Comparison
core vs agents
Verdict
Unverified catalog guidance: core: RedPlanetHQ/core offers an AI framework for personalized assistants focusing on ai-agent capabilities, ai-memory, and automation. It is self-hosted and open-source under the AGPL 3.0 license. agents: The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot.
Markdown twin · core alternatives · agents alternatives
GraphCanon updated Sep 20, 2026
Trust & integrity
| Signal | core | agents |
|---|---|---|
| Maintenance | Active (12d since push) As of Sep 20, 2026 · github_public_v1 | Very active (1d since push) As of Sep 20, 2026 · github_public_v1 |
| Provenance | Not a fork · Organization account As of Sep 20, 2026 · github_public_v1 | Not a fork · Personal account As of Sep 20, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Aug 2, 2026 · osv@v1 | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
| MCP manifest observations | No supported MCP manifest observed in this scan As of Jul 15, 2026 · mcp_manifest@v1 | No supported MCP manifest observed in this scan As of Jul 11, 2026 · mcp_manifest@v1 |
Tagline
- core
- Your Personal AI OS
- agents
- Multi-harness agentic plugin marketplace for various AI agents
Stars
- core
- 2.0k
- agents
- 40k
Forks
- core
- 194
- agents
- 4.2k
Open issues
- core
- 211
- agents
- 12
Language
- core
- TypeScript
- agents
- Python
Adopt for
- core
- Unverified catalog guidance: RedPlanetHQ/core offers an AI framework for personalized assistants focusing on ai-agent capabilities, ai-memory, and automation. It is self-hosted and open-source under the AGPL 3.0 license.
- agents
- Unverified catalog guidance: The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot
Persona
- core
- -
- agents
- -
Runtime
- core
- -
- agents
- -
License
- core
- Other
- agents
- MIT
Last pushed
- core
- Sep 7, 2026
- agents
- Sep 19, 2026
Categories
- core
- AI Agents, Developer Tools
- agents
- AI Agents, Developer Tools
Trust and health
Maintenance
- core
- Active (82%)
- agents
- Very active (96%)
Days since push
- core
- 12d
- agents
- 1d
Open issues (recorded)
- core
- 211
- agents
- 12
Stars delta
- core
- +38 (30d)
- agents
- +895 (30d)
Open issues delta
- core
- +3 (30d)
- agents
- +7 (30d)
Owner type
- core
- Organization
- agents
- User
Full report
- core
- Trust report
- agents
- Trust report
Choose core if…
- core is primarily TypeScript; agents is Python.
- License: core is Other, agents is MIT.
- Tags unique to core: ai-agent, ai-memory, automations, developer-tools.
- Unverified catalog guidance: When you require a personalized AI assistant that can integrate with multiple services you use daily.
When NOT to use core
- Unverified catalog guidance: If you prefer cloud-based solutions over self-hosted options as RedPlanetHQ/core requires local hosting to ensure data privacy and control.
- Unverified catalog guidance: When looking for a chatbot that operates on-demand instead of an AI assistant that is constantly active in the background.
Choose agents if…
- agents is primarily Python; core is TypeScript.
- License: agents is MIT, core is Other.
- Tags unique to agents: agent-skills, agentic-ai, prompt-engineering, workflows.
- Unverified catalog guidance: You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments
When NOT to use agents
- Unverified catalog guidance: You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support
- Unverified catalog guidance: Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (RedPlanetHQ/core) · observed Sep 20, 2026
- GitHub forks (RedPlanetHQ/core) · observed Sep 20, 2026
- Last push (RedPlanetHQ/core) · observed Sep 7, 2026
- License file (Other) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Aug 2, 2026
- GitHub stars (wshobson/agents) · observed Sep 20, 2026
- GitHub forks (wshobson/agents) · observed Sep 20, 2026
- Last push (wshobson/agents) · observed Sep 19, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: core 2.0k · agents 40k (synced Sep 20, 2026).
Common questions
- What is the difference between core and agents?
- core: Your Personal AI OS. agents: Multi-harness agentic plugin marketplace for various AI agents. See the comparison table for recorded GitHub metadata and shared categories.
- When should I choose core over agents?
- For core, compare these recorded points with agents: core is primarily TypeScript; agents is Python; License: core is Other, agents is MIT; Tags unique to core: ai-agent, ai-memory, automations, developer-tools; Unverified catalog guidance: When you require a personalized AI assistant that can integrate with multiple services you use daily.
- When should I choose agents over core?
- For agents, compare these recorded points with core: agents is primarily Python; core is TypeScript; License: agents is MIT, core is Other; Tags unique to agents: agent-skills, agentic-ai, prompt-engineering, workflows; Unverified catalog guidance: You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments.
- When should I avoid core?
- Unverified catalog guidance: If you prefer cloud-based solutions over self-hosted options as RedPlanetHQ/core requires local hosting to ensure data privacy and control. Unverified catalog guidance: When looking for a chatbot that operates on-demand instead of an AI assistant that is constantly active in the background.
- When should I avoid agents?
- Unverified catalog guidance: You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support Unverified catalog guidance: Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem
- Is core or agents more popular on GitHub?
- agents has more recorded GitHub stars (39,823 vs 1,985). Stars measure visibility, not whether either tool fits your constraints.
- Which licenses are recorded for core and agents?
- core: Other. agents: MIT. Check each repository's current license and terms before use. Public GitHub hosting alone does not establish open-source licensing.
- Where can I find alternatives to core or agents?
- GraphCanon lists candidates at core alternatives and agents alternatives (core markdown twin, agents markdown twin). The discovery order uses stored relationship proposals and shared categories; it is not a verified replacement ranking.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, core or agents?
- core: Active. agents: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for core and agents?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: core trust report; agents trust report.