Flue: A TypeScript Framework for Building Autonomous Coding Agents

Flue is a TypeScript framework for building autonomous agents using a programmable harness architecture — the same pattern behind Claude Code and Codex. It lets you define agents that plan, gather context, write files, spawn subagents, and run shell commands, all within a sandboxed environment.
Key Features
- Agent Harness: Combines a model (e.g., Anthropic Claude Sonnet 4-6) with a harness for tools like filesystem read/write, grep, glob, bash execution, and network access.
- Sessions: Persistent contexts for tracking work, similar to Claude Code or Codex sessions.
- Skills: Reusable workflows with structured output using Valibot for runtime validation.
- Sandbox: Built-in zero-config virtual sandbox, or connect your own remote sandbox. Fine-grained control over environment variables and token exposure.
- Deployment: Agents bundle into an HTTP server for remote use, or run via CLI (
flue run) for local tasks and CI.
Example: AI Issue Triage in 22 Lines
import type { FlueContext } from '@flue/sdk/client';
import { Octokit } from '@octokit/core';
import * as v from 'valibot';
export default async function ({ init, payload, env }: FlueContext) {
const { issueNumber } = payload;
const agent = await init({ model: 'anthropic/claude-opus-4-7' });
const session = await agent.session();
const triage = await session.skill('triage', {
args: { issueNumber },
result: v.object({
severity: v.picklist(['low', 'medium', 'high', 'critical']),
reproducible: v.boolean(),
summary: v.string(),
}),
});
const body = **Severity:** ${triage.severity}\n**Reproducible:** ${triage.reproducible}\n\n${triage.summary};
await (new Octokit({ auth: env.GITHUB_TOKEN })).request(
'POST /repos/{owner}/{repo}/issues/{num}/comments',
{ owner: 'withastro', repo: 'flue', num: issueNumber, body },
);
}
Who It's For
Developers building custom AI agents for code review, issue triage, data analysis, customer support, or coding automation who want full control over the agent stack without renting a third-party tool.
📖 Read the full source: HN LLM Tools
👀 See Also

Claude Code Skills for Automated Project Scaffolding
A developer has built Claude Code skills that automate full-stack project setup with commands for React, Next.js, Node.js APIs, and Turborepo monorepos. The skills pull latest dependencies, support 50+ integrations, and are MIT licensed.

MultiModel Code Review Workflow Packaged as Reusable Skill
A reusable skill that orchestrates multiple AI models for PR and non-PR code reviews, tested with OpenClaw and models like GPT-5.5, DeepSeek V4 Pro, Kimi K2.6, Qwen 3.6 Plus, and GLM-5.1.

alogin: A Go-based Security Gateway for AI Agents with Human-in-the-Loop
alogin is an open-source Go-based security gateway that provides a secure conduit between AI agents and infrastructure, featuring built-in MCP server support for Claude Desktop, human-in-the-loop safety rails, and encrypted credential storage.

Maggy: An Autonomous Engineering Platform on Claude Code with Cross-Session Memory and P2P Team Learning
Maggy sits at Level 4 of the AI coding tool spectrum: multi-model orchestration, cross-session memory, process intelligence from CI/reviews, and P2P team learning. Benchmarks show 83% reduction in Claude usage while catching 7 security issues missed by single-pipeline Claude Code.