Unified Go interface for Language Model (LLM) providers. Simplifies LLM integration with flexible prompt management and common task functions.

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.

Mock everything your AI app talks to — LLM APIs, MCP, A2A, vector DBs, search. One package, one port, zero dependencies.

Awesome papers involving LLMs in Social Science.

The .NET library to build AI agents with 30+ built-in connectors.

Daydreams is a set of tools for building agents for commerce

FastAPI Skeleton App to serve machine learning models production-ready.

A test runner for agentskills.io-style AI agent skills

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

LLM (Large Language Model) FineTuning

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

A framework-agnostic, git-native standard for defining AI agents

The open-source diagnostic for AI misalignment. 32 tests across fabrication, manipulation, deception, unpredictability, and opacity. Provider-agnostic. Runs against OpenAI, Anthropic, Bedrock, Azure, Gemini, and more. Letter grade in under 5 minutes, content-addressed manifest for bit-identical replay. Built by iMe.

Deliver safe & effective language models

Deliver safe & effective language models

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

Python + Inference - Model Deployment library in Python. Simplest model inference server ever.

Data-Driven Evaluation for LLM-Powered Applications

The Linux OS for AI Agents — Persistent memory, autonomy, and time-awareness for any LLM. Own the state. Rent the intelligence.

irresponsible innovation. Try now at https://chat.dev/

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

A fast and minimal framework for building agentic systems

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

Repo for fine-tuning Casual LLMs

Free, open-source AWS emulator. LocalStack alternative: 26 services, 1,924 operations, 100% conformance. No account, no auth token, no paid tier.

Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.

xFasterTransformer — open-source AI/LLM project.

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

A REST API for Caffe using Docker and Go

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

Awesome-LLM-Prompt-Optimization: a curated list of advanced prompt optimization and tuning methods in Large Language Models

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (RAG, Agents).

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

Learn to serve Stable Diffusion models on cloud infrastructure at scale. This Lightning App shows load-balancing, orchestrating, pre-provisioning, dynamic batching, GPU-inference, micro-services working together via the Lightning Apps framework.

LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.

APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention

Open-source autonomous AI agent — runs on Claude-web, Gemini-web, Kimi-web, Deepseek-web and more for free and Every paid model via liteLLM. No API key required.

A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)

Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.

A Production-Ready Framework for Building Composable AI Agents

Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework

The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)