AI tools tagged Outputs Json

OpenAI Fine-tuning

Fine-tuning · GPT-4o-mini / GPT-3.5

8.4

Fine-tune GPT-4o-mini and friends on your own data.

AgentMemory

Agents · Multi-model (Claude, Gemini, MiniMax, OpenRouter)

Open-source persistent memory runtime for AI coding agents, with hybrid retrieval and zero external dependencies.

Cursor Talk to Figma MCP

Agents · Multi-model (Cursor / Claude Code via MCP)

Open-source MCP bridge that lets Cursor and Claude Code read and edit Figma files directly from the editor.

Exa

RAG · Proprietary neural + keyword search

Web search API built for AI agents, with structured outputs and token-efficient highlights.

Firecrawl

RAG

Web scraping and crawling API that returns LLM-ready markdown, JSON, or structured data from any URL.

Forefront

Fine-tuning · Multi-model (Mistral-7B, Mixtral, Phi-2)

Fine-tune and serve open-source LLMs on your own data without managing GPUs.

Framelink

Coding · Multi-model (BYO agent: Cursor, Claude Code, VS Code, etc.)

Open-source MCP server that pipes Figma designs into AI coding agents as structured, low-noise context.

Graphiti

RAG · Multi-model

Open-source temporal knowledge graph framework for building agent memory that updates in real time.

HTML Anything

Coding · Multi-model (uses your local coding agent CLI)

Agentic HTML editor that turns markdown, CSV, and JSON into ship-ready posts for WeChat, X, Zhihu, and Xiaohongshu.

Headroom

Agents · Model-agnostic (Anthropic, OpenAI, Vertex, Bedrock, Azure, 100+ via LiteLLM)

Open-source context compression layer that strips 70-95% of boilerplate before it hits your LLM.

Hugging Face AutoTrain

Fine-tuning · Multi-model (Hugging Face Hub)

No-code fine-tuning and training pipeline that spins up state-of-the-art models on the Hugging Face Hub.

Lambda

Fine-tuning

On-demand NVIDIA GPU cloud built specifically for training, fine-tuning, and serving large AI models.

LangFast

Evaluation · Multi-model

No-signup LLM playground for testing, comparing, and versioning prompts against your own API keys.

Lexica

Image Generation · Lexica Aperture (proprietary) + Stable Diffusion

Text-to-image generator with a massive searchable prompt library built on its proprietary Aperture model.

Model Context Protocol

Agents · Model-agnostic

Open standard that lets AI apps plug into data sources, tools, and workflows like USB-C for LLMs.

Oh My OpenAgent

Agents · Multi-model (Claude Opus 4.7, Sonnet 4.6, GPT 5.5, Gemini 3.1 Pro)

Open-source multi-agent orchestration framework that coordinates specialized AI coders across planning, execution, and verification.

OneKE

RAG · Multi-model (OneKE-13B, LLaMA3, Qwen2.5, GPT, DeepSeek-R1)

Open-source multi-agent framework for schema-guided knowledge extraction from documents.

OpenDataLoader PDF

RAG

Open-source PDF parser built for RAG pipelines, with reading-order detection, table extraction, and bounding-box citations.

PySpur

Agents · Multi-model

Open-source agent builder with a drag-and-drop canvas, Python escape hatch, and a built-in test harness.

RabbitHoles AI

Agents · Multi-model (Anthropic, Google, Groq, Perplexity, custom)

Infinite-canvas AI chat client that lets you branch, fork, and connect conversations as nodes instead of scrolling a single linear thread.

Repomix

Coding

Packs an entire codebase into a single AI-friendly file so LLMs can actually read your repo.

ScrapeGraphAI

Agents · Multi-model (LLM, unspecified)

LLM-driven web scraping API that turns natural-language prompts into structured JSON.

Skyvern

Agents · Multi-model (OpenAI, Anthropic, Gemini, Ollama)

AI browser agent that automates web workflows from natural-language instructions, with CAPTCHA and 2FA handling built in.

Superpower ChatGPT

Agents · GPT (via ChatGPT UI)

Chrome extension that bolts folders, prompt libraries, and bulk export onto the ChatGPT web UI.

Vibe

Audio · OpenAI Whisper (via whisper.cpp)

Offline desktop transcription app powered by Whisper, with diarization, batch processing, and an HTTP API.

WhisperAPI

Audio · OpenAI Whisper

Hosted OpenAI Whisper transcription with a pay-as-you-go API and drop-in web dashboard.

llmfit

Evaluation · Multi-model

Terminal tool that scores hundreds of open LLMs against your actual CPU, RAM, and GPU and tells you which ones will run well.

oMLX

Coding · Multi-model (Qwen, Llama, Mistral, Gemma, DeepSeek, MiniMax, GLM)

Native macOS LLM inference server built on MLX, with paged SSD KV caching for Apple Silicon agents.