首页 / AI每日快讯

24小时 AI 开源项目 实时更新

AI 开源仓库与版本发布动态

LATEST UPDATES

最新获取

AI 开源项目 · 3209 条快讯
全部更新按发布时间倒序

2026-08-02

  1. thinking-machines-lab

    Thinking Machines Lab — independent third-party profile of a public API surface, by API Evangelist. Thinking Machines Lab is an AI research company (founded by Mira Murati) whose first product is Tinker — a cloud training API for researchers and developers. Tinker gives you full control over your data, algorithms, and models while it manages the GP

    AI 开源项目版本发布查看详情
  2. thinking-machines

    Thinking Machines — independent third-party profile of a public API surface, by API Evangelist. Thinking Machines Lab is an artificial intelligence research and product company building tools to make AI systems more widely understood, customizable, and generally capable. Its flagship developer product is Tinker, a managed API with an official Pytho

    AI 开源项目版本发布查看详情
  3. Vega-Agent

    Automate file management, web research, and code tasks on Android using your own API key with this local-first AI agent.

    AI 开源项目版本发布查看详情
  4. PaglaROUTER

    Unified LLM gateway for the PaglaAI ecosystem - one OpenAI + Anthropic endpoint, weighted multi-provider routing, multi-account aggregation. Intelligence Unhinged.

    AI 开源项目版本发布查看详情
  5. OpenRSI

    Execute, measure, and reproduce Recursive Self-Improvement for AI models using standardized datasets and training tasks.

    AI 开源项目版本发布查看详情
  6. n8n_agents

    Automate complex tasks using a collection of pre-built n8n workflows and agentic patterns ready for local deployment.

    AI 开源项目版本发布查看详情
  7. cortexagent

    Private, local AI coding agent on llama.cpp — CortexAgent Console (chat + tasks + browser tabs in one window), SlimToken context compression, automatic memory, speech-to-text voice input, overseer routing. No cloud, no API key.

    AI 开源项目版本发布查看详情
  8. awesome-ai-native

    Curate a list of AI-native products where large language models define the core functionality rather than serving as secondary features.

    AI 开源项目版本发布查看详情
  9. stepfun

    StepFun — independent third-party profile of a public API surface, by API Evangelist. StepFun (阶跃星辰) is a Shanghai-based AI foundation-model company whose open platform serves the Step model family — multimodal reasoning (step-3.7-flash), fast language reasoning (step-3.5-flash), vision, image generation and editing (step-2x-large, step-image-edit-

    AI 开源项目版本发布查看详情
  10. ai-virtual-receptionist

    24/7 AI receptionist that books appointments, captures leads, routes conversations, and hands off to humans — built with Next.js, NestJS, pgvector, React Native, and Gemini.

    AI 开源项目版本发布查看详情
  11. trusted-router-java

    Java, Kotlin, and Android SDK for TrustedRouter

    AI 开源项目版本发布查看详情
  12. stacks-ai

    Stacks Ai — StackAI (Stack AI, Inc.) is an enterprise AI agent platform that lets teams build, deploy, and govern no-code agentic workflows at scale. Its visual Workflow Builder chains LLMs, knowledge bases, connections, and logic nodes into production agents that can be deployed as a REST API, chat assistant, form, or batch job.

    AI 开源项目版本发布查看详情
  13. enlil

    Source-available control and audit plane for AI agent actions. Enforce what your agents may do, and prove what they did.

    AI 开源项目版本发布查看详情
  14. caseweave

    CaseWeave 纬策 — 把需求织成用例:AI 驱动的智能测试用例生成系统(需求澄清 → 用例生成 → Excel 导出 → 反馈进化)

    AI 开源项目版本发布查看详情

2026-08-01

  1. scorecard

    Scorecard — independent third-party profile of a public API surface, by API Evangelist. Scorecard is a simulation and evaluation platform for building, testing, and deploying frontier AI agents. Teams run their agents through thousands of realistic scenarios, judge outputs with configurable AI, human, and heuristic metrics, and ship new capabilitie

    AI 开源项目版本发布查看详情
  2. sambanova-systems

    SambaNova Systems is an AI infrastructure company that builds custom Reconfigurable Dataflow Unit (RDU) chips and the SambaCloud, SambaStack, and SambaRack platforms for fast, energy-efficient AI inference.

    AI 开源项目版本发布查看详情
  3. sail

    Sail Research provides cloud infrastructure for running long-horizon AI agents efficiently. Its inference platform serves leading open-source models (GLM, Kimi, DeepSeek, gpt-oss, Gemma, and more) through an OpenAI-compatible Responses and Chat Completions API plus an Anthropic-compatible Messages API, so existing SDKs work as drop-in clients.

    AI 开源项目版本发布查看详情
  4. go-llama

    llama.cpp in pure Go

    AI 开源项目版本发布查看详情
  5. laravel-natural-query

    Ask your database questions in English, by voice or by typing. The AI sees only your schema, never your data. Any LLM - hosted or self-hosted.

    AI 开源项目版本发布查看详情
  6. RuneForgeAI-Project-Aesir

    Bare-metal Mojo inference engine designed for local sovereignty. Features zero-copy GGUF parsing, PagedAttention KV caching, and a stateless sampler. Optimized for consumer hardware, it eliminates cloud dependency and bloat to deliver high-performance, private AI directly on the edge.

    AI 开源项目版本发布查看详情