taylorwilsdon / llm-context-limitsLinks
Since OpenAI and friends refuse to give us a max_ctx param in /models, here's the current context window, input token and output token limits for OpenAI (API), Anthropic, Qwen, Deepseek, llama, Phi, Gemini and Mistral
☆50Updated last month
Alternatives and similar repositories for llm-context-limits
Users that are interested in llm-context-limits are comparing it to the libraries listed below
Sorting:
- This tool is a cutting-edge memory engine that blends real-time learning, persistent three-tier context awareness, and seamless plug-n-pl…☆59Updated 3 weeks ago
- Comprehensive, highly performant Google Workspace MCP Server with complete coverage for Calendar, Gmail, Docs, Sheets, Slides, Chat, Form…☆167Updated last week
- 🚀 FlexLLama - Lightweight self-hosted tool for running multiple llama.cpp server instances with OpenAI v1 API compatibility and multi-GP…☆21Updated 2 weeks ago
- Cognito: Supercharge your Chrome browser with AI. Guide, query, and control everything using natural language.☆48Updated this week
- Enable tool/function calling for any LLM, in OpenAI and Ollama API formats, adding universal function calling to models without native su…☆41Updated last month
- A sophisticated biologically inspired memory system for AI agents. Provides organic, high quality, persistent memory with self-maintenanc…☆43Updated 3 weeks ago
- Generates breakthrough ideas from a single prompt through an 8 stage walkthrough, with optional research proposal paper.☆56Updated 3 months ago
- ☆103Updated last month
- Not just another MCP filesystem. Optimized file operations with smart context management and token-efficient partial reading/editing. Pro…☆34Updated 3 months ago
- Fast local speech-to-text for any app using faster-whisper☆74Updated 2 months ago
- Web UI and API for managing MCP Orchestrator (mcpo) instances and configurations☆72Updated last month
- MCP server for enabling LLM applications to perform deep research via the MCP protocol☆188Updated last week
- MCP servers that models can use to extend their capabilities for general-use tasks and formalized workflows. all servers available via Sm…☆42Updated this week
- Open-sourced and improved memory for developers and consumers built on top of mem0.☆92Updated this week
- ☆100Updated 4 months ago
- This is a cross-platform desktop application that allows you to chat with locally hosted LLMs and enjoy features like MCP support☆221Updated last week
- A systematic reasoning MCP server implementation for Claude Desktop with beam search and thought evaluation.☆26Updated 4 months ago
- beep boop 🤖 (experimental)☆111Updated 5 months ago
- Finally, an open source Youtube Summarizer extension☆73Updated 2 months ago
- ☆50Updated 3 months ago
- Effortlessly Build Model Context Protocol Servers with OpenAPI or Swagger or Google Discovery Specifications☆50Updated 3 weeks ago
- WebRAgent is a retrieval-augmented generation (RAG) web application featuring agent-based query decomposition, vector search with Qdrant,…☆44Updated 3 months ago
- PocketFlow's node-based workflow structure, with Manus' agents and tools!☆240Updated 2 weeks ago
- ☆38Updated 2 months ago
- ☆145Updated last month
- MAESTRO is an AI-powered research application designed to streamline complex research tasks.☆158Updated last week
- Give your local LLM a real memory with a lightweight, fully local memory system — just like a human recalling past discussions. 100% off…☆45Updated last week
- This is a technical writeup of the next evolution in the Adaptive Modular Network. It aims to unify the components of the AMN and fill ga…☆56Updated last week
- Personal voice assistant, with voice interruption and Twilio support☆17Updated 4 months ago
- reddacted lets you analyze & sanitize your online footprint using LLMs, PII detection & sentiment analysis to identify anything that migh…☆100Updated 3 weeks ago