Tag
Explore by tags
A human-verified subset of 500 SWE-bench test cases for evaluating models that resolve GitHub issues into PRs using unit-test verification. Contains problem statements and base commits (pre-fix) for reproducible unit-test based evaluation; suitable for benchmarking code-fix and issue-resolution capabilities.
Official reference code for building browser-controlling agents on Google's Gemini computer-use models. The model sees a screenshot, proposes a UI action, and the loop executes its clicks, typing and scrolling via local Playwright or cloud Browserbase.
Real-time, streaming world model for interactive long-horizon video and scene generation — provides persistent memory across interactions, streaming inference for live scenarios, and example demos for building interactive environments.
Converts document images—scans, photos, born-digital PDFs—into structured text in two stages: first map layout and reading order, then parse each element (text, tables, formulas, figures) in parallel, each guided by its own task prompt.
Converts PDFs into AI-ready structured outputs (Markdown, JSON with bounding boxes, HTML) for RAG and accessibility workflows; offers deterministic local parsing plus a hybrid AI mode for complex tables, OCR, formulas, and auto-tagging previews.
Transforms research papers, natural-language specs, and technical descriptions into runnable code via a multi-agent system. Covers Paper2Code, Text2Web, and Text2Backend; scores 75.9% on OpenAI's PaperBench, ahead of top ML PhDs.
Builds production AI agents around a model-driven loop with provider abstraction, tools, guardrails, streaming, MCP, tracing, and multi-agent patterns across Python and TypeScript SDKs.
Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).
Drops Claude Code into GitHub Actions so it responds to @claude mentions in PRs and issues — answering questions, reviewing diffs, and committing fixes or features on a branch. Runs on your runners via the Anthropic API, Bedrock, or Vertex AI.
Enables bidirectional checkpoint conversion between Hugging Face and Megatron formats and provides a PyTorch-native training library with tensor/pipeline parallelism, FP8/BF16 mixed precision, SFT and PEFT (LoRA) support for large and multimodal models.
Translates full-length books, subtitles, and documents with LLMs while preserving original formatting and structure. Uses intelligent chunking to handle arbitrarily long files, supports local or cloud providers, and resumes interrupted jobs without losing progress.