Constrained generation library for LLMs. Uses finite state machines to mask invalid tokens during generation. Guarantees schema-compliant output with zero retries.
Outlines is a Python library from .txt (dottxt) that pioneered grammar-based constrained generation for language models. Instead of validating output after the fact, Outlines uses a finite state machine to mask invalid tokens during generation, so the model can only produce schema-compliant output. It supports JSON Schema, regex, and full context-free grammar (CFG/EBNF) constraints. The same code runs across OpenAI, Ollama, vLLM, and Hugging Face models. The outlines-core Rust port (in collaboration with Hugging Face) delivers a 2x improvement in index compilation speed. For developers running local models who need guaranteed schema compliance with zero retries, Outlines is the tool. It excels at research, custom grammars, and self-hosted LLM prototyping where deterministic output is non-negotiable.
Multi-agent orchestration framework built on the OpenAI Agents SDK. Define agent roles, typed tools, and directional communication flows. Production-focused, open-source.
Type-safe Python agent framework from the Pydantic team. Brings the FastAPI feeling to AI development. Composable tools, durable execution, and full IDE autocomplete.
Structured data extraction from any LLM using Pydantic models. Automatic retries, validation, and streaming. 3M+ monthly downloads. Available in Python, TypeScript, Go, Ruby, and Rust.
Open-source AI orchestration framework by deepset. Modular pipelines for RAG, agents, semantic search, and multimodal apps. Pipeline-as-graph architecture with explicit control.
Constrained generation library for LLMs. Uses finite state machines to mask invalid tokens during generation. Guarantees schema-compliant output with zero retries.
Try OutlinesHonest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeThe TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 50K+ GitHub stars.
Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.
Anthropic's Python SDK for building production agent systems. Tool use, guardrails, agent handoffs, and orchestration. Released alongside Claude 4.
Deep comparison of the top AI agent frameworks - LangGraph, CrewAI, Mastra, CopilotKit, AutoGen, and Claude Code.
AI AgentsInstall the dd CLI and scaffold your first AI-powered app in under a minute.
Getting StartedConfigure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
AI Agents
Google released DiffusionGemma today, a 26B MoE open model that generates entire 256-token blocks in parallel instead of...

An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no c...

A CS student built 30papers.com to make Ilya's legendary ML reading list more accessible. HN has thoughts on the source,...

IEEE Spectrum reports on pharmaceutical AI running on handheld devices. HN debates emergency kits, domain-specific model...

A new study from Dartmouth measures the impact of an AI tutoring platform on introductory statistics performance. Full e...

Comparing LLMs by token pricing alone can lead you to choose worse, more expensive models. Cost per task tells the real...

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.