Building A Coding Agent From Scratch Course

From agent user to agent builder: build a Claude Code-style coding agent from scratch in Python: 8 articles, 4 videos, one codebase

LLM Mart
2 views 79 listing impressions
0 Visit tool

Try the finished agent first — 5 minutes, $0:

git clone https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-course.git
cd building-a-coding-agent-from-scratch-course
make install
cp .env.example .env   # set LLM API key
uv run decode

Then type /demo- and pick a demo — see what they do below. Full setup guide.

The demo skills listed inside the decode TUI after typing /demo-

Type /demo- and the six demos are one keystroke away.

📖 About This Course

In LangChain's Terminal-Bench experiment, changing only the harness (with the same model) moved a coding agent from ~30th place into the top 5: the harness, not the model, is what makes a coding agent good.

The agent is ~20 lines. The course is everything else.

agent = Agent(
    build_model(settings.llm_provider),        # gemini | openrouter | modal
    deps_type=AgentDeps,                       # cwd, event sink, permission gate
    output_type=[str, DeferredToolRequests],   # final answer, or tools paused for approval
)
register_tools(agent)                          # read, edit, bash, grep, ...

async with agent.iter(prompt, message_history=history) as run:
    async for node in run:                     # model request → tool calls → repeat
        stream_events(node)

That's the entire tool-calling agent. Everything else in this repo: the tools, skills, the permission layer, sandbox, steering queue, memory, compaction, session recording & replay, remote execution, the subagent fan-out, the evals, is the harness. That's what you're here to build.

A fresh decode session: Opik tracing on, a Modal-served Qwen model, skill autocomplete, steering keys in the footer
A fresh session powered by Qwen 3.6 35B hosted on Modal

We spent months under the hood of Claude Code (via its leaked source), OpenCode, Pi, and Aider, then distilled it into 8 articles and 4 videos where you'll build decode, your own coding agent, from scratch. One headless core hooked to two modes: an interactive TUI and Modal serverless functions running N copies in parallel, fired by CLI, webhook, or cron.

Diagram of a coding agent harness: two interfaces (Interactive TUI with steering queue and priority gate; Remote Modal runtime running N headless harnesses via CLI, webhook, or cron) drive one Headless Harness made of a Context Window with compaction, an LLM-to-Tools Agent Loop, and six modules (LLM Providers, Memory, Skills, Sandbox, Permissions, LSP Server). An Evals and Observability layer (benchmarks, regressions, replays via Opik and Kitaru) sits underneath.

The architecture of the harness of the coding agent you will build during this course.

🎮 See It Work

The finished agent ships with demo skills under .decode/skills/. Open the TUI, type /demo-, pick one, and watch the harness you're about to build do real work:

The demo skills listed inside the decode TUI after typing /demo-
Implement the Skills Standard
Type /demo- and the six demos are one keystroke away.

From the project's README.

Comments (0)

Sign in to join the conversation.

No comments yet.