Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.compose.market/llms.txt

Use this file to discover all available pages before exploring further.

Manowar lets the model reason, but keeps execution contracts typed. The clearest example is the Manowar Agent Loop (mal) harness.

​
Typed Surfaces

SurfaceType sourceRuntime behavior
ToolsJSON Schema or ZodConverted into OpenAI-style function tools.
MAL plansharness/types.ts plus interpreter validationParsed from YAML/JSON and dispatched by closed op enum.
SubagentsSubAgentSpecRequires deployed agentWallet, explicit model, budgets, and depth.
Memory loopAgentMemoryScope and workflow response typesEnforces scope and step names.
TelemetryUsageRecord, FeedbackRecord, RunMetadataRecordNormalizes provider usage into runtime records.

​
MAL Ops

OpPurpose
taskSpawn a focused registered subagent.
delegateCall a registered deployed agent.
fanoutRun branches with controlled concurrency.
toolCall a registered tool directly.
ifBranch on a safe mini expression.
loopRepeat a bounded block.
scratchRead/write private run state.
synthesizeCombine saved values with an explicit model.
stopReturn final output.
ask_userRequest host-provided input.

​
Example

description: "Research, draft, and synthesize"
budget:
  maxDepth: 3
  maxWallMs: 300000
steps:
  - op: delegate
    saveAs: research
    agentWallet: "0x1111111111111111111111111111111111111111"
    prompt: "Collect source-backed notes for the topic."

  - op: synthesize
    saveAs: answer
    from: ["research"]
    model: "gpt-5.5"
    instruction: "Write a concise answer using only the saved notes."

  - op: stop
    output: "{{answer}}"
The interpreter validates the plan, resolves {{step.path}} references, executes each step, and records step results. The model does not parse an English instruction manual on every step.