Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
Repository Index
142,273 visible repositories in the index
529–552 of 802 · Most stars
Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.
- audio-ai
- audio-processing
- foundational-models
- large-language-models
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
NextCRM — Open-source CRM built with Next.js 16, React 19, PostgreSQL, Prisma 7, and shadcn/ui. CRM, projects, invoicing, documents, email client & AI features.
- next-auth
- prisma
- typescript
- tremor
Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
- chatbot
- python
- realtime
AI-friendly semantic code search engine for large codebases. Combines ripgrep speed with tree-sitter AST parsing. Powers AI coding assistants with precise, context-aware code understanding.
- ai
- ai-coder
- search-engine
- ast
macOS menubar app for fast local DeepSeek V4.1, with 1M context.
- deepseek
- deepseek-v4
- deepseek-v4-pro
- ds4
A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
- ai
- coding-agent
- embeddings
- knowledge-graph
SEAIT is a user-friendly application that simplifies the installation process of AI-related projects
- ai
- artificial-intelligence
- automatic1111
- install
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf
A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
Accurate, large-scale, and extensible simulator for LLM inference Systems
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
Stock market MCP server for Yahoo Finance data, technical analysis, portfolio tracking, and Python backtesting. Runs locally with no API key for core tools.
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
- claude-code
- execution
- marketplace
- planning
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
- artificial-intelligence
- attention
- attention-is-all-you-need
- attention-mechanisms
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
- efficient-inference
- large-language-models
- llm
- model-compression
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
- gpt
- kanformers
- kolmogorov-arnold-networks
- kolmogorov-arnold-representation
Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent video. Provider-agnostic (OpenAI/Claude, MJ, Minimax, Veo/Sora, fal, ComfyUI). MIT.
A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use
- alpha-evolve
- alphacode
- openevolve
- openloop
NucliaDB, The AI Search database for RAG
- database
- language-model
- machine-learning
- mlops