fast-agent, inside Glueprint.
Code and build agents with comprehensive multi-provider support. Glueprint runs fast-agent over the Agent Client Protocol it already speaks — adding live sessions on every device, approvals from your phone, parallel worktrees, schedules, and memory.
fast-agent
enquiries@fast-agent.ai
- Agent
- fast-agent
- Maintainer
- enquiries@fast-agent.ai
- Connection
- Agent Client Protocol
- Wire format
- JSON-RPC 2.0 over stdio
- Registry version
- 0.9.2
- License
- Apache 2.0
What is fast-agent?
fast-agent is an open-source agent framework for defining, building, and evaluating agents from the terminal. It offers a Python API, a Harness API, and an interactive TUI, with native support for Anthropic, Google, and OpenAI plus OpenAI-compatible endpoints, local models via llama.cpp, and providers such as xAI, Azure, and Bedrock. It supports both Model Context Protocol and Agent Client Protocol, along with Agent Skills, structured outputs, and a Python plugin system.
- Python API plus interactive terminal UI
- Native Anthropic, Google, and OpenAI support
- Local models via llama.cpp
- Both MCP and ACP protocol support
- Agent Skills, structured outputs, plugin hooks
Best for Python developers building and evaluating multi-provider agents from the terminal.
Sourced from fast-agent's official site and repository.
How Glueprint runs fast-agent
fast-agent connects over the open Agent Client Protocol — one generic adapter implements the protocol's client side, so fast-agent gets the same surfaces as every other harness:
Glueprint spawns fast-agent, not a fork
Glueprint finds the fast-agent binary you installed and spawns it, then speaks the Agent Client Protocol — JSON-RPC 2.0 over stdio — to drive it. Same CLI, same authentication; Glueprint just wraps the session.
Output streams as structure
Message chunks, tool calls, and tool-call updates from fast-agent arrive as protocol notifications and render as the same live, typed timeline every Glueprint session gets — watchable from desktop, browser, or phone.
Permission requests become approval cards
When fast-agent asks to write a file or run a command, the protocol's permission request surfaces as an inline approval card on whatever device you're holding. Approve, deny, or auto-allow per tool.
One adapter, the whole fleet
Because fast-agent speaks ACP, adding it is a catalog entry, not an engineering project — the same adapter runs every other agent in the registry, so you can tile them side by side.
What fast-agent gains inside Glueprint
Everything below works with the fast-agent CLI you have today — no migration, no new account for the model, no lock-in. Uninstall Glueprint and your terminal workflow is exactly as it was.
Live sessions on every surface
Watch every fast-agent prompt, tool call, and diff stream in real time — desktop, web portal, iOS and Android. The session runs on your machine; the view follows you.
Approve from your phone
Permission prompts arrive as approval cards wherever you are. Kick off a refactor at your desk, approve the file writes from the couch.
Parallel sessions across worktrees
Run several fast-agent sessions side by side, each in its own git worktree, with diffs, history, and a three-pane conflict resolver alongside.
Mix harnesses in one mosaic
Tile fast-agent next to Claude Code, Codex, and the rest of the ACP fleet in the Command Center. The protocol differs; the surface doesn't.
fast-agent as a persistent assistant
Promote it to an assistant: persona, constitution, long-term memory, and a daily journal on disk, loaded into every wake.
Routines on a schedule
Wake it on cron: triage the inbox every 30 minutes, sweep PRs at 9am, run the nightly cleanup. Quiet hours and watermarks prevent re-fires.
Analytics per harness
Messages, sessions, and output tokens computed from session logs — compare fast-agent against Claude Code, Codex, and your other ACP agents.
Encrypted to the relay
Remote viewing rides AES-256-GCM envelope encryption. The relay routes; it cannot read.
fast-agent + Glueprint, asked plainly
Can I run fast-agent with Glueprint?
Yes. fast-agent is registered in the official Agent Client Protocol registry, and Glueprint implements the protocol's client side. It spawns the fast-agent CLI you already installed and drives it over JSON-RPC 2.0 — adding live sessions, inline approvals, worktrees, and remote control.
Do I need a separate fast-agent subscription or API key?
No. Glueprint doesn't resell model access. fast-agent authenticates exactly the way its vendor designed — its own login, subscription, or API key. Glueprint spawns the binary and speaks the protocol; it doesn't sit between you and the model provider.
Can I run fast-agent from my phone?
Sessions always run on your machines — a laptop, a desktop, or a server with the headless daemon. The iOS and Android app streams fast-agent sessions live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run fast-agent next to Claude Code and Codex?
Yes — that's the point. Each harness is an adapter; sessions from all of them tile into the same Command Center, share the same task boards, and roll up in the same per-harness analytics.
Is my session content private?
Yes. Remote viewing routes AES-256-GCM-encrypted envelopes through the relay, which stores a wrapped key it cannot open — decryption happens on your devices. On the free local tier, session content never leaves your machine at all. See security.
Bring Glueprint to your workflow.
Download once, run on your hardware, scale up to teams when you're ready. No credit card.