Download docs/llms.txt from graphene-lab/AgentBridge: direct link, hf CLI and curl.
- Browser
- Download file 2.4 kB
-
https://huggingface.co/graphene-lab/AgentBridge/resolve/main/docs/llms.txt
- Command line
-
hf download hf://graphene-lab/AgentBridge/docs/llms.txt
-
curl -L -o llms.txt https://huggingface.co/graphene-lab/AgentBridge/resolve/main/docs/llms.txt
2.4 kB
| # AgentBridge | |
| > AgentBridge is a self-hosted server that runs AI agents with two interfaces in a single process: a full-screen chat terminal (TUI) and a standard HTTP API compatible with OpenAI, plus a native MCP connector. It automates office work (documents, spreadsheets, email, presentations, web research) while your data stays on your machine inside an application-level sandbox. Self-contained archives (~460 MB, no .NET needed) run on Windows x64, Linux x64/ARM64 and macOS (Intel / Apple Silicon), and work with local models (Ollama, ExLlamaV2) or cloud providers (DeepSeek, Z.ai, Gemini, Anthropic) with GDPR-ready anonymization. Reachable 24/7 via SIP phone and Telegram. | |
| ## User documentation | |
| - [User manual](https://graphenelab.it/AgentBridge/MANUAL.md): install, configure the JSON files, use the terminal UI, connect a client to localhost — start here | |
| - [Terminal UI reference](https://graphenelab.it/AgentBridge/TUI.md): every command, shortcut and mouse action | |
| - [HTTP API reference](https://graphenelab.it/AgentBridge/API.md): all endpoints — chat, sessions, LLM switching, TTS, voice, files, MCP connector | |
| - [Telegram chat](https://graphenelab.it/AgentBridge/telegram.md): connect the agents to Telegram — config, first login, allow-list, attachments | |
| - [SIP telephony](https://graphenelab.it/AgentBridge/sip.md): phone-gate the agents — config, PIN/allow-list security, NAT/trunk, STT deployment | |
| - [Auto-update](https://graphenelab.it/AgentBridge/autoupdate.md): how the automatic update works and what it never touches | |
| - [AIOrchestrator white paper](https://graphenelab.it/AgentBridge/AIORCHESTRATOR-WHITEPAPER.md): why the AIOrchestrator library model outperforms MCP deployments | |
| ## Download | |
| - [Download for your OS](https://graphenelab.it/AgentBridge/download/): auto-detect page with direct archive links | |
| - [Windows installer](https://graphenelab.it/AgentBridge/install.ps1): one-line PowerShell install | |
| - [Linux/macOS installer](https://graphenelab.it/AgentBridge/install.sh): one-line shell install | |
| ## Source code | |
| - [GitHub repository](https://github.com/Graphene-Lab/AgentBridge): source, issues and releases | |
| - [README](https://raw.githubusercontent.com/Graphene-Lab/AgentBridge/master/README.md): overview, features and FAQ | |
| ## Optional | |
| - [Andrea Bruno License 1.4](https://github.com/Graphene-Lab/AgentBridge/blob/master/LICENSE.md): license and terms of use | |