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.
Orchestrates a lead agent, isolated parallel sub-agents, long-term memory, and sandboxes for long-horizon tasks — minutes to hours of deep research, coding, and content creation. LangChain/LangGraph-based with extensible skills; v2 is a full rewrite.
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).
Framework for building an organization's internal coding agents — runs tasks in isolated cloud sandboxes, integrates with Slack/Linear/GitHub, orchestrates subagents, and automates commits/PRs. Built on LangGraph and Deep Agents for easy customization.
Packages an AI agent's memory — data, embeddings, search indexes, and metadata — into one portable .mv2 file, replacing multi-service RAG stacks. Combines BM25 and HNSW search with temporal queries and sub-millisecond local reads, fully offline.
Wraps Claude Code as an MCP server that orchestrates 100+ specialized agents into self-organizing swarms — hierarchical, mesh, or adaptive consensus — backed by persistent vector memory, coordination hooks, and secure cross-machine federation.
Gives AI coding assistants a queryable index of n8n's 2,000+ workflow nodes — their real properties, operations, and 2,300+ templates — so generated workflow JSON validates instead of hallucinating node names and connections.
Run Claude as a programmatic agent in Python: one-shot query() calls or a stateful ClaudeSDKClient for multi-turn loops. Define in-process tools, lifecycle hooks, and per-tool permissions; it bundles the Claude Code CLI and exposes its full toolset.
Curated marketplace of community-contributed GitHub Copilot customizations — reusable agents, file-scoped instructions, skills, plugins, hooks, and agentic workflows — installable via the Copilot CLI and searchable on a companion site.
Orchestrates 10+ coding agents (Claude Code, Codex, Gemini CLI) from a kanban board: plan tasks as issues, then run each in an isolated workspace with its own branch, terminal, and dev server. Inline diff review and one-click PR creation.