A terminal coding agent in Python — streaming agentic loop, 13 built-in tools, MCP servers, subagents, context compaction, and a configurable approval layer for shell and file operations.
A terminal coding agent in Python — streaming agentic loop, 12 built-in tools, MCP servers, subagents, context compaction, and a configurable approval layer for shell and file operations.
AshCode reads and writes files, runs shell commands, searches the web, and delegates work to scoped subagents — driven by any OpenAI-compatible model endpoint. Built from scratch to understand what actually goes into a coding agent: not just the tool-calling loop, but context management under a finite window, safety gating on destructive operations, and recovery when the model gets stuck.
Single-shot mode. One prompt, one answer — the agent picks its own tools and exits. python main.py "list the files in this directory"
Video demos: ▶ reading through a codebase · ▶ creating and deleting a file
- Why this exists - Features - Architecture - Install - Usage - Configuration - Extending - Engineering notes - Testing - Project layout
Wrapping a chat completion in a while loop gets you a demo. The gap between that and a usable agent is made of unglamorous problems, and this project is an attempt to solve them properly rather than skip them:
- The context window fills up. A real session blows past the limit in twenty minutes. AshCode compacts history into a structured summary at 80% capacity and separately clears stale tool outputs, so long sessions degrade gracefully instead of erroring. - Models get stuck. They will call the same failing tool forever. A signature-based loop detector catches exact repeats and short cycles, then injects a corrective prompt. - Agents r
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/AuthRan--AshCode.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.