Tag
Explore by tags
Turns a raw idea, novel, or screenplay into a complete multi-shot video through a multi-agent pipeline that scripts, storyboards, and renders shots while a vision model checks character and scene consistency across the whole story.
Twelve engineering principles for building production-grade LLM agents, modeled on the 12-Factor App. Argues the best agents are mostly deterministic software with a few well-placed LLM calls, not a prompt-and-tools loop.
Generates full-stack web apps with the backend included — database, auth, file uploads, real-time UIs, and background workflows — by writing code against Convex's reactive APIs. A fork of bolt.diy; bring your key for Claude, GPT, Gemini, or Grok.
Builds a table-of-contents tree index over long PDFs and uses LLM tree search to fetch relevant sections — no embeddings, chunking, or vector database. Hits 98.7% on FinanceBench, for financial, legal, and technical docs where relevance needs reasoning.
Builds, evaluates, and deploys multi-agent systems in Python, code-first. A graph-based runtime handles routing, fan-out/fan-in, loops, retries, and human-in-the-loop; a Task API covers agent-to-agent delegation, plus a CLI and web UI.
Provides ready-to-use sample agents for Google’s Agent Development Kit across Python, TypeScript, Go, Java, Kotlin, and Android, from simple assistants to multi-agent workflows.
Orchestrates AI coding agents around tasks, sessions, artifacts, reviews, and parallel Claude Code workflows so teams can manage complex codebase work with more visibility.
Autonomously proposes hypotheses, runs experiments, analyzes results, and drafts workshop-level papers via an agentic tree-search pipeline. Unlike template-driven predecessors, it explores open-ended ML research paths but requires GPU/PyTorch and careful sandboxing due to execution of LLM-written code.
Argues AI has entered its 'second half': a working recipe (language pre-training priors + scale + reasoning) now generalizes RL across tasks, so the bottleneck shifts from inventing methods to defining problems and rethinking evaluation.
Lets LLM agents drive real Android and iOS devices from natural-language commands by turning each screen's accessibility tree into structured text the model reads directly, not just screenshots. LLM-agnostic; runs via CLI, Python, or Docker.
Brings Gemini models into the terminal as an agent that reads files, runs shell commands, and edits code in place. Includes Google Search grounding, MCP server support, and a free OAuth tier (60 req/min, 1,000 req/day) with a 1M-token context window.
Builds production-grade AI agents and multi-agent workflows in .NET and Python, with graph-based orchestration for sequential, concurrent, and handoff patterns. Unifies Microsoft's Semantic Kernel and AutoGen lineages, adding durable, checkpointed runs.