Home/Compare/google-research vs agents

Comparison

google-research vs agents

Verdict

Pick google-research when google-research is primarily Jupyter Notebook; agents is Python; pick agents when agents is primarily Python; google-research is Jupyter Notebook.

Markdown twin · google-research alternatives · agents alternatives

GraphCanon updated today

google-research logo

google-research

google-research/google-research

38kpushed Jul 11, 2026
vs
agents logo

agents

wshobson/agents

38kpushed Jul 8, 2026

Trust & integrity

Signalgoogle-researchagents
Maintenance
Very active (0d since push)
As of today · github_public_v1
Very active (2d since push)
As of today · github_public_v1
Provenance
Not a fork · Organization account
As of today · github_public_v1
Not a fork · Personal account
As of today · github_public_v1
Security (OSV)
No lockfile
As of today · none
No MCP manifest
As of today · mcp_manifest

Tagline

google-research
Google Research
agents
Multi-harness agentic plugin marketplace for various AI agents

Stars

google-research
38k
agents
38k

Forks

google-research
8.5k
agents
4.0k

Open issues

google-research
2.0k
agents
1

Language

google-research
Jupyter Notebook
agents
Python

Adopt for

google-research
-
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

Persona

google-research
-
agents
-

Runtime

google-research
-
agents
-

License

google-research
Apache-2.0
agents
MIT

Last pushed

google-research
Jul 11, 2026
agents
Jul 8, 2026

Categories

google-research
Developer Tools
agents
AI Agents, Developer Tools

Trust and health

Days since push

google-research
0d
agents
2d

Open issues (now)

google-research
2.0k
agents
1

Owner type

google-research
Organization
agents
User

Security scan

google-research
No lockfile
agents
No MCP manifest

Full report

google-research
Trust report

Choose google-research if…

  • google-research is primarily Jupyter Notebook; agents is Python.
  • License: google-research is Apache-2.0, agents is MIT.
  • Tags unique to google-research: research, ai, machine-learning, jupyter notebook.

When NOT to use google-research

  • Developer Tools: A gateway is overkill when you're pinned to a single provider and model.

Choose agents if…

  • agents is primarily Python; google-research is Jupyter Notebook.
  • License: agents is MIT, google-research is Apache-2.0.
  • Tags unique to agents: agent-skills, workflows, agentic-ai, 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

Explore

Sources

Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.

GitHub stars on cards: google-research 38k · agents 38k (synced Jul 11, 2026).

Common questions

What is the difference between google-research and agents?
google-research: Google Research. agents: Multi-harness agentic plugin marketplace for various AI agents. See the comparison table for live GitHub stats and shared categories.
When should I choose google-research over agents?
Choose google-research over agents when google-research is primarily Jupyter Notebook; agents is Python; License: google-research is Apache-2.0, agents is MIT; Tags unique to google-research: research, ai, machine-learning, jupyter notebook.
When should I choose agents over google-research?
Choose agents over google-research when agents is primarily Python; google-research is Jupyter Notebook; License: agents is MIT, google-research is Apache-2.0; Tags unique to agents: agent-skills, workflows, agentic-ai, 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 avoid google-research?
Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
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
Is google-research or agents more popular on GitHub?
google-research has more GitHub stars (38,353 vs 37,779). Stars measure visibility, not whether either tool fits your constraints.
Are google-research and agents open source?
Yes - both are open-source projects on GitHub (google-research: Apache-2.0, agents: MIT).
Where can I find alternatives to google-research or agents?
GraphCanon lists graph-backed alternatives at google-research alternatives and agents alternatives (google-research markdown twin, agents 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, google-research or agents?
google-research: Very 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 google-research and agents?
GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: google-research trust report; agents trust report.