由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI,token 成本极低。
覆盖 459 类工作流,通过流量估算、产品功能与替代方案辅助选型。
“Code Debugging” · 写作与文本编辑·202 个结果
重新开始由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI,token 成本极低。


为 TradingView 策略与指标生成 AI 版 Pine Script

开源可观测性:发现 AI Agent 的故障,并直接修复


Maxim AI is a platform for evaluating, testing, and monitoring AI applications, and the home of Bifrost, an open-source LLM gateway. It helps teams ship reliable AI features with tracing, evaluation, agent simulation, and production observability.
Maxim AI is a platform for evaluating, testing, and monitoring AI applications, and the home of Bifrost, an open-source LLM gateway. It helps teams ship reliable AI features with tracing, evaluation, agent simulation, and production observability.
16x Prompt is a desktop application for developers that helps you gather source-code context, compose structured prompts, and run them through leading LLMs to complete real coding work on existing codebases. It combines a context manager, a prompt builder, custom instructions, task templates, and optional bring-your-own-key API integrations in one local app.
16x Prompt is a desktop application for developers that helps you gather source-code context, compose structured prompts, and run them through leading LLMs to complete real coding work on existing codebases. It combines a context manager, a prompt builder, custom instructions, task templates, and optional bring-your-own-key API integrations in one local app.

Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.
Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.



Replicate is a cloud API for running, fine-tuning, and deploying machine learning models. Spin up open-source and hosted models — from image, video, and audio generation to speech synthesis, captioning, and LLM inference — with one line of code, or package your own model with Cog and put it behind a production-ready API.
Replicate is a cloud API for running, fine-tuning, and deploying machine learning models. Spin up open-source and hosted models — from image, video, and audio generation to speech synthesis, captioning, and LLM inference — with one line of code, or package your own model with Cog and put it behind a production-ready API.
由 PyTorch Lightning 创建团队打造的 AI 云平台
面向编码智能体的 Fast Apply 与智能体调优推理

Vellum is a personal AI assistant that you own and customize. It runs locally on your machine or in Vellum Cloud, remembers your context over time, connects to your tools and takes real actions like email, calendar, research and file work, with model choice across OpenAI, Anthropic, Gemini or local open weights via Ollama.
Vellum is a personal AI assistant that you own and customize. It runs locally on your machine or in Vellum Cloud, remembers your context over time, connects to your tools and takes real actions like email, calendar, research and file work, with model choice across OpenAI, Anthropic, Gemini or local open weights via Ollama.
Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.

Langtail is a prompt management platform for product teams that lets engineers, PMs, and domain experts build, test, version, and deploy LLM prompts through a spreadsheet-like interface, with observability logs, evaluation runs, and an AI firewall for blocking prompt injection and unsafe outputs. It works across OpenAI, Anthropic, Gemini, Mistral, and other major providers.
Langtail is a prompt management platform for product teams that lets engineers, PMs, and domain experts build, test, version, and deploy LLM prompts through a spreadsheet-like interface, with observability logs, evaluation runs, and an AI firewall for blocking prompt injection and unsafe outputs. It works across OpenAI, Anthropic, Gemini, Mistral, and other major providers.

