Building AI agents, atomically

Building AI agents, atomically

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

Agent OS: Stop prompting. Start specifying. A Socratic interview gates the spec on an ambiguity score, then one command drives execution, a 3-stage evaluation gate, and a budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

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.

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

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

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

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

Low-latency AI engine for mobile devices & wearables

Build distributed, production-grade, long-running agents.

Zero-Config Code Flow for Claude code & Codex

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

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

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

An awesome & curated list of best LLMOps tools for developers

🐢 Open-Source Evaluation & Testing library for LLM Agents

Democratizing Reinforcement Learning for LLMs

Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.

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

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.

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

🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

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

The open source platform for AI-native application development.

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

A curated list of vibe coding references, collaborating with AI to write code.

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

Olares: An Open-Source Personal Cloud to Reclaim Your Data

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、LLM大模型、传统深度学习、自动驾驶、AI Agent、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

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

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks

RuVector is a High Performance, Real-Time, Self-Learning, Vector Graph Neural Network, and Database built in Rust.

RuVector is a High Performance, Real-Time, Self-Learning, Vector Graph Neural Network, and Database built in Rust.

A simple yet powerful agent framework that delivers with open-source models

Open-source graph database, tuned for dynamic analytics environments. Easy to adopt, scale and own.