24小时 AI 开源项目 实时更新

ai-data-analyst

AI-powered data analyst — upload any CSV, Excel, JSON, PDF, or SQL file and ask questions in plain English. Instant charts, powered by Groq.

AI 开源项目版本发布查看详情

prompt-armor

PromptArmor — independent third-party profile of a public API surface, by API Evangelist. PromptArmor (YC W24) is an LLM application security platform that detects and blocks enterprise-grade threats - indirect prompt injection, data exfiltration, phishing, and system manipulation - in production AI applications.

AI 开源项目版本发布查看详情

protectai

Protect AI — independent third-party profile of a public API surface, by API Evangelist. Protect AI is an AI/ML security platform (now part of Palo Alto Networks) whose products secure the AI lifecycle from model selection to runtime. Its developer surface centers on LLM Guard, an open-source Python toolkit of prompt and output scanners that ships

AI 开源项目版本发布查看详情

klu-ai

Klu — independent third-party profile of a public API surface, by API Evangelist. Klu (klu.ai) is an LLM app platform for designing, deploying, evaluating, and observing prompt-driven AI applications. The Klu Engine exposes a REST API at https://api.klu.ai/v1 (Bearer API key) where an Action encapsulates a prompt template, model config, context (RA

AI 开源项目版本发布查看详情

deepchecks

Deepchecks — independent third-party profile of a public API surface, by API Evangelist. Deepchecks is an ML and LLM testing, evaluation, and monitoring platform. Its cloud LLM Evaluation product exposes a REST API for logging LLM interactions, managing applications and versions, retrieving annotations, and configuring evaluation properties, while

AI 开源项目版本发布查看详情

uptrain

UpTrain is an open-source (Apache-2.0) unified platform to evaluate and improve generative AI and LLM applications. It ships a Python framework plus a managed evaluation API that grades responses against 20+ preconfigured checks - context relevance, factual accuracy, response completeness, hallucination, tonality, prompt injection and more - and…

AI 开源项目版本发布查看详情

martian-ai

Martian operates an LLM model router and gateway that dynamically routes each request to the best underlying model across providers for the optimal balance of quality, latency, and cost.

AI 开源项目版本发布查看详情

athina

Athina AI — independent third-party profile of a public API surface, by API Evangelist. Athina AI is an LLM monitoring, evaluation, and experimentation platform for building production-grade AI applications. Its REST API lets teams log inferences and traces, manage datasets, run 50+ preset and custom evaluations, version and run prompt templates, a

AI 开源项目版本发布查看详情

keywordsai

Keywords AI — independent third-party profile of a public API surface, by API Evangelist. Keywords AI is an LLM observability and gateway platform. It exposes an OpenAI-compatible proxy (chat completions across 250+ models) plus REST APIs for request logging, prompt management, threads, evaluations, and traces - all under a single Bearer-authentica

AI 开源项目版本发布查看详情

requesty

Requesty — independent third-party profile of a public API surface, by API Evangelist. Requesty is an LLM routing and gateway platform that exposes a single OpenAI-compatible API across 300+ models from providers like OpenAI, Anthropic, DeepSeek, and Together AI. The Requesty Router adds intelligent routing, automatic fallbacks, response caching, s

AI 开源项目版本发布查看详情

llmwhisperer

LLMWhisperer is a document-to-text extraction API from Unstract (Zipstack) that turns complex PDFs, scanned documents, and images into clean, layout-preserving text ready for large language models.

AI 开源项目版本发布查看详情

literalai

Literal AI is the collaborative observability, evaluation, and analytics platform for building production-grade LLM applications, from the Chainlit team. Its API is GraphQL (POST /api/graphql) consumed through Python and TypeScript SDKs, capturing threads, steps, generations, datasets, experiments, prompts, and scores, with an additional…

AI 开源项目版本发布查看详情

openlayer

Openlayer — independent third-party profile of a public API surface, by API Evangelist. Openlayer is an AI evaluation, testing, and observability platform for machine learning and LLM applications. Its REST API lets teams create projects, commit model versions and datasets, run tests, stream production inference data into monitoring pipelines, and

AI 开源项目版本发布查看详情

promptlayer

PromptLayer — independent third-party profile of a public API surface, by API Evangelist. PromptLayer is a prompt engineering, prompt management, and LLM observability platform. Its REST API logs and tracks LLM requests, manages a versioned prompt registry with release labels, ingests OpenTelemetry-style spans and traces, and runs evaluations and d

AI 开源项目版本发布查看详情

contextual-ai

Contextual AI is an enterprise RAG platform built around a Grounded Language Model (GLM) engineered to minimize hallucinations. Its REST API exposes end-to-end RAG agents (create, configure, query) plus standalone component APIs - Generate, Rerank, Parse, and LMUnit - over datastores of ingested documents, all authenticated with a Bearer API key.

AI 开源项目版本发布查看详情

predibase

Predibase — independent third-party profile of a public API surface, by API Evangelist. Predibase is a platform for fine-tuning and serving open-source LLMs. It pairs efficient LoRA / Turbo LoRA supervised and reinforcement (GRPO) fine-tuning with serverless and dedicated inference powered by LoRAX, the open-source multi-LoRA serving stack that pac

AI 开源项目版本发布查看详情

braintrust-data

Braintrust — independent third-party profile of a public API surface, by API Evangelist. Braintrust (braintrust.dev) is an end-to-end platform for building, evaluating, and observing AI applications. Its REST API at api.braintrust.dev exposes projects, experiments, datasets, logs/spans, prompts, functions and scorers, evals, and full organization/A

AI 开源项目版本发布查看详情

pantella-wow

World of Warcraft integration for Pantella: Radiant real-time LLM voice & text conversations with NPCs and combat pets

AI 开源项目版本发布查看详情

parallax

A Gen Z couples app — React Native + Expo + Supabase. Daily prompt 'drops', a server-gated 'wavelength' reveal (RLS-enforced), and AI conflict mediation. Building in public · pre-launch.

AI 开源项目版本发布查看详情

hl-claude-plugins

A personal collection of Claude Code skills, distributed as installable plugins.

AI 开源项目版本发布查看详情