Tag: Indie Dev - Blog ArceApps

Codex September 10, 2026

Codex Agent Router: Orchestrating External Agents

Configure Codex Agent Router to delegate to native subagents or route work to OpenCode, MiniMax, Big Pickle, and Antigravity from one interface.

DeepSeek August 20, 2026

DeepSeek Harness: the runtime where everything is a plugin

DeepSeek Harness (dsh) is an MIT open-source runtime where model, tools, session, sandbox and even the loop are plugins. Deep-dive into Cordis, runtime modes, append-only session log and self-evolution.

DeepSeek August 19, 2026

DeepSeek Harness vs OpenCode, Codex and Claude Code: head to head

Honest comparison of DeepSeek Harness (dsh), OpenCode, Codex CLI and Claude Code. Philosophy, plugin model, sandbox, ecosystem and who wins each in 2026.

OpenChamber August 16, 2026

OpenChamber: the agentic cockpit that supervises - OpenCode

OpenChamber in depth: the 6 features of v0.7 (Session Goals, Multi-run with Fusion, Changes Walkthrough, Preview, issue-to-PR, cron), the supervision architecture around the OpenCode SDK, and the context of Bohdan Triapitsyn building the missing cockpit in the ecosystem.

Paseo August 15, 2026

Paseo: the coding agent orchestrator that rewrote the category

Paseo in depth: daemon+relay architecture in Elixir, 35+ providers via ACP, TypeScript SDK, three skills (Handoff, Advisor, Committee), and RFC #1042 explaining why it migrated to the Agent Client Protocol. A case study of solo open source done right.

OpenChamber August 14, 2026

OpenChamber, Paseo, CodeNomad, opencode-mobile: 2026 comparison

Four visual frontends for coding agents tested on desktop and mobile. Paseo as multi-provider orchestrator, OpenChamber as full cockpit, CodeNomad as premium IDE, opencode-mobile as native Android. Primary data from repos and HN.

SDD August 11, 2026

Spec-Driven Development: The Developer Role Redefined

How Spec-Driven Development flips the developer from typist to architect of intent. Inside the 40-60% waste map, the three maturity levels, and the Spec-as-Source role shift that ends vibe coding.

Intent-Driven Development August 10, 2026

IDD: Intent-Driven Development with FORGE and AISpec

Intent-Driven Development shifts the question from 'how to build' to 'what result we want'. FORGE and AISpec turn your intent into verifiable software. Analysis with examples.

Dark Factory August 9, 2026

Dark Factory: The Self-Evolving Software Factory

The dark factory takes AI agent autonomy to the extreme: code that writes, tests and ships without human review. Real cases, infrastructure and risks.

OpenCode July 26, 2026

Awesome OpenCode: The Ecosystem Zoo

A curated map of the OpenCode ecosystem in 2026: 10 persistent-memory plugins no blog has shown you, 4 real Hacker News critiques, and the indie community's defensive response.

OpenCode July 26, 2026

OpenChamber, CodeNomad, nomacode, opencode-mobile: honest OpenCode comparison

Four visual clients for OpenCode put through real work on desktop and mobile. We compare install, day-to-day feel, remote access setup, and the parts each one still falls short on, with primary data from their own repos.

OpenCode July 25, 2026

Model Routing for Subagents: Cut Coding Agent Costs 30-80%

Route each subagent to the right model: explore to 9B, planner to 122B. Brick, OpenCode-subagent-router, and a DIY hook compared with real cost math.

RTK July 15, 2026

RTK vs Caveman: real token savings in AI agents

RTK and Caveman promise 60-90% token cuts in agents. I measure both with real data: JetBrains' 8.5% finding, a 614M-token replay and the output-vs-prose gap.

AI July 14, 2026

HyperFrames vs Remotion 2026: The Definitive Comparison

HyperFrames vs Remotion 2026: the definitive technical comparison for AI agent video. React vs HTML, licensing, benchmarks, and Agent Skills.

Harness Engineering July 2, 2026

Harness Engineering: The Wrapper Wins

Harness Engineering explained: why the wrapper (tools, memory, guardrails) makes agents productive. Definition, anatomy, and real indie application.

AI June 16, 2026

Native OpenCode Plugins for Persistent

Comparative technical analysis of three native OpenCode plugins to give your AI agent persistent local memory: simple-memory (logfmt), Mnemosyne (offline Go binary), and true-mem (cognitive psychology).

AI June 12, 2026

Cross-Agent MCP Servers for Persistent

Exhaustive technical comparison of three cross-platform MCP servers to give AI agents persistent memory: opencode-supermemory (cloud), basic-memory (Markdown + graph), and forgetful (atomic Zettelkasten). Works with Claude Code, Codex, Cursor and more.

Headroom June 8, 2026

Headroom: the context compression layer yo...

Deep dive into Headroom, the open-source project (33.4k ⭐) that promises 60-95% token reduction on what you send to an LLM without losing accuracy. We test its 6 algorithms, its reversible CCR, and its proxy mode, and compare it to the rest of the ecosystem.

AI June 5, 2026

GSD Core: the Anti-Ceremony Framework That...

Deep dive into GSD Core (formerly Get Shit Done): 33 agents, wave execution, 200K fresh context per subagent, and the Discuss→Plan→Execute→Verify→Ship phase loop. How to install it, when to use it, and when not to.