ai-tools.md

🤖 AI Agents & Local LLM Tools

Open-source AI frameworks, local model runtimes, coding assistants, and autonomous agent systems.

← Back to Main Directory • 🌐 Live Search App • ➕ Submit New Resource

Jump to Subcategory: AI Agents & MCP Servers • AI Workflow & Orchestration • Autonomous Coding & Agent Dev • Local AI & Inference • Web UI & Chat

---

AI Agents & MCP Servers (1)

Tool	Language	License	Description	Links
MCP Dubai	Python	MIT	Open-source MCP server connecting AI assistants to Dubai and UAE public APIs — real estate, transport, statistics, education, health, and business data via Dubai Pulse, RTA, DLD, KHDA, and DHA. Runs locally over stdio.	GitHub

AI Workflow & Orchestration (22)

Tool	Language	License	Description	Links
Dify	Python / TypeScript	Apache-2.0	An open-source LLM app development platform combining AI workflow, RAG pipeline, agent capabilities, and model management.	GitHub
Flowise	TypeScript	Apache-2.0	Drag & drop user interface for building customized LLM applications, autonomous agents, and RAG pipelines.	GitHub
Langflow	Python / TypeScript	MIT	Dynamic visual framework for building, testing, and deploying multi-agent AI and RAG applications.	GitHub
LlamaIndex	Python / TypeScript	MIT	Data framework for connecting enterprise custom data sources and knowledge bases to Large Language Models.	GitHub
LangChain	Python / TypeScript	MIT	Standard open-source framework for building context-aware reasoning applications, agents, and multi-agent systems.	GitHub
Instructor	Python	MIT	Structured data extraction from LLMs powered by Pydantic with validation, retries, and streaming support.	GitHub
MindsDB	Python	GPL-3.0	Platform for customizing AI models directly on top of real-time enterprise data engines using SQL queries.	GitHub
SearXNG	Python	AGPL-3.0	Privacy-respecting open-source metasearch engine ideal for grounding AI models and retrieval-augmented generation.	GitHub
RAGFlow	Python	Apache-2.0	Next-generation open-source RAG engine based on deep document understanding to extract structured data from complex files.	GitHub
Mem0	Python	Apache-2.0	The memory layer for personalized AI assistants and autonomous agents, improving retention over time.	GitHub
⭐ CrewAI	Python	MIT	Cutting-edge framework for orchestrating role-playing, autonomous AI agents to collaborate seamlessly.	GitHub
AutoGen	Python	CC-BY-4.0	Microsoft's multi-agent conversation framework for building advanced AI agent workflows and collaborative task execution.	GitHub
MetaGPT	Python	MIT	Multi-agent framework assigning distinct software company roles (Product Manager, Architect, Engineer) to LLMs.	GitHub
ChatDev	Python	Apache-2.0	Virtual software company simulated by communicative agents to complete full lifecycle software development.	GitHub
Ragas	Python	Apache-2.0	Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines with faithfulness metrics.	GitHub
DeepEval	Python	Apache-2.0	The open-source LLM evaluation framework like Pytest for LLM applications with 14+ benchmark metrics.	GitHub
NeMo-Guardrails	Python	Apache-2.0	NVIDIA's toolkit for easily adding programmable guardrails and safety bounds to LLM-based conversational apps.	GitHub
Guidance	Python	MIT	A guidance language for controlling large language models with interleaved generation, prompting, and constrain.	GitHub
Outlines	Python	Apache-2.0	Structured text generation library with regular expressions, JSON schemas, and context-free grammars.	GitHub
Promptfoo	TypeScript	MIT	Test your prompts, agents, and RAGs against red-teaming attacks, prompt injections, and regression suites.	GitHub
LMQL	Python	Apache-2.0	A query language for programming Large Language Models with typed output constraints and distribution control.	GitHub
⭐ DSPy	Python	MIT	Stanford framework for programming—rather than prompting—foundation models with automatic prompt optimization.	GitHub

Autonomous Coding & Agent Dev (11)

