Packs a Git repository into a single AI-friendly file for easy ingestion by LLMs. Offers per-file and total token counts, optional Tree-sitter compression, secret scanning, and multiple interfaces (CLI, web, browser extension, Docker, MCP) for AI-driven code review and analysis.
Open-source platform for autonomous coding agents that work like developers: editing files, running shell commands, browsing the web, and calling APIs in an isolated sandbox. Model-agnostic, with GitHub, Slack, and CI/CD integration.
Reviews code in the IDE, CLI, and pull requests, flagging bugs, logic gaps, security holes, and missing tests using context from the whole repo and its dependencies. Enforces team-specific rules learned from past PRs.
Generates and deploys full-stack React apps from natural-language prompts on Cloudflare’s platform, combining AI code generation, previews, Workers, Durable Objects, and containers.
A GitHub repository of learning notes and code dedicated to ML + SYS (machine learning systems). It collects tutorials, code walkthroughs and engineering notes on RLHF, distributed training (FSDP, Megatron), inference and scheduling (SGLang, vllm), quantization, CUDA/GPU optimization, system design, and practical engineering.
Keeps the former Windsurf IDE lineage alive as Devin Desktop, a local editor for planning, delegating, reviewing, and shipping code with cloud and local agents from one surface.
Terminal-native AI coding agent that brings conversational, multi-model code assistance into your shell. Integrates with 300+ models and providers, offers an interactive TUI, Zsh ':' plugin, semantic workspace search, and Git-oriented workflows for in-terminal edits, commits, and command suggestions.
Structures AI-assisted development as deterministic YAML workflows—planning, implementation, validation, review, and PR creation—so agent runs are repeatable and isolated. Mixes deterministic nodes with AI nodes and runs from CLI, Web UI, or chat integrations.
A curated dataset of ~30,000 CUDA kernels generated by an agentic pipeline, including reference PyTorch implementations, runtime metrics, NCU/Torch/Clang-Tidy profiles, error messages and correctness labels — released under CC-BY-4.0 for model fine-tuning and offline RL/optimization research.
Feeds simplified Figma layout and style metadata to AI coding agents like Cursor and Claude Code to implement designs in one shot. Sends descriptive JSON (1px border, 16px padding) rather than code, leaving framework choices to the model.
Performs fast static type checking and provides a language server with code navigation, semantic highlighting, and completions for Python. Processes ~1.85M lines/sec and completes IDE rechecks typically under 10ms — intended for responsive editor workflows and large codebases.
A benchmark dataset for evaluating MLLM-driven interactive webpage code generation: provides prototyping screenshots, action.json interaction metadata, and example generation scripts across 127 webpages and 374 interactions to test dynamic UI-to-code capabilities.