List all AI models available through the AiChat API, grouped by provider with descriptions. Find supported models like GPT-4/5, DeepSeek, Grok, and GLM for your conversations.
MIT
596,922 tools. Updated 2026-09-21 10:31
"How to improve memory or retention like GPT models" matching MCP tools:
- Calculate day-based retention (D1/D2/D7/D30) for a game, optionally scoped to a build version, to compare retention across builds.MIT
- Send a question to AI models like GPT-4, DeepSeek, or Grok to get generated answers. Continue existing conversations by providing a conversation ID for context-aware responses.MIT
- Monitor how your brand appears in AI-generated responses across ChatGPT, Claude, Gemini, and other AI models.MIT
- Run a maintenance pass to consolidate memory: promote repeated episodes into semantic facts, decay stale working-memory slots, and prune data below retention threshold.Apache 2.0Destructive
- Set how long snapshots are kept before automatic cleanup by specifying retention days, or clear retention to keep them indefinitely. Updates the workspace's snapshot-retention policy.MIT
Matching MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to control and interact with a local Windows computer through authenticated MCP tools, including file operations, shell commands, process management, HTTP requests, and system/media inspection.-
- FlicenseAqualityBmaintenanceEnables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.8-
Matching MCP Connectors
GPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.
Simple GPT: A simple floating widget allows you to access the AI assistant immediately from.
- Check remaining model quota for Antigravity's Gemini and Claude+GPT pools to avoid delegation failures or decide which model family has available capacity.MIT
- Route AI tasks to the local Codex desktop agent via Codex CLI for non-interactive execution using your OpenAI subscription. Choose it when Claude limits are tight or tasks fit OpenAI's models.MIT
- Check cognitive memory retention to spot declining quality, view distribution buckets, and receive recommendations for improvement.AGPL 3.0
- Generate images from text prompts using 30+ AI models including DALL-E, GPT Image, and Stable Diffusion. No API keys needed.MIT
- Free GPU VRAM by unloading cached models and memory in ComfyUI, preventing out-of-memory errors when switching between model families or running multiple generations.MIT
- Mark a recalled memory as helpful to improve ranking. Track which memories are valuable for future responses.MIT
- View your prompt scoring history, average score, grade distribution, and creative DNA patterns to find how to improve your AI prompts.MIT
- Get proof strategy suggestions and alternative reasoning paths for Lean 4 code and math problems by querying Gemini or GPT models. Discuss approaches, compare suggestions, and debug stuck proofs.MIT
- Lists configured image providers (Gemini, Grok, GPT-image) with their live models and indicates the default provider/model for image generation.MIT
- Edits or transforms your images based on a text prompt, using Gemini, Grok, or GPT-image models, and saves the result to disk.MIT
- Compare pricing across multiple LLM models side by side to analyze input/output costs, context windows, and relative cost differences.MIT
- Count tokens in text across multiple LLM models to check context window usage and compare costs before sending to an LLM.MIT
- Signal recalled memories as useful or irrelevant to improve future retrieval accuracy.MIT
- Edit images using inpainting with OpenAI GPT models. Apply edits to transparent areas of a mask while preserving faces and logos with adjustable fidelity.MIT
- List all available chat completion models including GPT-4, GPT-4o, GPT-5, and o-series models. View model names and descriptions in a table.MIT