Tool	Language	License	Description	Links
Fabric	Go	MIT	Open-source prompt and automation framework for augmenting humans using AI patterns and modular CLI tooling.	GitHub
Aider	Python	Apache-2.0	AI pair programming in your terminal: edit code in local git repos with Claude 3.5 Sonnet, GPT-4o, or local LLMs with auto-commits.	GitHub
OpenHands	Python	MIT	Open-source platform for software development agents that can write code, fix bugs, run bash commands, and browse documentation autonomously.	GitHub
Continue	TypeScript	Apache-2.0	Leading open-source AI code assistant inside VS Code and JetBrains: bring your own models, embeddings, and context providers.	GitHub
Tabby	Rust	Apache-2.0	Self-hosted AI coding assistant alternative to GitHub Copilot with local model execution and editor plugins.	GitHub
Open-Interpreter	Python	AGPL-3.0	Open-source, local-first code interpreter that lets LLMs run Python, JavaScript, and Bash code on your computer.	GitHub
⭐ AutoGPT	Python	MIT	Autonomous AI agent platform empowering developers to create, test, and deploy customized AI agent chains.	GitHub
SuperAGI	Python	MIT	Dev-first open source autonomous AI agent framework with GUI, agent telemetry, concurrent agents, and marketplace.	GitHub
BabyAGI	Python	MIT	Pioneering AI-powered task management and autonomous agent execution system that builds on task completion loops.	GitHub
OpenCodeInterpreter	Python	Apache-2.0	Open-source code generation system integrating dynamic execution feedback and compiler outputs for iterative code refinement.	GitHub
SWE-agent	Python	MIT	Autonomous software engineering agent that turns LM models into autonomous agents solving GitHub issues.	GitHub

Local AI & Inference (51)

