GigaAgent overview
GigaAgent is a modular agent framework with a FastAPI backend, a LangGraph execution graph, and a bundled React web UI. The giga_agent dev command starts a local server on port 9090 and serves both the API and the UI.
Main parts
| Part | Purpose |
|---|---|
giga_agent Python package | CLI command, backend, execution graph, modules, and migrations. |
| Web UI | Chat, settings, RAG collections, memory, administration, and files. |
| Execution graph | Controls model calls, tool calls, streaming, and callbacks. |
| Modules | Add authentication, RAG, memory, search, images, file operations, skills, deep research, and integrations. |
| Providers | Language models, embeddings, search, image generation, and sandbox runtimes. |
What the agent can do
Useful work requires a configured language model. Depending on user settings, the agent can use chat streaming with clarifying questions, files, RAG, long-term memory, agent skills, deep research, images, code execution, weather, search, and legacy subagents kept for compatibility (landing page, presentation, meme, and more).
External services connect through the connectors catalog: MCP servers, Yandex Mail, Calendar, and Disk, VK, GitHub. Results of some tools render as chat widgets. The agent also runs scheduled tasks with delivery to a Telegram channel.
Start here
- Install and run the repository build: Local quickstart.
- Configure a model and send the first message: First chat.
- Review feature prerequisites: Capabilities and requirements.
- For shared installations, read Shared server.
- For implementation details, read Architecture.