Archon alternatives
6 agents tools in the same lane as Archon, ranked by editorial score.
GE
gpt-engineer
Agents · OpenAI GPT (default), Anthropic Claude, Azure OpenAI, and open-weights models like WizardCoder via configuration
Describe software in natural language, watch an AI agent write, run, and improve it.
Free· Free and open source under MIT license. Users pay only for the underlying LLM API calls (OpenAI, Anthropic, Azure OpenAI) or run local models at zero token cost.Greenfield script and prototype generationSmall single-file utility creation from a spec
AI
AionUi
Agents · Model-agnostic: routes to Claude, GPT-4/5, Gemini, DeepSeek, Qwen, Kimi, plus local Ollama and LM Studio runtimes and any OpenAI-compatible endpoint.
Open-source desktop cowork app that unifies 20+ AI coding agents and CLI models in a single graphical workspace.
Free· Free and open-source under Apache-2.0. You bring your own API keys (Gemini, Claude, OpenAI, Qwen, DeepSeek, etc.) and pay each provider directly, or run local models via Ollama or LM Studio at zero token cost.Unified control panel for multiple CLI coding agentsLocal-first AI chat with private SQLite history
OP
OpenHands
Agents · Multi-model (Claude, Gemini, GPT/Codex)
8.0
Open-source autonomous coding agent that plans, edits, and ships changes across real codebases.
Freemium· Open Source: Free · Individual: Free · Enterprise: Custom pricingautonomous-codingpr-review
AG
AgentMemory
Agents · Multi-model (Claude, Gemini, MiniMax, OpenRouter)
7.3
Open-source persistent memory runtime for AI coding agents, with hybrid retrieval and zero external dependencies.
Free· Free, open-source (Apache 2.0); bring your own LLM API keyagent-memorycoding-agents
AP
Approving
Agents · Model-agnostic; routes to ACP backends including Cursor, Claude Code, CodeBuddy, and Trae
Visual orchestration for coding agents with human approval gates and sandboxed execution
Free· Free / MIT-licensed open source. Self-hosted; infrastructure costs (Docker host, agent API tokens) are on you.Multi-agent code delivery pipelinesHuman-approved MR/PR generation
CM
claude-mem
Agents · Model-agnostic — works with the models used by the connected agent (Claude, GPT, Gemini, etc.) via MCP
Persistent, cross-agent memory for Claude Code and other coding assistants
Freemium· Pro: $30/mo · Team Cloud: $333 per seat per monthPersistent memory for Claude Code sessionsCross-IDE context sharing via MCP