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

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

The Open Source Feature Store for AI/ML

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

AI + Data, online. https://vespa.ai

Plano is an AI-native proxy server and data plane for agentic apps - centralizing orchestration, safety, observability, and smart LLM routing so you can deliver agents faster.

Postgres with GPUs for ML/AI apps.

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

Open-source implementation of AlphaEvolve

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with MCP and live tracing. Three runtime dependencies.

TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js runs.

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

Efficient Triton Kernels for LLM Training

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

An open and fair framework for everyone to build AI agents equipped with powerful skills. Launch your agent, improve the world, your wallet, or both!

Open-source context retrieval layer for AI agents

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括335个大模型，覆盖chatgpt、gpt-5.2、o4-mini、谷歌gemini-3-pro、Claude-4.5、文心ERNIE-X1.1、ERNIE-5.0-Thinking、qwen3-max、百川、讯飞星火、商汤senseChat等商用模型， 以及kimi-k2、ernie4.5、minimax-M2、deepseek-v3.2、qwen3-2507、llama4、智谱GLM-4.6、gemma3、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

A query and indexing engine for Redis, providing secondary indexing, full-text search, vector similarity search and aggregations.

Zero-Config Code Flow for Claude code & Codex

Building AI agents, atomically

Building AI agents, atomically

Memory library for building stateful agents

FlashInfer: Kernel Library for LLM Serving

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

An awesome & curated list of best LLMOps tools for developers

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

A visual playground for agentic workflows: Iterate over your agents 10x faster

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Democratizing Reinforcement Learning for LLMs

A curated list of Artificial Intelligence Top Tools

🐢 Open-Source Evaluation & Testing library for LLM Agents

HelixDB is an open-source graph-vector database built from scratch in Rust.

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

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.

A framework for efficient model inference with omni-modality models

An Open Agent Computer for ANY digital work.

Low-latency AI engine for mobile devices & wearables

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）