Comparison
agents vs viewer
Verdict
Pick agents when tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering; pick viewer when tags unique to viewer: python.
Markdown twin · agents alternatives · viewer alternatives
GraphCanon updated today
Trust & integrity
| Signal | agents | viewer |
|---|---|---|
| Maintenance | Very active (2d since push) As of today · github_public_v1 | Dormant (1433d since push) As of today · github_public_v1 |
| Provenance | Not a fork · Personal account As of today · github_public_v1 | Not a fork · Organization account As of today · github_public_v1 |
| Security (OSV) | No MCP manifest As of today · mcp_manifest | No lockfile As of today · none |
Tagline
- agents
- Multi-harness agentic plugin marketplace for various AI agents
- viewer
- ML models and internal tensors 3D visualizer
Stars
- agents
- 38k
- viewer
- 1.8k
Forks
- agents
- 4.0k
- viewer
- 168
Open issues
- agents
- 1
- viewer
- 17
Language
- agents
- Python
- viewer
- Python
Adopt for
- 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
- viewer
- -
Persona
- agents
- -
- viewer
- -
Runtime
- agents
- -
- viewer
- -
License
- agents
- MIT
- viewer
- -
Last pushed
- agents
- Jul 8, 2026
- viewer
- Aug 8, 2022
Categories
- agents
- AI Agents, Developer Tools
- viewer
- Developer Tools
Trust and health
Maintenance
- agents
- Very active (96%)
- viewer
- Dormant (18%)
Days since push
- agents
- 2d
- viewer
- 1433d
Open issues (now)
- agents
- 1
- viewer
- 17
Owner type
- agents
- User
- viewer
- Organization
Security scan
- agents
- No MCP manifest
- viewer
- No lockfile
Full report
- agents
- Trust report
- viewer
- Trust report
Choose agents if…
- Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering.
- Also covers AI Agents.
- 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
- 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
- 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
Choose viewer if…
- Tags unique to viewer: python.
When NOT to use viewer
- Last GitHub push was 1434 days ago (dormant maintenance, Aug 8, 2022). Validate activity before betting a new project on viewer.
- Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (wshobson/agents) · observed Jul 11, 2026
- GitHub forks (wshobson/agents) · observed Jul 11, 2026
- Last push (wshobson/agents) · observed Jul 8, 2026
- License file (MIT) · observed Jul 11, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (zetane/viewer) · observed Jul 11, 2026
- GitHub forks (zetane/viewer) · observed Jul 11, 2026
- Last push (zetane/viewer) · observed Aug 8, 2022
- License file (unknown) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: agents 38k · viewer 1.8k (synced Jul 11, 2026).
Common questions
- What is the difference between agents and viewer?
- agents: Multi-harness agentic plugin marketplace for various AI agents. viewer: ML models and internal tensors 3D visualizer. See the comparison table for live GitHub stats and shared categories.
- When should I choose agents over viewer?
- Choose agents over viewer when Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering; Also covers AI Agents; 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 choose viewer over agents?
- Choose viewer over agents when Tags unique to viewer: python.
- When should I avoid agents?
- 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 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
- When should I avoid viewer?
- Last GitHub push was 1434 days ago (dormant maintenance, Aug 8, 2022). Validate activity before betting a new project on viewer. Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
- Is agents or viewer more popular on GitHub?
- agents has more GitHub stars (37,779 vs 1,832). Stars measure visibility, not whether either tool fits your constraints.
- Are agents and viewer open source?
- Yes - both are open-source projects on GitHub.
- Where can I find alternatives to agents or viewer?
- GraphCanon lists graph-backed alternatives at agents alternatives and viewer alternatives (agents markdown twin, viewer markdown twin), ranked by typed relationship edges rather than popularity votes.
- 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, agents or viewer?
- agents: Very active. viewer: Dormant. 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 agents and viewer?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: agents trust report; viewer trust report.