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
All Categories
Agent Frameworks
AI Operations
Automation
Content
Data & Storage
Inference & Serving
Infrastructure
Learning
LLM SDKs
LLM Tooling
MCP & Tooling
RAG & Vector Search
Search & Grounding
Video & Media
Workflow Orchestration
LLM TOOLING
stanfordnlp/dspy ↗
★ 38,656
Framework for algorithmically optimizing LLM prompts and weights through teleprompters rather than hand-crafted strings.
Why It's Essential:
“Instead of spending 3 days guessing adjectives in a prompt to improve extraction accuracy, DSPy treats prompts as modular programs and uses Bayesian optimization against ground-truth validation datasets to auto-tune instruction weights. It boosted a client legal-contract extraction pipeline from 78% to 94.2% accuracy without manual prompt editing.”