OpenClaw — CodeDocs Vault

OpenClaw

Open-source Claude-Code-style agent reproduction. Bigger than NanoClaw, reveals which patterns scale and which stay minimal.

Pedagogical: ★★★★☆
Flags: md-skills · streaming
Concepts: agent-loop ·tool-calling-formats ·prompt-caching ·skills-as-md ·streaming-tools
Verified: paper-pass
Upstream: —

Mark "OpenClaw" as studied

What it is

Open-source Claude-Code-style agent reproduction. Bigger than NanoClaw, reveals which patterns scale and which stay minimal.

The full per-doc analysis lives below — these are the original numbered analyses, rendered as styled HTML. Pick a section to study deeper.

Agent loop The skeleton every agent shares — read state, ask the model, parse, act, repeat — and how the wiring choices shape every other system around it.
Prompt caching Pay 10–50% of input cost on cached tokens. The art is choosing where the static-vs-dynamic boundary lives.
Skills as markdown Move agent expertise out of code and into versionable markdown. Domain experts contribute via PR; the loop almost never changes.
Streaming tool calls Don't wait for the full response. Parse tool calls as they stream and dispatch the moment you have enough — sometimes earlier.
Tool calling formats How the agent and the model agree on 'I want to run this function.' Get this wrong and you're locked into one provider, can't stream cleanly, or pay for trailing hallucination.