fast-agent

Name: fast-agent Review
Item: fast-agent
Rating: 3.8
Author: Aaron Matthews

Skill Development Solid

Works inClaude Code

Solid Scanned — metadata only

Reduces agent development cycle time by combining coding, building, and evaluation in one workflow.

fast-agent is a Python framework and CLI for building, running, and evaluating LLM agents and workflows — usable as an interactive coding agent or as a declarative multi-agent framework. It is the first framework with complete end-to-end-tested MCP feature support (including sampling and elicitations), supports Agent Skills (SKILL.md), ACP clients, and shell mode, and works with Anthropic, OpenAI, Google, Azure, Ollama, and local models. Start instantly with uvx fast-agent-mcp@latest -x.

Build autonomous agents that write and test their own code without manual intervention
Evaluate agent performance across different models to find the fastest, most accurate version
Integrate custom skills and MCP protocols into agents for specialized development tasks

3,893 starsApache-2.0 (commercial OK)FreeQuick setup

Why it matters

Reduces agent development cycle time by combining coding, building, and evaluation in one workflow. Supports multiple model backends and protocol standards, lowering switching costs and vendor lock-in risk.

Best for

AI/ML engineering teams building and testing production agents at scale.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/evalstate/fast-agent

By evalstate

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

uv tool install -U fast-agent-mcp   # or run without installing: uvx fast-agent-mcp@latest -x

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me build autonomous agents that write and test their own code without manual intervention

Prerequisitesuv (Astral's Python package manager); an API key for your chosen model provider or a local modelCostFree

Trust Signals Auto-scanned

Stars3,893Contributors76Last updated2026-08-17LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-18 · scanner v1

Community Pulse Growing

Discussed on Hacker News

Show HN: Fast-agent – Compose MCP enabled Agents and Workflows in minutes — Hacker News · 29 pts
rag not lag: rl for fast agentic retrieval — Hacker News · 3 pts
Cognition – Introducing SWE-1.5: Our Fast Agent Model — Hacker News · 2 pts

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 3,844 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

4/5

Versatility

5/5

Reliability

3/5

Security

3/5

Overall score3.85 / 5.00 SolidEvaluatedJun 2026

Scored from trust signals (evidence-eval-v1): 3,844 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory