Agent tools

Tools for running agents on an InferOptimal endpoint.

Compare the harnesses on one model in the harness results.

Get the agents script

Every install line below runs ~/.inferoptimal/agents.mjs. Download it once (Node 20 or later):

mkdir -p ~/.inferoptimal && curl -fsSL https://www.inferoptimal.com/agents/inferoptimal-agents.mjs -o ~/.inferoptimal/agents.mjs

Or ask your agent to call query action get_codex_config over MCP. It returns the same download and install in one paste.

Every tool

  1. InferOptimal OpenEvolve tool Recommended

    Recommended for well-defined tasks with a reward that can be hill-climbed: a score you can compute for every candidate and want to raise.

    Fits: A program, prompt or configuration with a score you can measure and want to raise.

    Install: node ~/.inferoptimal/agents.mjs tool install openevolve

    Read the InferOptimal OpenEvolve tool guide

  2. Microsoft Agent Framework fan-out Recommended

    Recommended as the best overall harness we measured, with known failure modes where it fails completely: document retrieval, finding vulnerable files, a run that ends at its time cap with no answer, and very heavy token use.

    Fits: A hard question over many documents, worked as parallel lines of inquiry; uses many tokens.

    Install: node ~/.inferoptimal/agents.mjs tool install agent-framework

    Read the Microsoft Agent Framework fan-out guide

  3. DeepSeek Harness on your endpoint Recommended

    Recommended as the safer alternative harness. That is our recommendation, resting on measured facts: one agent ended each of its short-task runs in minutes, none at the time cap, and was right 5 of 9 times on hard research. Its own measured weakness: one agent can run into the output limit on a long answer and end with none.

    Fits: One hard task over a folder or repository for one persistent agent.

    Install: node ~/.inferoptimal/agents.mjs tool install deepseek-harness

    Read the DeepSeek Harness on your endpoint guide

  4. InferOptimal subagents

    Fits: Many separate coding tasks at once: features, fixes, tests or research across a repository.

    Guide: node ~/.inferoptimal/agents.mjs guide subagents

  5. OpenResearch add-on for the OpenEvolve tool In development

    In development: still offered, but not recommended yet, because it is not performing well enough. Its measured results are below.

    Fits: A research question with no fixed metric; a buried detail may override the obvious answer.

    Install: node ~/.inferoptimal/agents.mjs tool install openresearch

    Read the OpenResearch add-on for the OpenEvolve tool guide

  6. InferOptimal web tools

    Fits: A swarm that collects data from the web: searching, reading and extracting across many sources.

    Install: node ~/.inferoptimal/agents.mjs tool install web --tier <read|collect|browse>