← Back to Skills Marketplace
ontology
by
oswalpalash
· GitHub ↗
· v1.0.4
· MIT-0
193767
Downloads
650
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install ontology
Description
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Usage Guidance
Install this only if you want agents to keep a durable local knowledge graph. Avoid storing passwords, tokens, API keys, or raw secrets; use secret references only. Periodically inspect memory/ontology/graph.jsonl and schema.yaml because updates and deletes are represented through appended history and shared state may be read by other skills.
Capability Analysis
Type: OpenClaw Skill
Name: ontology
Version: 1.0.4
The 'ontology' skill provides a robust framework for managing a local knowledge graph (entities and relations) stored in JSONL format. The implementation in `scripts/ontology.py` includes proactive security measures such as a `resolve_safe_path` function to prevent path traversal and schema constraints in `references/schema.md` that explicitly forbid storing raw secrets like passwords or tokens. The logic is transparent, well-documented, and strictly focused on its stated purpose of structured memory management.
Capability Assessment
Purpose & Capability
The stated purpose, documentation, and Python CLI align around creating, querying, linking, and validating ontology graph data. It can store personal, project, message, account, and credential-reference metadata, so the graph may become sensitive even though raw secrets are explicitly discouraged.
Instruction Scope
Runtime instructions are scoped to local ontology files under memory/ontology and disclose shared-state use. The trigger phrase "remember" is broad, and validation is available but not consistently shown as an automatic gate before every write, so users should control when persistent writes happen.
Install Mechanism
No install-time commands, package fetching, network setup, or privilege escalation were found. The artifacts are Markdown references plus a local Python CLI.
Credentials
The script uses local file reads and writes consistent with a workspace memory store, includes workspace-bound path resolution for supplied graph/schema/input paths, and shows no network calls, subprocess execution, environment scraping, or credential harvesting.
Persistence & Privilege
The skill intentionally creates durable append-only graph history and can merge schema changes under memory/ontology. Deletes are logical graph operations rather than file removal, and no background execution or elevated OS privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ontology - After installation, invoke the skill by name or use
/ontology - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- Initial release of the ontology skill for typed, constraint-validated knowledge graphs.
- Supports entity and relation CRUD, property and relation validation, and graph traversal for common types such as Person, Project, Task, Event, and Document.
- Provides schema-driven constraints including required properties, enums, forbidden fields, cardinality, and acyclicity.
- Enables multi-step planning and shared memory across skills via structured ontology objects.
- Includes CLI tooling for creating, querying, linking, and validating graph data using JSONL storage.
v0.1.2
No functional or documentation changes were detected in this release.
- Version bumped to 0.1.2 with no file or content changes.
v0.1.1
- Added an "Append-Only Rule" to encourage appending or merging ontology data and schema changes rather than overwriting files, preserving history and prior definitions.
- Updated quick start instructions to use `schema-append` for safely modifying schemas instead of direct file editing.
- Expanded the documentation to clarify that runtime commands and validations operate on local files, create necessary directories, and are within the skill's supported behaviors.
- Clarified the scope of validation: property, enum, forbidden checks, relation validation, acyclicity, and specific Event constraints are supported; higher-level constraints remain documentation unless implemented.
v0.1.0
Initial release: typed knowledge graph for agent memory, entity CRUD, relations, constraints, skill interop
Metadata
Frequently Asked Questions
What is ontology?
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin... It is an AI Agent Skill for Claude Code / OpenClaw, with 193767 downloads so far.
How do I install ontology?
Run "/install ontology" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ontology free?
Yes, ontology is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ontology support?
ontology is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ontology?
It is built and maintained by oswalpalash (@oswalpalash); the current version is v1.0.4.
More Skills