A strictly vetted directory of open-source artificial intelligence repositories, local LLM engines, multi-agent frameworks, and vector search tooling. Annotated with personal engineering takes from production builds.
Curated Open-Source AI Repositories
modelcontextprotocol/servers ↗
Reference implementations for Model Context Protocol (MCP) servers (Postgres, SQLite, Git, Filesystem, Slack).
“The definitive gold standard for how LLM agents interact with local databases, system tools, and APIs cleanly without messy custom glue code.”
anthropics/anthropic-sdk-python ↗
Official Python client library for Anthropic Claude models, tools, and batch processing.
“Remarkably clean async client with native prompt caching and tool-use support that outperforms raw HTTP requests in production.”
google-gemini/generative-ai-python ↗
Official Python SDK for the Google Gemini API, structured outputs, and multimodality.
“Massive context windows (up to 2M tokens) and native image/audio understanding make this essential for deep analysis agents.”
vllm-project/vllm ↗
A high-throughput and memory-efficient inference and serving engine for LLMs using PagedAttention.
“The backbone of self-hosted open LLM deployments. 2-4x higher throughput than HuggingFace TGI.”
langchain-ai/langgraph ↗
Build resilient language agents as graphs with cyclical loops, human-in-the-loop, and persistence.
“Provides state-machine determinism to AI agent loops instead of leaving multi-step workflows to random chance.”
run-llama/llama_index ↗
Context augmentation framework for LLM applications with advanced RAG indexing and retrieval.
“Best-in-class data connectors for PDFs, Notion, SQL, and enterprise data with hybrid retrieval.”
remotion-dev/remotion ↗
Make programmatic videos with React and CSS motion design.
“Programmatic video rendering engine that turns React components into frame-accurate 60fps MP4 reels.”
n8n-io/n8n ↗
Fair-code workflow automation platform with native AI agent nodes and LangChain integrations.
“Visual workflow canvas with full self-hosting control and native AI agent routing.”
ollama/ollama ↗
Get up and running with Llama 3, Mistral, and other large language models locally.
“The Docker for local LLMs. Run 8B and 70B parameter open-weights models on Apple Silicon with 1 command.”
BerriAI/litellm ↗
Call 100+ LLMs using the OpenAI Input/Output Format with proxy routing, fallbacks, and cost tracking.
“Unified interface for OpenAI, Anthropic, Gemini, Groq, and Bedrock with automatic fallback switching when an API is down.”
browser-use/browser-use ↗
Make websites accessible for AI agents via Playwright and visual vision models.
“Enables agents to interact with modern complex SPAs, solve captchas, and execute browser workflows autonomously.”
crewAIInc/crewAI ↗
Framework for orchestrating role-playing, autonomous AI agents for collaborative intelligence.
“Intuitive role-based mental model (Researcher, Writer, Auditor) that makes complex multi-agent swarms easy to conceptualize.”
microsoft/autogen ↗
A framework for building multi-agent conversational systems and group chat dynamics.
“Groundbreaking architecture for autonomous agent-to-agent code generation and execution loops.”
qdrant/qdrant ↗
High-performance vector similarity search engine with extended filtering support in Rust.
“Blazing fast vector lookup with rich metadata payload filtering, written in Rust with minimal memory footprint.”
chroma-core/chroma ↗
The AI-native open-source embedding database for rapid prototyping and local vector search.
“Zero-setup embedded database that lets you spin up local vector search in 3 lines of Python.”
openai/whisper ↗
Robust Speech Recognition via Large-Scale Weak Supervision.
“State-of-the-art multilingual audio transcription that forms the backbone of all video subtitle pipelines.”
AUTOMATIC1111/stable-diffusion-webui ↗
Stable Diffusion web UI for image synthesis, ControlNet, and LoRA experimentation.
“The open powerhouse for generative visual pipelines, ControlNet pose locking, and localized inpainting.”
activepieces/activepieces ↗
Open source business automation tool and Zapier alternative with TypeScript-first pieces.
“Clean TypeScript piece architecture makes writing custom integrations and internal API connectors effortless.”
searxng/searxng ↗
A privacy-respecting, open metasearch engine ideal for grounding AI search agents.
“Gives autonomous agents unmetered, privacy-first web search capabilities without expensive SERP API quotas.”
Significant-Gravitas/AutoGPT ↗
The vision of accessible AI for everyone, to use and to build on.
“The pioneering repository that ignited the entire autonomous agent revolution in early 2023.”