Tag
Explore by tags
Runs a local AI assistant across WeChat/Feishu/DingTalk/WeCom/QQ/MP/Web, with an Agent mode for task planning, long-term memory, Skills, and tool calling so it can keep working toward goals rather than just chat.
Lets LLMs run code and control a user’s computer via natural language (Python, JavaScript, Shell, etc.) with interactive approval. Supports local or hosted models, terminal and Colab/Codespaces integrations, streaming output, and configurable safety/auto-run options.
Orchestrates and coordinates multiple coding agents in a shared, cross-device workspace — preserving context, files, and durable artifacts so teams can run parallel agent workflows without losing intent or state.
Desktop finance analytics terminal that combines CFA-level models, real-time trading and 100+ data connectors with embedded Python for analytics; includes 37 AI agents and local/multi-provider LLM support for automated research and decision workflows.
Brings an agentic chat experience to the terminal: describe a task in natural language and it plans, edits files, and runs commands to build the app. Written in Rust, ships on macOS and Linux. Now succeeded by the closed-source Kiro CLI.
Evaluates and optimizes AI agents and language models in containerized environments, supporting large-scale parallel benchmarks and RL rollouts. Integrates with third‑party providers for thousands of parallel environments and serves as the official harness for Terminal‑Bench.
Extensible AI coding-agent toolkit offering a terminal-first coding agent CLI, a unified multi-provider LLM API, TUI and web UI libraries, Slack integration, and vLLM pod support—built to prototype and run agent-driven developer workflows.
Provides a set of Claude Code skills that let an LLM-driven agent control Browserbase via browser automation and the official bb CLI — includes browser automation with anti-bot/solver support, cookie sync, fetch/tracing, site-debugging, and serverless function workflows.
Provides 22 scripts that let Claude Code build, test, and interact with iOS apps by wrapping xcodebuild and controlling the simulator via simctl/idb. Uses accessibility-driven UI navigation, progressive build summaries, and compressed screenshots to cut token cost and fragility for AI agents and developers.
Indexes full text of visited web pages and local files on a self‑hosted server so you can search your personal knowledge from a web UI, terminal, CLI, or an AI assistant. Runs without mandatory telemetry, offers a browser extension for automatic capture, and supports optional semantic search via a configurable embeddings endpoint.
Grows a personal skill tree by crystallizing each solved task into reusable skills; a ~3K-line autonomous agent framework that gives an LLM system-level control of browser, terminal, filesystem, input/vision and mobile (ADB) via nine atomic tools, optimized for low token cost.