--- title: "FLAML vs agents" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-flaml-vs-wshobson-agents" tools: ["microsoft-flaml", "wshobson-agents"] --- # FLAML vs agents *GraphCanon updated Jul 11, 2026* ## Verdict Pick FLAML when fLAML is primarily Jupyter Notebook; agents is Python; pick agents when agents is primarily Python; FLAML is Jupyter Notebook. [FLAML](https://microsoft.github.io/FLAML/) reports 4.4k GitHub stars, 558 forks, and 182 open issues, last pushed Jul 11, 2026. [agents](https://sethhobson.com) has 38k stars, 4.0k forks, and 1 open issues, last pushed Jul 8, 2026. Figures are from public GitHub metadata via [FLAML's repository](https://github.com/microsoft/FLAML) and [agents's repository](https://github.com/wshobson/agents). | | [FLAML](/tools/microsoft-flaml.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Tagline | A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP. | Multi-harness agentic plugin marketplace for various AI agents | | Stars | 4,373 | 37,779 | | Forks | 558 | 4,050 | | Open issues | 182 | 1 | | Language | Jupyter Notebook | Python | | Adopt for | - | 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 | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [FLAML](/tools/microsoft-flaml.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Days since push | 0d | 2d | | Open issues (now) | 182 | 1 | | Owner type | Organization | User | | Security scan | No lockfile | No MCP manifest | | Full report | [trust report](/tools/microsoft-flaml/trust.md) | [trust report](/tools/wshobson-agents/trust.md) | ## Decision facts: agents - **Adopt for:** 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 ## Choose when ### Choose FLAML if… - FLAML is primarily Jupyter Notebook; agents is Python. - Tags unique to FLAML: automl, data-science, hyperparam, deep-learning. - FLAML ships Docker support for self-hosted deployment. ### Choose agents if… - agents is primarily Python; FLAML is Jupyter Notebook. - 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 FLAML - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ## 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 ## Common questions ### What is the difference between FLAML and agents? FLAML: A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.. 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 FLAML over agents? Choose FLAML over agents when FLAML is primarily Jupyter Notebook; agents is Python; Tags unique to FLAML: automl, data-science, hyperparam, deep-learning; FLAML ships Docker support for self-hosted deployment. ### When should I choose agents over FLAML? Choose agents over FLAML when agents is primarily Python; FLAML is Jupyter Notebook; 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 FLAML? 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 FLAML or agents more popular on GitHub? agents has more GitHub stars (37,779 vs 4,373). Stars measure visibility, not whether either tool fits your constraints. ### Are FLAML and agents open source? Yes - both are open-source projects on GitHub (FLAML: MIT, agents: MIT). ### Where can I find alternatives to FLAML or agents? GraphCanon lists graph-backed alternatives at [FLAML alternatives](/tools/microsoft-flaml/alternatives) and [agents alternatives](/tools/wshobson-agents/alternatives) ([FLAML markdown twin](/tools/microsoft-flaml/alternatives.md), [agents markdown twin](/tools/wshobson-agents/alternatives.md)), 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](/compare/microsoft-flaml-vs-wshobson-agents.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, FLAML or agents? FLAML: 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 FLAML and agents? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [FLAML trust report](/tools/microsoft-flaml/trust); [agents trust report](/tools/wshobson-agents/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-flaml`](/api/graphcanon/graph?tool=microsoft-flaml) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_