Tool	Language	License	Description	Links
⭐ Ollama	Go	MIT	Get up and running with Llama 3.3, Mistral, Qwen, and other large language models locally with a simple CLI and REST API.	GitHub
vLLM	Python / C++	Apache-2.0	A high-throughput and memory-efficient inference and serving engine for LLMs with PagedAttention.	GitHub
YYLO	TypeScript	MIT	Command-line orchestrator for AI coding agents: runs Claude Code, Codex CLI, and Gemini CLI in parallel git worktrees with Kanban task state, typed merge flows, and per-agent skills.	GitHub
LocalAI	Go / C++	MIT	Local, OpenAI-compatible REST API for running LLMs, audio transcription, image generation, and embeddings on commodity CPU/GPU.	GitHub
AnythingLLM	JavaScript	MIT	The all-in-one Desktop & Docker AI application with full RAG pipeline, multi-agent workspaces, and complete privacy.	GitHub
Jan	TypeScript / C++	AGPL-3.0	Open-source desktop alternative to ChatGPT that runs 100% offline on local hardware with zero data leakage.	GitHub
llama.cpp	C / C++	MIT	High-performance LLM inference in pure C/C++ with minimal setup and state-of-the-art quantization across Apple Silicon and GPUs.	GitHub
LiteLLM	Python	MIT	Call 100+ LLM APIs using the standardized OpenAI input/output format with load balancing, proxy, and spend tracking.	GitHub
PrivateGPT	Python	Apache-2.0	100% private, local document question and answering engine using open LLMs without internet connection or data leaks.	GitHub
GPT4All	C++ / Python	MIT	Open-source ecosystem of consumer hardware-optimized LLMs running locally with desktop client and Python bindings.	GitHub
Khoj	Python	GPL-3.0	Open-source, personal AI second brain that searches, reasons over, and answers questions from your personal docs and notes.	GitHub
Chroma	Python	Apache-2.0	The AI-native open-source embedding database with simple Python and JavaScript client SDKs.	GitHub
Qdrant	Rust	Apache-2.0	Vector similarity search engine with extended filtering support, payload indexing, and high-performance Rust core.	GitHub
Milvus	Go / C++	Apache-2.0	Cloud-native open-source vector database built for massive scale similarity search and AI vector retrieval.	GitHub
Weaviate	Go	BSD-3-Clause	Open-source vector database that stores both objects and vectors, allowing for seamless hybrid search.	GitHub
Bark	Python	MIT	Transformer-based text-to-audio model created by Suno that can generate highly realistic speech, music, and ambient noise.	GitHub
Whisper.cpp	C/C++	MIT	High-performance inference of OpenAI's Whisper automatic speech recognition in pure C/C++ without external dependencies.	GitHub
ComfyUI	Python	GPL-3.0	The most powerful and modular stable diffusion GUI and backend with graph/nodes-based workflow interface.	GitHub
TGI (Text Generation Inference)	Rust / Python	Apache-2.0	Hugging Face's production-ready toolkit for deploying and serving Large Language Models at scale with Tensor Parallelism.	GitHub
SGLang	Python / C++	Apache-2.0	Fast serving engine for large language models and vision-language models with RadixAttention for multi-turn caching.	GitHub
TensorRT-LLM	C++ / Python	Apache-2.0	NVIDIA's specialized library providing state-of-the-art acceleration and optimized execution for LLM inference.	GitHub
ExLlamaV2	Python / C++	MIT	Fast inference library for running local LLMs on modern NVIDIA GPUs with EXL2 quantization.	GitHub
llamafile	C++	Apache-2.0	Distribute and run LLMs with a single multi-GB binary that runs across Windows, macOS, Linux, and FreeBSD.	GitHub
Aphrodite Engine	Python	Apache-2.0	High-throughput, memory-efficient LLM inference engine supporting many architectures and quantizations.	GitHub
⭐ Unsloth	Python	Apache-2.0	Finetune Llama 3.3, Mistral, and Qwen 2x-5x faster with 70% less memory using optimized hand-written GPU kernels.	GitHub
Axolotl	Python	Apache-2.0	Post-training framework for fine-tuning hundreds of open-source language models with standard YAML configurations.	GitHub
LLaMA-Factory	Python	Apache-2.0	Unified web UI and CLI for easy fine-tuning and evaluation of 100+ LLMs and multi-modal models.	GitHub
AutoAWQ	Python / C++	Apache-2.0	Activation-aware Weight Quantization package for 4-bit LLM quantization with 3x speedup.	GitHub
AutoGPTQ	Python / CUDA	MIT	Easy-to-use LLMs quantization package with user-friendly APIs, based on GPTQ algorithm.	GitHub
bitsandbytes	C++ / Python	MIT	Accessible 8-bit and 4-bit optimizers and quantization functions for deep learning on CUDA and ROCm.	GitHub
PEFT	Python	Apache-2.0	Hugging Face's state-of-the-art Parameter-Efficient Fine-Tuning library (LoRA, QLoRA, Prefix Tuning).	GitHub
TRL	Python	Apache-2.0	Transformer Reinforcement Learning library with Supervised Fine-Tuning (SFT), DPO, and PPO training loops.	GitHub
Stable Diffusion WebUI	Python	AGPL-3.0	The ubiquitous browser interface for Stable Diffusion based on Gradio library with extensive extensions.	GitHub
InvokeAI	Python / TypeScript	Apache-2.0	Professional generative AI engine and canvas for creative visual artists and digital designers.	GitHub
Fooocus	Python	GPL-3.0	Focus on prompting and generating without complex parameter tuning, inspired by Midjourney simplicity.	GitHub
LLaVA	Python	Apache-2.0	Visual instruction tuning toward large multimodal models: chat and reasoning over high-res images.	GitHub
Segment Anything (SAM)	Python	Apache-2.0	Meta's foundation model for image segmentation, allowing promptable cutouts of any object with one click.	GitHub
YOLOv8	Python	AGPL-3.0	Ultralytics YOLOv8 for real-time object detection, image segmentation, pose estimation, and classification.	GitHub
PaddleOCR	Python	Apache-2.0	Awesome multilingual OCR toolkits supporting 80+ languages, table recognition, and document structure analysis.	GitHub
⭐ Kokoro-TTS	Python	Apache-2.0	Lightweight, open-weight text-to-speech model producing studio-grade human voices with only 82M parameters.	GitHub
Piper TTS	C++	MIT	Fast, local neural text to speech system that sounds great and is optimized for Raspberry Pi and low-power hardware.	GitHub
ChatTTS	Python	CC-BY-NC-4.0	A generative text-to-speech model specifically designed for conversational scenarios and dialogue synthesis.	GitHub
Faster-Whisper	Python	MIT	Reimplementation of OpenAI's Whisper model using CTranslate2, delivering up to 4x faster transcription.	GitHub
⭐ pgvector	C	PostgreSQL	Open-source vector similarity search extension for PostgreSQL, supporting exact and approximate nearest neighbor.	GitHub
Faiss	C++ / Python	MIT	Meta's library for efficient similarity search and clustering of dense vectors, indexing billions of vectors on GPUs.	GitHub
LanceDB	Rust / Python	Apache-2.0	Developer-friendly, serverless open-source vector database for multi-modal AI with zero-copy storage.	GitHub
Vespa	C++ / Java	Apache-2.0	The open big data serving engine: store, search, organize, and machine-learn over large vector and text datasets in real-time.	GitHub
Annoy	C++ / Python	Apache-2.0	Spotify's C++ library with Python bindings to search for points in space that are close to a given query point.	GitHub
AutoRound	Python	Apache-2.0	Intel's advanced weight-only quantization algorithm for low-bit LLM optimization without accuracy degradation.	GitHub
FastChat	Python	Apache-2.0	An open platform for training, serving, and evaluating LLM-based chatbots, the core engine behind LMSYS Chatbot Arena.	GitHub
GPTCache	Python	MIT	Semantic cache for LLM queries to cut costs and speed up response time up to 10x using vector similarity.	GitHub

Web UI & Chat (2)

Tool	Language	License	Description	Links
Open-WebUI	Python / Svelte	MIT	User-friendly AI interface designed for self-hosting with complete Ollama and OpenAI-compatible API support.	GitHub
LibreChat	TypeScript	MIT	Enhanced, self-hostable open-source AI chat platform unifying OpenAI, Anthropic, Gemini, and local LLMs.	GitHub