pynydus.agents.openclaw.spawner

OpenClaw spawner connector. Spec §10.3.

Parses an OpenClaw workspace directory containing:

  • SOUL.md / soul.md -> memory records labeled “persona”

  • IDENTITY.md -> memory records labeled “persona”

  • AGENTS.md -> memory records labeled “flow”

  • BOOT.md / HEARTBEAT.md -> memory records labeled “flow”

  • USER.md -> memory records labeled “context”

  • TOOLS.md -> memory records labeled “context”

  • knowledge.md / MEMORY.md -> memory records labeled “state”

  • memory/YYYY-MM-DD.md -> memory records labeled “state”

  • skill.md / skills.md / skills/ -> skill records

  • config.yaml / config.json -> secret requirements

Module Contents

Classes

OpenClawSpawner

Parse OpenClaw workspace directory.

Functions

_split_markdown_sections

Split markdown into sections by headings. Returns [{name, content}].

Data

_PERSONA_FILES

_FLOW_FILES

_CONTEXT_FILES

_STATE_FILES

_SKILL_FILES

FILE_PATTERNS

Glob patterns the pipeline uses to read source files from disk.

API

pynydus.agents.openclaw.spawner._PERSONA_FILES

(‘SOUL.md’, ‘soul.md’, ‘IDENTITY.md’)

pynydus.agents.openclaw.spawner._FLOW_FILES

(‘AGENTS.md’, ‘agents.md’, ‘BOOT.md’, ‘HEARTBEAT.md’)

pynydus.agents.openclaw.spawner._CONTEXT_FILES

(‘USER.md’, ‘user.md’, ‘TOOLS.md’)

pynydus.agents.openclaw.spawner._STATE_FILES

(‘knowledge.md’, ‘MEMORY.md’)

pynydus.agents.openclaw.spawner._SKILL_FILES

(‘skill.md’, ‘skills.md’)

pynydus.agents.openclaw.spawner.FILE_PATTERNS

[’.md’, ‘.yaml’, ‘.yml’, ‘.json’, ‘.txt’, ‘skills/.md’, ‘memory/*.md’]

Glob patterns the pipeline uses to read source files from disk.

class pynydus.agents.openclaw.spawner.OpenClawSpawner

Bases: pynydus.api.protocols.Spawner

Parse OpenClaw workspace directory.

FILE_PATTERNS

None

parse(files: dict[str, str]) → pynydus.api.raw_types.ParseResult

Parse pre-redacted file contents into raw skills and memory.

Args: files: filename -> UTF-8 content (already redacted).

Returns: Skills, memory, and MCP configs.

_parse_skills(files: dict[str, str]) → list[pynydus.api.raw_types.RawSkill]

Parse skills from file contents dict.

_parse_memories(files: dict[str, str]) → list[pynydus.api.raw_types.RawMemory]

Parse memory from all recognized OpenClaw workspace files.

static _parse_mcp_configs(files: dict[str, str]) → dict[str, dict]
pynydus.agents.openclaw.spawner._split_markdown_sections(text: str) → list[dict[str, str]]

Split markdown into sections by headings. Returns [{name, content}].