-io
Acontext

Agent Skills as a Memory Layer

Score
92
โ˜… 3.6k โ‘‚ 323 +3/day
JavaScript
truera
truera
trulens

Evaluation and Tracking for LLM Experiments and AI Agents

Score
100
โ˜… 3.4k โ‘‚ 309 +16/day
Python
iusztinpaul
iusztinpaul
hands-on-llms

๐Ÿฆ– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป about ๐—Ÿ๐—Ÿ๐— ๐˜€, ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€, and ๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐——๐—•๐˜€ for free by designing, training, and deploying a real-time financial advisor LLM system ~ ๐˜ด๐˜ฐ๐˜ถ๐˜ณ๐˜ค๐˜ฆ ๐˜ค๐˜ฐ๐˜ฅ๐˜ฆ + ๐˜ท๐˜ช๐˜ฅ๐˜ฆ๐˜ฐ & ๐˜ณ๐˜ฆ๐˜ข๐˜ฅ๐˜ช๐˜ฏ๐˜จ ๐˜ฎ๐˜ข๐˜ต๐˜ฆ๐˜ณ๐˜ช๐˜ข๐˜ญ๐˜ด

Score
72
โ˜… 3.4k โ‘‚ 551 โ€”
Jupyter Notebook
langwatch
langwatch
langwatch

The platform for LLM evaluations and AI agent testing

Score
91
โ˜… 3.4k โ‘‚ 328 +29/day
TypeScript
pezzolabs
pezzolabs
pezzo

๐Ÿ•น๏ธ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

Score
31
โ˜… 3.3k โ‘‚ 276 โ€”
TypeScript
Josh-XT
Josh-XT
AGiXT

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

Score
41
โ˜… 3.2k โ‘‚ 445 โ€”
Python
protectai
protectai
llm-guard

The Security Toolkit for LLM Interactions

Score
90
โ˜… 3.2k โ‘‚ 416 +14/day
Python
lmnr-ai
lmnr-ai
lmnr

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

Score
67
โ˜… 3.1k โ‘‚ 216 +5/day
TypeScript
ianarawjo
ianarawjo
ChainForge

An open-source visual programming environment for battle-testing prompts to LLMs.

Score
88
โ˜… 3.0k โ‘‚ 257 +1/day
TypeScript
decodingai-magazine
decodingai-magazine
second-brain-ai-assistant-course

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

Score
71
โ˜… 2.9k โ‘‚ 509 +16/day
Jupyter Notebook
OpenPipe
OpenPipe
OpenPipe

Turn expensive prompts into cheap fine-tuned models

Score
69
โ˜… 2.8k โ‘‚ 175 โ€”
TypeScript
apache
apache
hamilton

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Score
86
โ˜… 2.5k โ‘‚ 198 +2/day
Jupyter Notebook
vllm-project
vllm-project
vllm-ascend

Community maintained hardware plugin for vLLM on Ascend

Score
94
โ˜… 2.5k โ‘‚ 1.7k +90/day
C++
apache
apache
burr

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Score
87
โ˜… 2.5k โ‘‚ 169 +5/day
Python
uptrain-ai
uptrain-ai
uptrain

UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.

Score
67
โ˜… 2.4k โ‘‚ 202 โ€”
Python
dot-agent
dot-agent
nextpy

๐Ÿค–Self-Modifying Framework from the Future ๐Ÿ”ฎ World's First AMS

Score
65
โ˜… 2.3k โ‘‚ 181 โ€”
Python
bionic-gpt
bionic-gpt
bionic-gpt

Bionic is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

Score
50
โ˜… 2.3k โ‘‚ 235 โ€”
Rust
trypromptly
trypromptly
LLMStack

No-code multi-agent framework to build LLM Agents, workflows and applications with your data

Score
69
โ˜… 2.3k โ‘‚ 347 โ€”
Python
tensorchord
tensorchord
envd

๐Ÿ•๏ธ Reproducible development environment for humans and agents

Score
89
โ˜… 2.2k โ‘‚ 168 +3/day
Go
BlazeUp-AI
BlazeUp-AI
Observal

Observal is a sandboxed artifactory and analytics platform for your AI development stack. Setup Observal, define the scope and share your Skills, MCPs and Agents.

Score
34
โ˜… 2.2k โ‘‚ 463 +20/day
Python
mcp-router
mcp-router
mcp-router

A Unified MCP Server Management App (MCP Manager).

Score
86
โ˜… 2.1k โ‘‚ 168 +2/day
TypeScript
microsoft
microsoft
aici

AICI: Prompts as (Wasm) Programs

Score
17
โ˜… 2.1k โ‘‚ 84 โ€”
Rust
supervc-stack
supervc-stack
VectorChord

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

Score
67
โ˜… 1.7k โ‘‚ 70 +9/day
Rust
Related Topics
#llm#ai#mlops#openai#generative-ai#python#machine-learning#evaluation#prompt-engineering#agents#llm-evaluation#langchain

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly